CN120126328A - Highway environment monitoring terminal based on the Internet of Things - Google Patents

Highway environment monitoring terminal based on the Internet of Things Download PDF

Info

Publication number
CN120126328A
CN120126328A CN202510606306.XA CN202510606306A CN120126328A CN 120126328 A CN120126328 A CN 120126328A CN 202510606306 A CN202510606306 A CN 202510606306A CN 120126328 A CN120126328 A CN 120126328A
Authority
CN
China
Prior art keywords
data
module
unit
time
real
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202510606306.XA
Other languages
Chinese (zh)
Inventor
林爱萍
曹洁梅
吴腾飞
邹泽昌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian Chuanzheng Communications College
Original Assignee
Fujian Chuanzheng Communications College
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujian Chuanzheng Communications College filed Critical Fujian Chuanzheng Communications College
Priority to CN202510606306.XA priority Critical patent/CN120126328A/en
Publication of CN120126328A publication Critical patent/CN120126328A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/20—Information sensed or collected by the things relating to the thing itself
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/30—Control
    • G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/009—Security arrangements; Authentication; Protecting privacy or anonymity specially adapted for networks, e.g. wireless sensor networks, ad-hoc networks, RFID networks or cloud networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/03—Protecting confidentiality, e.g. by encryption
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Environmental & Geological Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Business, Economics & Management (AREA)
  • Toxicology (AREA)
  • General Business, Economics & Management (AREA)
  • Medical Informatics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a highway environment monitoring terminal based on the Internet of things, and relates to the technical field of traffic environment monitoring. The highway environment monitoring terminal based on the Internet of things comprises an environment monitoring module, an edge computing module, an Internet of things communication module, a cloud analysis module, an intelligent linkage module, a power module and an equipment self-maintenance module. According to the intelligent traffic management system, the edge calculation module is used for carrying out real-time preprocessing and intelligent analysis on the environmental data, abnormal modes in the environmental data are rapidly identified, real-time analysis results are generated, the data transmission bandwidth requirement and the processing delay are greatly reduced, the cloud analysis module is used for providing a global evaluation result based on the deep learning model by combining the historical data and the real-time data, and therefore the intelligent traffic management decision is supported.

Description

Highway environment monitoring terminal based on thing networking
Technical Field
The invention relates to the technical field of traffic environment monitoring, in particular to a highway environment monitoring terminal based on the Internet of things.
Background
The conventional environment monitoring system mostly adopts a single sensor to collect environment data, and cannot comprehensively and real-timely dynamically monitor complex meteorological conditions, air quality and road conditions along a highway, particularly when sudden environment changes (such as heavy rainfall, road surface icing and air pollution events) occur, the response speed is slower. The data processing efficiency is low, the existing monitoring system generally depends on a centralized data processing architecture, and all data can be obtained after being uploaded to a cloud end for analysis. The architecture is easy to cause delay when the network is interrupted or the data volume is increased suddenly, and cannot meet the requirements of highway environment monitoring on real-time performance and high efficiency. The traditional monitoring system lacks intelligent analysis and prediction capability, and can not combine real-time and historical data to conduct trend prediction or anomaly detection. Meanwhile, the response mechanism for the emergency is mostly dependent on manual intervention, and early warning or linkage of related traffic management equipment is difficult to trigger in time. The system has insufficient reliability, equipment interference resistance and stability of the existing system are limited in a complex highway environment, and fault monitoring and maintenance capability of sensors and communication modules are weak, so that once equipment faults occur, the whole monitoring function is greatly influenced.
Based on the above problems, a technical solution capable of monitoring the environment along the road comprehensively and intelligently in real time is needed.
Disclosure of Invention
The invention provides a road environment monitoring terminal based on the Internet of things, which can monitor the environment along a road in real time and can perform intelligent analysis and linkage control on data through the organic combination of a multi-sensor array, edge calculation, cloud analysis and an intelligent linkage module, so that optimal decision support and emergency response capability are provided for traffic management departments.
Highway environment monitoring terminal based on thing networking includes:
the environment monitoring module is used for collecting real-time environment data along the road through the sensor array, including meteorological parameters, air quality parameters and road condition parameters, and the environment data are processed into structural information and transmitted to the edge calculation module;
The edge calculation module is connected with the environment monitoring module, processes the environment data in real time based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model and a prediction analysis sub-model, generates a real-time analysis result by primarily analyzing the environment data, comprises a data anomaly flag, a trend prediction result and event response information, and transmits the real-time analysis result to the Internet of things communication module and the intelligent linkage module;
The internet of things communication module is connected with the edge calculation module and is used for uploading the environment data and the real-time analysis result to the cloud analysis module, receiving the global evaluation result returned by the cloud analysis module and realizing interconnection and intercommunication between the terminal devices and stable communication with the cloud platform;
The cloud analysis module is connected with the edge calculation module through the communication module of the Internet of things, carries out global analysis and processing on the environmental data and the real-time analysis result based on a global evaluation model in the cloud, and the global evaluation model combines the historical data and the real-time data to generate a global evaluation result which comprises the prediction information of the environment, the optimization suggestion of traffic management and the response strategy of an emergency, and transmits the global evaluation result back to the communication module of the Internet of things;
The intelligent linkage module is respectively connected with the edge calculation module and the Internet of things communication module, and is used for receiving the real-time analysis result and the global evaluation result, and executing corresponding linkage control operation, including dynamically adjusting the operation parameters of the traffic management equipment, triggering the real-time warning equipment or sending control instructions to the management center.
As a preferred embodiment of the present invention, the environment monitoring module includes:
the sensor array includes:
the system comprises a meteorological sensor, a sensor and a wind speed sensor, wherein the meteorological sensor is used for collecting data related to meteorological conditions along a highway and comprises a temperature sensor, a humidity sensor and a wind speed sensor, and is used for respectively detecting ambient temperature, humidity and wind speed;
An air quality sensor for detecting the concentration of pollutants in air along a highway, wherein the air quality sensor comprises a PM2.5 sensor, a PM10 sensor and a carbon dioxide sensor, and is used for respectively detecting the concentration of fine particles, inhalable particles and carbon dioxide;
The road state sensor is used for collecting image data of the road surface to analyze accumulated water, icing, obstacles and traffic flow, the infrared sensor is used for detecting temperature distribution of the road surface to judge whether icing or temperature abnormality exists or not, and the humidity sensor is used for detecting the humidity level of the road surface to judge the accumulated water or wet and slippery condition;
the data processing unit is connected with the sensor array and is used for receiving the environmental data acquired by various sensors, processing the environmental data, removing abnormal data and noise data, converting the processed data into structured information in a uniform format and transmitting the structured information to the edge computing module.
As a preferred embodiment of the present invention, the edge calculation module includes:
the data receiving unit is used for receiving the environment data from the environment monitoring module;
the data preprocessing unit is connected with the data receiving unit and is used for processing the received environmental data, including removing repeated data and repairing lost data;
The real-time analysis unit is connected with the data preprocessing unit and is used for intelligently analyzing the processed data based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model, a prediction analysis sub-model and a data processing unit, wherein the anomaly detection sub-model is used for detecting an anomaly mode or an anomaly event in the data, and the anomaly mode or the anomaly event comprises accumulation of water, icing or air pollutant exceeding;
The result generation unit is connected with the real-time analysis unit and used for generating a real-time analysis result and transmitting the generated real-time analysis result to the Internet of things communication module and the intelligent linkage module.
As a preferred embodiment of the present invention, the real-time analysis model includes:
an anomaly detection sub-model adopts an anomaly classification algorithm based on a support vector machine to input environmental data Constructing a separation hyperplane in a high-dimensional space for judging whether data are abnormal points or not as feature vectors, wherein the hyperplane is defined by the following formula: Wherein As a weight vector of the weight vector,As a bias term, ifJudging normal data, otherwise judging abnormal data;
The abnormal detection sub-model is obtained through training of feature vectors extracted from a historical environment data set, and classification accuracy of abnormal data and normal data is used as an optimization target;
Trend prediction sub-model adopts time sequence prediction algorithm based on long-short time memory network to use time sequence of environment data Predicting environmental parameters at future time points as inputs;
the trend prediction sub-model is trained in a supervised learning mode, historical time sequence data and a corresponding future target value are used as training samples, and minimized mean square error is used as a loss function for optimization;
the real-time analysis model is obtained through pre-training, training data are derived from historical environment monitoring data, the data comprise meteorological data, air quality data and road state data, the training process is completed through a distributed computing platform and comprises four stages of data preprocessing, feature extraction, model training and parameter optimization, and a cross verification method is adopted to verify the performance of the model, and classification accuracy, prediction error and model convergence are used as model evaluation standards.
As a preferred technical solution of the present invention, the communication module of the internet of things includes:
The communication protocol unit is used for supporting wireless communication protocols, including LoRa, NB-IoT, 4G and 5G communication protocols, and automatically switching communication modes according to application scenes, wherein the application scenes comprise low power consumption, high bandwidth and long-distance transmission;
The data transmission unit is connected with the communication protocol unit and is used for uploading the environment data and the real-time analysis result generated by the edge calculation module to the cloud analysis module and receiving the global evaluation result returned by the cloud analysis module;
the data buffer unit is connected with the data transmission unit, and is used for temporarily storing environment data and real-time analysis results when communication is interrupted or the network is unstable, and automatically uploading the environment data and the real-time analysis results after communication is recovered;
The communication state monitoring unit is used for monitoring the running state of the communication module in real time, including the network connection state, the signal strength and the data transmission rate, and sending fault information to the equipment self-maintenance module when communication is abnormal;
the low-power consumption unit is used for optimizing the energy consumption of the communication module and dynamically adjusting the communication power and the working mode according to the data transmission task.
As a preferred technical solution of the present invention, the cloud analysis module includes:
the data receiving unit is used for receiving the environmental data and the real-time analysis result uploaded by the communication module of the Internet of things, classifying and storing the received data, and dividing the data into real-time data and historical data according to the time dimension so as to support the subsequent analysis;
the global evaluation unit is connected with the data receiving unit, performs global analysis and processing on the received data based on the global evaluation model, and generates the following three types of results:
The environment prediction information is based on a deep learning algorithm, and future environmental conditions including weather change trend, air quality distribution and future change of road state are predicted by extracting features of real-time environment data and combining with time sequence change rules of historical environment data;
The optimization proposal of traffic management is based on a graph convolution neural network and a long-short time memory network, and the dynamic change characteristics of traffic flow are analyzed through joint modeling of real-time traffic flow data and historical traffic data, so as to generate the optimization proposal of traffic management, including traffic signal lamp period adjustment, diversion route planning and traffic dispersion proposal;
the response strategy of the emergency event is that the current emergency event is identified through real-time environment data and by referring to similar event modes recorded in historical data, and a corresponding response strategy is generated, wherein the response strategy comprises real-time early warning information, road closing instructions and a warning signal triggering scheme;
The response strategy generation unit is connected with the global evaluation unit and is used for receiving environment prediction information, traffic management optimization suggestions and emergency response strategies and integrating the results into specific executable instructions;
The result sending unit is connected with the response strategy generating unit and is used for transmitting the environment prediction information, the traffic management optimization suggestions and the emergency response strategy to the communication module of the Internet of things for use by the terminal equipment or the traffic management center;
the model optimization unit is used for iterating a training deep learning algorithm and a traffic flow evaluation algorithm based on a graph convolution neural network and a long-time memory network based on the uploaded real-time data and historical data and actual execution feedback of a global evaluation result so as to improve the prediction precision and response efficiency of model output;
The cloud storage unit is used for storing historical environment data, global evaluation results and response strategies and providing long-term data support for the global evaluation unit and the model optimization unit.
As a preferred embodiment of the present invention, the global evaluation model includes:
An environment predictor model for generating prediction information of an environment, the environment predictor model constructed based on a deep learning algorithm, the training and use thereof comprising:
The method comprises the steps of extracting historical environment data from a cloud storage unit to serve as a training data set, capturing time sequence changes of the environment data by using a long-short-time memory network as a basic model, and optimizing the model by minimizing mean square error;
inputting the real-time environment data into an environment prediction sub-model, and generating environment prediction information in a future time period by combining the historical data;
the traffic flow evaluation sub-model is used for generating an optimization suggestion of traffic management, is constructed based on a combined algorithm of a graph convolution neural network and a long-time and short-time memory network, and is trained and used by the traffic flow evaluation sub-model, and comprises the following steps:
Modeling the spatial characteristics of the road network by using a graph convolution neural network, modeling the time characteristics of traffic flow data by using a long-short-term memory network, extracting the time sequence characteristics and combining the output of the graph convolution neural network;
Inputting traffic flow and a current road network topological structure, and generating an evaluation result of a current traffic flow state and traffic flow prediction in a future time period by combining historical traffic data;
An emergency recognition sub-model for generating a response strategy for an emergency, the emergency recognition sub-model constructed based on a combination algorithm of a convolutional neural network and a time convolutional network in deep learning, the training and use of the emergency recognition sub-model comprising:
The method comprises the steps of extracting historical emergency data and corresponding environmental data from a cloud storage unit as a training data set, extracting spatial features of the environmental data and traffic flow data by using a convolutional neural network, modeling time sequence features of the data by using a time convolutional network, constructing an emergency recognition model by combining the spatial features and the time sequence features, and optimizing by using a cross entropy loss function;
inputting real-time environment data and traffic flow data to generate an emergency detection result, and generating a corresponding response strategy according to the detection result.
As a preferred technical solution of the present invention, the intelligent linkage module includes:
The linkage data receiving unit is used for receiving the real-time analysis result from the edge calculation module and the global evaluation result of the cloud analysis module;
the linkage strategy analysis unit is connected with the linkage data receiving unit and is used for analyzing the global evaluation result pair and generating a corresponding control instruction according to the analysis result;
Judging weather change trend, air quality change and road state prediction in the environment prediction information, and determining whether to trigger an environment early warning instruction; analyzing the traffic signal lamp period adjustment, the diversion route planning and the traffic guiding scheme in the traffic management optimization suggestion to generate corresponding traffic signal equipment control instructions;
the device control unit is connected with the linkage strategy analysis unit and is used for executing the analyzed control instruction;
The device control comprises traffic signal device control, early warning broadcasting triggering, electronic display screen or other warning devices, and real-time early warning information providing for vehicles or personnel, wherein the traffic signal device control dynamically adjusts the period of traffic signal lamps, switches traffic signs or starts dynamic warning lamps;
The remote control module is used for sending a linkage control instruction to the traffic management center and supporting remote operation and manual intervention;
The state feedback unit is used for monitoring the execution state of the equipment in real time, and transmitting the execution state and feedback information to the cloud analysis module and the equipment self-maintenance module so as to facilitate subsequent optimization and fault processing;
The priority scheduling unit is connected with the linkage strategy analysis unit and is used for scheduling a plurality of linkage control instructions according to the priority, and when a plurality of linkage control tasks conflict, the linkage instructions are selectively executed according to the event type and the emergency degree.
As a preferred technical solution of the present invention, the present invention further includes:
the power module is used for intelligently supplying power to the highway environment monitoring terminal and supporting low-power-consumption operation of each module;
the power module includes:
The solar power supply unit is used for capturing light energy and converting the light energy into electric energy, and providing sustainable energy support for the terminal;
the energy storage battery unit is connected with the solar power supply unit and is used for storing redundant electric energy and supplying power to the terminal under the condition of insufficient illumination or no illumination;
The low-power consumption management unit is used for dynamically adjusting the power consumption state of each module, and optimizing power supply distribution by analyzing the running condition and the energy use requirement of the terminal;
the standby power supply unit is connected with the energy storage battery unit and is used for providing emergency power supply when the solar power supply and the energy storage battery are not available at the same time, so that the basic operation of the terminal is ensured;
The power state monitoring unit is used for monitoring the running states of the solar power supply unit, the energy storage battery unit and the standby power supply unit in real time, including electric quantity, output power and running efficiency, and transmitting monitoring results to the equipment self-maintenance module.
As a preferred technical solution of the present invention, the present invention further includes:
The equipment self-maintenance module is connected with the environment monitoring module, the edge computing module, the Internet of things communication module and the power module in the terminal, and is used for monitoring the running state of each module, executing automatic detection and diagnosis of equipment faults and transmitting fault diagnosis reports to the intelligent linkage module;
The device self-maintenance module comprises:
the state monitoring unit is used for monitoring the running states of the environment monitoring module, the edge computing module, the Internet of things communication module, the power module and the intelligent linkage module in real time, and comprises a working state, a data transmission state, a power state and a device connection state;
The fault detection unit is connected with the state monitoring unit and is used for analyzing the monitoring data and identifying the abnormality or fault in the operation of the module, including sensor failure, communication interruption, insufficient electric quantity and module hardware fault;
The diagnosis unit is connected with the fault detection unit and is used for generating a fault diagnosis report based on a fault detection result, wherein the fault diagnosis report comprises fault reasons, influence ranges and priority evaluation;
the fault response unit is connected with the diagnosis unit and is used for automatically taking corresponding response measures according to the fault diagnosis report, and the fault response unit comprises a restarting module, a communication path switching module, a standby power supply starting module or a fault alarm sending module;
the fault report unit is used for sending a fault diagnosis report and response measures to the cloud analysis module or the traffic management center through the communication module of the Internet of things;
the log recording unit is used for recording the equipment operation log and the fault diagnosis log, including time, position, fault type and processing result, and storing the log in the cloud storage unit.
The invention has the following advantages:
According to the invention, through various sensor arrays of the environment monitoring module, meteorological parameters, air quality parameters and road condition parameters along the road are collected in real time, and the monitoring data comprehensively cover various key environment factors along the road, so that accurate environment state information is provided for a road management department, and traffic safety is ensured.
The cloud analysis module is used for carrying out real-time preprocessing and intelligent analysis on the environmental data through the edge calculation module, rapidly identifying abnormal modes in the environmental data and generating real-time analysis results, reducing the data transmission bandwidth requirement and processing delay, and providing a global evaluation result based on a deep learning model by combining historical data and real-time data, so that the intellectualization of traffic management decisions is supported.
According to the invention, the intelligent linkage module dynamically adjusts the traffic management equipment, triggers the early warning equipment or sends the control instruction to the management center according to the real-time analysis result and the global evaluation result, and the automatic linkage control capability improves the emergency response efficiency under the emergency situation and reduces the time cost of human intervention;
the invention monitors the running states of the environment monitoring module, the edge computing module, the communication module, the power module and the like in real time through the equipment self-maintenance module, automatically detects equipment faults and generates a diagnosis report, thereby guaranteeing the long-term stable running of the system, and the system can realize high-reliability running in a complex highway environment through a fault response mechanism and can keep the normal running of the monitoring function even under the condition of equipment faults or communication interruption.
The solar energy power supply unit and the energy storage battery unit are provided, the low-power consumption management technology is combined, the power distribution can be dynamically adjusted according to the energy consumption requirement, the long-term operation of the equipment in the remote or highway environment lacking the power grid support is ensured, the utilization mode of the green energy source accords with the concept of energy conservation and environmental protection, and the operation and maintenance cost of the system is reduced.
Drawings
For a clearer description of an embodiment of the present invention or a technical solution in the prior art, the following description will briefly introduce the drawings required to be used in the embodiment or the description of the prior art, it is obvious that the drawings in the following description are only schematic views of the present invention, and other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art;
Fig. 1 is a schematic structural diagram of a highway environment monitoring terminal based on internet of things according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In an embodiment, a highway environment monitoring terminal based on the internet of things, the structure of which is shown in fig. 1, includes:
the environment monitoring module is used for collecting real-time environment data along the road through the sensor array, including meteorological parameters, air quality parameters and road condition parameters, and the environment data are processed into structural information and transmitted to the edge calculation module;
The environment monitoring module includes:
the sensor array includes:
the system comprises a meteorological sensor, a sensor and a wind speed sensor, wherein the meteorological sensor is used for collecting data related to meteorological conditions along a highway and comprises a temperature sensor, a humidity sensor and a wind speed sensor, and is used for respectively detecting ambient temperature, humidity and wind speed;
An air quality sensor for detecting the concentration of pollutants in air along a highway, wherein the air quality sensor comprises a PM2.5 sensor, a PM10 sensor and a carbon dioxide sensor, and is used for respectively detecting the concentration of fine particles, inhalable particles and carbon dioxide;
The road state sensor is used for collecting image data of the road surface to analyze accumulated water, icing, obstacles and traffic flow, the infrared sensor is used for detecting temperature distribution of the road surface to judge whether icing or temperature abnormality exists or not, and the humidity sensor is used for detecting the humidity level of the road surface to judge the accumulated water or wet and slippery condition;
the data processing unit is connected with the sensor array and is used for receiving the environmental data acquired by various sensors, processing the environmental data, removing abnormal data and noise data, converting the processed data into structured information in a uniform format and transmitting the structured information to the edge computing module.
The edge calculation module is connected with the environment monitoring module, processes the environment data in real time based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model and a prediction analysis sub-model, generates a real-time analysis result by primarily analyzing the environment data, comprises a data anomaly flag, a trend prediction result and event response information, and transmits the real-time analysis result to the Internet of things communication module and the intelligent linkage module;
the edge calculation module includes:
the data receiving unit is used for receiving the environment data from the environment monitoring module;
the data preprocessing unit is connected with the data receiving unit and is used for processing the received environmental data, including removing repeated data and repairing lost data;
The real-time analysis unit is connected with the data preprocessing unit and is used for intelligently analyzing the processed data based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model, a prediction analysis sub-model and a data processing unit, wherein the anomaly detection sub-model is used for detecting an anomaly mode or an anomaly event in the data, and the anomaly mode or the anomaly event comprises accumulation of water, icing or air pollutant exceeding;
The result generation unit is connected with the real-time analysis unit and used for generating a real-time analysis result and transmitting the generated real-time analysis result to the Internet of things communication module and the intelligent linkage module.
The real-time analysis model comprises:
an anomaly detection sub-model adopts an anomaly classification algorithm based on a support vector machine to input environmental data Constructing a separation hyperplane in a high-dimensional space for judging whether data are abnormal points or not as feature vectors, wherein the hyperplane is defined by the following formula: Wherein As a weight vector of the weight vector,As a bias term, ifJudging normal data, otherwise judging abnormal data;
The abnormal detection sub-model is obtained through training of feature vectors extracted from a historical environment data set, and classification accuracy of abnormal data and normal data is used as an optimization target;
Trend prediction sub-model adopts time sequence prediction algorithm based on long-short time memory network to use time sequence of environment data Predicting environmental parameters at future time points as inputs;
The core formula of the long-short-time memory network comprises the following components:
an input door: Wherein Representing the activation value (range of input gates),As a weight matrix of the input gates,The representation Sigmod activates the function,Indicating the hidden state of the last time step,Representing the current input and the current level of the input,Bias for input gates, for deciding how much of the currently input information is introduced into the cell stateIs a kind of medium.
Forgetting the door: Wherein Indicating activation value (range of forgetting gate),For a weight matrix of forgetting gates,Bias for forgetting the gate, for determining the state of the last time stepHow much information in the system needs to be forgotten;
Output door: Wherein Representing the activation value (range of output gates),To output the weight matrix of the gate,For outputting the bias of the gate for determining the cell stateWhich information needs to be output to the current hidden state;
Cell state update: Wherein To generate the weight matrix for the new information,For the current bias term, tanh is a hyperbolic tangent function used to map information toRepresenting the importance of the information,Status information indicating the last time step left by the forget gate decision,The method comprises the steps of determining new information added by an input gate, integrating information of a forget gate and the input gate, and updating the state of a unit in the current time step;
hidden state: , representing the hidden state of the current time step, An activation value representing an output gate, which determines which information is output from the cell state;
The trend prediction sub-model is trained in a supervised learning mode, historical time sequence data and a corresponding future target value are used as training samples, minimized mean square error is used as a loss function for optimization, and a calculation formula of minimized mean square error is as follows: Wherein The true value is represented by a value that is true,In order to be able to predict the value,Is the total number of samples;
the real-time analysis model is obtained through pre-training, training data are derived from historical environment monitoring data, the data comprise meteorological data, air quality data and road state data, the training process is completed through a distributed computing platform and comprises four stages of data preprocessing, feature extraction, model training and parameter optimization, and a cross verification method is adopted to verify the performance of the model, and classification accuracy, prediction error and model convergence are used as model evaluation standards.
The specific pre-training process is as follows:
Acquiring historical environment monitoring data, and preprocessing the data, wherein the method comprises the following steps of:
data cleaning, namely eliminating abnormal values, noise data and complement of missing values, and ensuring the quality of input data;
data standardization, carrying out normalization processing on data acquired by different sensors, and unifying the scale range of the characteristics;
Feature engineering, an anomaly detection sub-model, a trend prediction sub-model and a characteristic analysis sub-model, wherein the key features (such as a temperature fluctuation range, a humidity change rate, an anomaly peak value of pollutant concentration and the like) are extracted;
Training of a model:
The anomaly detection submodel is based on a Support Vector Machine (SVM) algorithm, a training set is constructed by using normal samples and abnormal samples in historical data, feature vectors are used as input, labels are normal or abnormal, classification hyperplanes are optimized, and hyperparameters are optimized through grid search.
A trend prediction sub-model, based on a long and short time memory network (LSTM), inputs an environmental parameter with a time sequence as an input characteristic and a future time point as an output target, and adjusts the model parameter by using an Adam optimizer so as to improve the training convergence speed;
Model optimization:
The method comprises the steps of cross-verifying, namely dividing a data set into a training set, a verification set and a test set, evaluating the performance of a model by using K-fold cross-verifying, and optimizing classification precision and prediction error;
The method comprises the steps of carrying out high-efficiency training on massive historical data based on a distributed computing platform (TensorFlow distributed training framework), parallelizing computing and accelerating feature extraction, parameter updating and model verification processes;
the environmental data collected in real time are added into a training data set at regular intervals, model retraining and optimization are carried out, and the adaptability of the model to the latest environmental change is ensured;
The model performance evaluation indexes comprise an abnormality detection sub-model, a trend prediction sub-model and a model analysis sub-model, wherein the abnormality detection sub-model comprises classification precision, recall rate and F1 fraction;
After the system is deployed, the data acquired in real time can be periodically uploaded to the cloud as a data source for model retraining;
Fully training a model by using an offline data set before deployment;
After deployment, optimizing the model according to the actual application scene in a fine tuning mode;
The internet of things communication module is connected with the edge calculation module and is used for uploading the environment data and the real-time analysis result to the cloud analysis module, receiving the global evaluation result returned by the cloud analysis module and realizing interconnection and intercommunication between the terminal devices and stable communication with the cloud platform;
The communication module of the Internet of things comprises:
The communication protocol unit is used for supporting wireless communication protocols, including LoRa, NB-IoT, 4G and 5G communication protocols, and automatically switching communication modes according to application scenes, wherein the application scenes comprise low power consumption, high bandwidth and long-distance transmission;
The data transmission unit is connected with the communication protocol unit and is used for uploading the environment data and the real-time analysis result generated by the edge calculation module to the cloud analysis module and receiving the global evaluation result returned by the cloud analysis module;
the data buffer unit is connected with the data transmission unit, and is used for temporarily storing environment data and real-time analysis results when communication is interrupted or the network is unstable, and automatically uploading the environment data and the real-time analysis results after communication is recovered;
The communication state monitoring unit is used for monitoring the running state of the communication module in real time, including the network connection state, the signal strength and the data transmission rate, and sending fault information to the equipment self-maintenance module when communication is abnormal;
the low-power consumption unit is used for optimizing the energy consumption of the communication module and dynamically adjusting the communication power and the working mode according to the data transmission task.
The cloud analysis module is connected with the edge calculation module through the communication module of the Internet of things, carries out global analysis and processing on the environmental data and the real-time analysis result based on a global evaluation model in the cloud, and the global evaluation model combines the historical data and the real-time data to generate a global evaluation result which comprises the prediction information of the environment, the optimization suggestion of traffic management and the response strategy of an emergency, and transmits the global evaluation result back to the communication module of the Internet of things;
the cloud analysis module comprises:
the data receiving unit is used for receiving the environmental data and the real-time analysis result uploaded by the communication module of the Internet of things, classifying and storing the received data, and dividing the data into real-time data and historical data according to the time dimension so as to support the subsequent analysis;
the global evaluation unit is connected with the data receiving unit, performs global analysis and processing on the received data based on the global evaluation model, and generates the following three types of results:
The environment prediction information is based on a deep learning algorithm, and future environmental conditions including weather change trend, air quality distribution and future change of road state are predicted by extracting features of real-time environment data and combining with time sequence change rules of historical environment data;
The optimization proposal of traffic management is based on a graph convolution neural network and a long-short time memory network, and the dynamic change characteristics of traffic flow are analyzed through joint modeling of real-time traffic flow data and historical traffic data, so as to generate the optimization proposal of traffic management, including traffic signal lamp period adjustment, diversion route planning and traffic dispersion proposal;
the response strategy of the emergency event is that the current emergency event is identified through real-time environment data and by referring to similar event modes recorded in historical data, and a corresponding response strategy is generated, wherein the response strategy comprises real-time early warning information, road closing instructions and a warning signal triggering scheme;
The response strategy generation unit is connected with the global evaluation unit and is used for receiving environment prediction information, traffic management optimization suggestions and emergency response strategies and integrating the results into specific executable instructions;
The result sending unit is connected with the response strategy generating unit and is used for transmitting the environment prediction information, the traffic management optimization suggestions and the emergency response strategy to the communication module of the Internet of things for use by the terminal equipment or the traffic management center;
the model optimization unit is used for iterating a training deep learning algorithm and a traffic flow evaluation algorithm based on a graph convolution neural network and a long-time memory network based on the uploaded real-time data and historical data and actual execution feedback of a global evaluation result so as to improve the prediction precision and response efficiency of model output;
The cloud storage unit is used for storing historical environment data, global evaluation results and response strategies and providing long-term data support for the global evaluation unit and the model optimization unit.
The global assessment model includes:
An environment predictor model for generating prediction information of an environment, the environment predictor model constructed based on a deep learning algorithm, the training and use thereof comprising:
The method comprises the steps of extracting historical environment data from a cloud storage unit to serve as a training data set, capturing time sequence changes of the environment data by using a long-short-time memory network as a basic model, and optimizing the model by minimizing mean square error;
inputting the real-time environment data into an environment prediction sub-model, and generating environment prediction information in a future time period by combining the historical data;
the traffic flow evaluation sub-model is used for generating an optimization suggestion of traffic management, is constructed based on a combined algorithm of a graph convolution neural network and a long-time and short-time memory network, and is trained and used by the traffic flow evaluation sub-model, and comprises the following steps:
the method comprises the steps of extracting vehicle flow in historical environment data from a cloud storage unit, combining the vehicle flow with a road network topological structure to be used as a training data set, modeling the spatial characteristics of the road network by using a graph convolution neural network, and realizing the aggregation of node characteristics based on the following formula: Wherein A is an adjacency matrix of the road network, D is a degree matrix, Is the firstThe feature matrix of the layer is used,As a matrix of weights, the weight matrix,Representing an activation function;
Modeling the time characteristics of traffic flow data by using a long-short time memory network, extracting time sequence characteristics and combining the output of a graph convolution neural network;
Inputting traffic flow and a current road network topological structure, and generating an evaluation result of a current traffic flow state and traffic flow prediction in a future time period by combining historical traffic data;
An emergency recognition sub-model for generating a response strategy for an emergency, the emergency recognition sub-model constructed based on a combination algorithm of a convolutional neural network and a time convolutional network in deep learning, the training and use of the emergency recognition sub-model comprising:
The method comprises the steps of extracting historical emergency data and corresponding environmental data from a cloud storage unit as a training data set, extracting spatial features of the environmental data and traffic flow data by using a convolutional neural network, modeling time sequence features of the data by using a time convolutional network, constructing an emergency recognition model by combining the spatial features and the time sequence features, and optimizing by using a cross entropy loss function;
inputting real-time environment data and traffic flow data to generate an emergency detection result, and generating a corresponding response strategy according to the detection result.
The intelligent linkage module is respectively connected with the edge calculation module and the Internet of things communication module, and is used for receiving the real-time analysis result and the global evaluation result, and executing corresponding linkage control operation, including dynamically adjusting the operation parameters of the traffic management equipment, triggering the real-time warning equipment or sending a control instruction to the management center;
The intelligent linkage module includes:
The linkage data receiving unit is used for receiving the real-time analysis result from the edge calculation module and the global evaluation result of the cloud analysis module;
the linkage strategy analysis unit is connected with the linkage data receiving unit and is used for analyzing the global evaluation result pair and generating a corresponding control instruction according to the analysis result;
Judging weather change trend, air quality change and road state prediction in the environment prediction information, and determining whether to trigger an environment early warning instruction; analyzing the traffic signal lamp period adjustment, the diversion route planning and the traffic guiding scheme in the traffic management optimization suggestion to generate corresponding traffic signal equipment control instructions;
the device control unit is connected with the linkage strategy analysis unit and is used for executing the analyzed control instruction;
The device control comprises traffic signal device control, early warning broadcasting triggering, electronic display screen or other warning devices, and real-time early warning information providing for vehicles or personnel, wherein the traffic signal device control dynamically adjusts the period of traffic signal lamps, switches traffic signs or starts dynamic warning lamps;
The remote control module is used for sending a linkage control instruction to the traffic management center and supporting remote operation and manual intervention;
The state feedback unit is used for monitoring the execution state of the equipment in real time, and transmitting the execution state and feedback information to the cloud analysis module and the equipment self-maintenance module so as to facilitate subsequent optimization and fault processing;
The priority scheduling unit is connected with the linkage strategy analysis unit and is used for scheduling a plurality of linkage control instructions according to the priority, and when a plurality of linkage control tasks conflict, the linkage instructions are selectively executed according to the event type and the emergency degree.
The power module is used for intelligently supplying power to the highway environment monitoring terminal and supporting low-power-consumption operation of each module;
the power module includes:
The solar power supply unit is used for capturing light energy and converting the light energy into electric energy, and providing sustainable energy support for the terminal;
the energy storage battery unit is connected with the solar power supply unit and is used for storing redundant electric energy and supplying power to the terminal under the condition of insufficient illumination or no illumination;
The low-power consumption management unit is used for dynamically adjusting the power consumption state of each module, and optimizing power supply distribution by analyzing the running condition and the energy use requirement of the terminal;
the standby power supply unit is connected with the energy storage battery unit and is used for providing emergency power supply when the solar power supply and the energy storage battery are not available at the same time, so that the basic operation of the terminal is ensured;
The power state monitoring unit is used for monitoring the running states of the solar power supply unit, the energy storage battery unit and the standby power supply unit in real time, including electric quantity, output power and running efficiency, and transmitting monitoring results to the equipment self-maintenance module.
The equipment self-maintenance module is connected with the environment monitoring module, the edge computing module, the Internet of things communication module and the power module in the terminal, and is used for monitoring the running state of each module, executing automatic detection and diagnosis of equipment faults and transmitting fault diagnosis reports to the intelligent linkage module.
The device self-maintenance module comprises:
the state monitoring unit is used for monitoring the running states of the environment monitoring module, the edge computing module, the Internet of things communication module, the power module and the intelligent linkage module in real time, and comprises a working state, a data transmission state, a power state and a device connection state;
The fault detection unit is connected with the state monitoring unit and is used for analyzing the monitoring data and identifying the abnormality or fault in the operation of the module, including sensor failure, communication interruption, insufficient electric quantity and module hardware fault;
The diagnosis unit is connected with the fault detection unit and is used for generating a fault diagnosis report based on a fault detection result, wherein the fault diagnosis report comprises fault reasons, influence ranges and priority evaluation;
the fault response unit is connected with the diagnosis unit and is used for automatically taking corresponding response measures according to the fault diagnosis report, and the fault response unit comprises a restarting module, a communication path switching module, a standby power supply starting module or a fault alarm sending module;
the fault report unit is used for sending a fault diagnosis report and response measures to the cloud analysis module or the traffic management center through the communication module of the Internet of things;
the log recording unit is used for recording the equipment operation log and the fault diagnosis log, including time, position, fault type and processing result, and storing the log in the cloud storage unit.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (10)

1. Highway environment monitoring terminal based on thing networking, its characterized in that includes:
the environment monitoring module is used for collecting real-time environment data along the road through the sensor array, including meteorological parameters, air quality parameters and road condition parameters, and the environment data are processed into structural information and transmitted to the edge calculation module;
The edge calculation module is connected with the environment monitoring module, processes the environment data in real time based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model and a prediction analysis sub-model, generates a real-time analysis result by primarily analyzing the environment data, comprises a data anomaly flag, a trend prediction result and event response information, and transmits the real-time analysis result to the Internet of things communication module and the intelligent linkage module;
The internet of things communication module is connected with the edge calculation module and is used for uploading the environment data and the real-time analysis result to the cloud analysis module, receiving the global evaluation result returned by the cloud analysis module and realizing interconnection and intercommunication between the terminal devices and stable communication with the cloud platform;
The cloud analysis module is connected with the edge calculation module through the communication module of the Internet of things, carries out global analysis and processing on the environmental data and the real-time analysis result based on a global evaluation model in the cloud, and the global evaluation model combines the historical data and the real-time data to generate a global evaluation result which comprises the prediction information of the environment, the optimization suggestion of traffic management and the response strategy of an emergency, and transmits the global evaluation result back to the communication module of the Internet of things;
The intelligent linkage module is respectively connected with the edge calculation module and the Internet of things communication module, and is used for receiving the real-time analysis result and the global evaluation result, and executing corresponding linkage control operation, including dynamically adjusting the operation parameters of the traffic management equipment, triggering the real-time warning equipment or sending control instructions to the management center.
2. The internet of things-based highway environment monitoring terminal according to claim 1, wherein the environment monitoring module comprises:
the sensor array includes:
the system comprises a meteorological sensor, a sensor and a wind speed sensor, wherein the meteorological sensor is used for collecting data related to meteorological conditions along a highway and comprises a temperature sensor, a humidity sensor and a wind speed sensor, and is used for respectively detecting ambient temperature, humidity and wind speed;
An air quality sensor for detecting the concentration of pollutants in air along a highway, wherein the air quality sensor comprises a PM2.5 sensor, a PM10 sensor and a carbon dioxide sensor, and is used for respectively detecting the concentration of fine particles, inhalable particles and carbon dioxide;
The road state sensor is used for collecting image data of the road surface to analyze accumulated water, icing, obstacles and traffic flow, the infrared sensor is used for detecting temperature distribution of the road surface to judge whether icing or temperature abnormality exists or not, and the humidity sensor is used for detecting the humidity level of the road surface to judge the accumulated water or wet and slippery condition;
the data processing unit is connected with the sensor array and is used for receiving the environmental data acquired by various sensors, processing the environmental data, removing abnormal data and noise data, converting the processed data into structured information in a uniform format and transmitting the structured information to the edge computing module.
3. The internet of things-based highway environment monitoring terminal according to claim 1, wherein the edge calculation module comprises:
the data receiving unit is used for receiving the environment data from the environment monitoring module;
the data preprocessing unit is connected with the data receiving unit and is used for processing the received environmental data, including removing repeated data and repairing lost data;
The real-time analysis unit is connected with the data preprocessing unit and is used for intelligently analyzing the processed data based on an embedded real-time analysis model, wherein the real-time analysis model comprises an anomaly detection sub-model, a prediction analysis sub-model and a data processing unit, wherein the anomaly detection sub-model is used for detecting an anomaly mode or an anomaly event in the data, and the anomaly mode or the anomaly event comprises accumulation of water, icing or air pollutant exceeding;
The result generation unit is connected with the real-time analysis unit and used for generating a real-time analysis result and transmitting the generated real-time analysis result to the Internet of things communication module and the intelligent linkage module.
4. The internet of things-based highway environment monitoring terminal according to claim 3, wherein the real-time analysis model comprises:
an anomaly detection sub-model adopts an anomaly classification algorithm based on a support vector machine to input environmental data Constructing a separation hyperplane in a high-dimensional space for judging whether data are abnormal points or not as feature vectors, wherein the hyperplane is defined by the following formula: Wherein As a weight vector of the weight vector,As a bias term, ifJudging normal data, otherwise judging abnormal data;
The abnormal detection sub-model is obtained through training of feature vectors extracted from a historical environment data set, and classification accuracy of abnormal data and normal data is used as an optimization target;
A trend prediction sub-model, which adopts a time sequence prediction algorithm based on a long-short time memory network, takes a time sequence { X t,Xt-1,…,Xt-n } of environmental data as input, and predicts environmental parameters of a future time point;
the trend prediction sub-model is trained in a supervised learning mode, historical time sequence data and a corresponding future target value are used as training samples, and minimized mean square error is used as a loss function for optimization;
the real-time analysis model is obtained through pre-training, training data are derived from historical environment monitoring data, the data comprise meteorological data, air quality data and road state data, the training process is completed through a distributed computing platform and comprises four stages of data preprocessing, feature extraction, model training and parameter optimization, and a cross verification method is adopted to verify the performance of the model, and classification accuracy, prediction error and model convergence are used as model evaluation standards.
5. The internet of things-based highway environment monitoring terminal according to claim 1, wherein the internet of things communication module comprises:
The communication protocol unit is used for supporting wireless communication protocols, including LoRa, NB-IoT, 4G and 5G communication protocols, and automatically switching communication modes according to application scenes, wherein the application scenes comprise low power consumption, high bandwidth and long-distance transmission;
The data transmission unit is connected with the communication protocol unit and is used for uploading the environment data and the real-time analysis result generated by the edge calculation module to the cloud analysis module and receiving the global evaluation result returned by the cloud analysis module;
the data buffer unit is connected with the data transmission unit, and is used for temporarily storing environment data and real-time analysis results when communication is interrupted or the network is unstable, and automatically uploading the environment data and the real-time analysis results after communication is recovered;
The communication state monitoring unit is used for monitoring the running state of the communication module in real time, including the network connection state, the signal strength and the data transmission rate, and sending fault information to the equipment self-maintenance module when communication is abnormal;
the low-power consumption unit is used for optimizing the energy consumption of the communication module and dynamically adjusting the communication power and the working mode according to the data transmission task.
6. The internet of things-based highway environment monitoring terminal of claim 1, wherein the cloud analysis module comprises:
the data receiving unit is used for receiving the environmental data and the real-time analysis result uploaded by the communication module of the Internet of things, classifying and storing the received data, and dividing the data into real-time data and historical data according to the time dimension so as to support the subsequent analysis;
the global evaluation unit is connected with the data receiving unit, performs global analysis and processing on the received data based on the global evaluation model, and generates the following three types of results:
The environment prediction information is based on a deep learning algorithm, and future environmental conditions including weather change trend, air quality distribution and future change of road state are predicted by extracting features of real-time environment data and combining with time sequence change rules of historical environment data;
The optimization proposal of traffic management is based on a graph convolution neural network and a long-short time memory network, and the dynamic change characteristics of traffic flow are analyzed through joint modeling of real-time traffic flow data and historical traffic data, so as to generate the optimization proposal of traffic management, including traffic signal lamp period adjustment, diversion route planning and traffic dispersion proposal;
the response strategy of the emergency event is that the current emergency event is identified through real-time environment data and by referring to similar event modes recorded in historical data, and a corresponding response strategy is generated, wherein the response strategy comprises real-time early warning information, road closing instructions and a warning signal triggering scheme;
The response strategy generation unit is connected with the global evaluation unit and is used for receiving environment prediction information, traffic management optimization suggestions and emergency response strategies and integrating the results into specific executable instructions;
The result sending unit is connected with the response strategy generating unit and is used for transmitting the environment prediction information, the traffic management optimization suggestions and the emergency response strategy to the communication module of the Internet of things for use by the terminal equipment or the traffic management center;
the model optimization unit is used for iterating a training deep learning algorithm and a traffic flow evaluation algorithm based on a graph convolution neural network and a long-time memory network based on the uploaded real-time data and historical data and actual execution feedback of a global evaluation result so as to improve the prediction precision and response efficiency of model output;
The cloud storage unit is used for storing historical environment data, global evaluation results and response strategies and providing long-term data support for the global evaluation unit and the model optimization unit.
7. The internet of things-based highway environment monitoring terminal according to claim 6, wherein the global assessment model comprises:
An environment predictor model for generating prediction information of an environment, the environment predictor model constructed based on a deep learning algorithm, the training and use thereof comprising:
The method comprises the steps of extracting historical environment data from a cloud storage unit to serve as a training data set, capturing time sequence changes of the environment data by using a long-short-time memory network as a basic model, and optimizing the model by minimizing mean square error;
inputting the real-time environment data into an environment prediction sub-model, and generating environment prediction information in a future time period by combining the historical data;
the traffic flow evaluation sub-model is used for generating an optimization suggestion of traffic management, is constructed based on a combined algorithm of a graph convolution neural network and a long-time and short-time memory network, and is trained and used by the traffic flow evaluation sub-model, and comprises the following steps:
Modeling the spatial characteristics of the road network by using a graph convolution neural network, modeling the time characteristics of traffic flow data by using a long-short-term memory network, extracting the time sequence characteristics and combining the output of the graph convolution neural network;
Inputting traffic flow and a current road network topological structure, and generating an evaluation result of a current traffic flow state and traffic flow prediction in a future time period by combining historical traffic data;
An emergency recognition sub-model for generating a response strategy for an emergency, the emergency recognition sub-model constructed based on a combination algorithm of a convolutional neural network and a time convolutional network in deep learning, the training and use of the emergency recognition sub-model comprising:
The method comprises the steps of extracting historical emergency data and corresponding environmental data from a cloud storage unit as a training data set, extracting spatial features of the environmental data and traffic flow data by using a convolutional neural network, modeling time sequence features of the data by using a time convolutional network, constructing an emergency recognition model by combining the spatial features and the time sequence features, and optimizing by using a cross entropy loss function;
inputting real-time environment data and traffic flow data to generate an emergency detection result, and generating a corresponding response strategy according to the detection result.
8. The internet of things-based highway environment monitoring terminal of claim 1, wherein the intelligent linkage module comprises:
The linkage data receiving unit is used for receiving the real-time analysis result from the edge calculation module and the global evaluation result of the cloud analysis module;
the linkage strategy analysis unit is connected with the linkage data receiving unit and is used for analyzing the global evaluation result pair and generating a corresponding control instruction according to the analysis result;
Judging weather change trend, air quality change and road state prediction in the environment prediction information, and determining whether to trigger an environment early warning instruction; analyzing the traffic signal lamp period adjustment, the diversion route planning and the traffic guiding scheme in the traffic management optimization suggestion to generate corresponding traffic signal equipment control instructions;
the device control unit is connected with the linkage strategy analysis unit and is used for executing the analyzed control instruction;
The device control comprises traffic signal device control, early warning broadcasting triggering, electronic display screen or other warning devices, and real-time early warning information providing for vehicles or personnel, wherein the traffic signal device control dynamically adjusts the period of traffic signal lamps, switches traffic signs or starts dynamic warning lamps;
The remote control module is used for sending a linkage control instruction to the traffic management center and supporting remote operation and manual intervention;
The state feedback unit is used for monitoring the execution state of the equipment in real time, and transmitting the execution state and feedback information to the cloud analysis module and the equipment self-maintenance module so as to facilitate subsequent optimization and fault processing;
The priority scheduling unit is connected with the linkage strategy analysis unit and is used for scheduling a plurality of linkage control instructions according to the priority, and when a plurality of linkage control tasks conflict, the linkage instructions are selectively executed according to the event type and the emergency degree.
9. The internet of things-based highway environment monitoring terminal according to claim 1, further comprising:
the power module is used for intelligently supplying power to the highway environment monitoring terminal and supporting low-power-consumption operation of each module;
the power module includes:
The solar power supply unit is used for capturing light energy and converting the light energy into electric energy, and providing sustainable energy support for the terminal;
the energy storage battery unit is connected with the solar power supply unit and is used for storing redundant electric energy and supplying power to the terminal under the condition of insufficient illumination or no illumination;
The low-power consumption management unit is used for dynamically adjusting the power consumption state of each module, and optimizing power supply distribution by analyzing the running condition and the energy use requirement of the terminal;
the standby power supply unit is connected with the energy storage battery unit and is used for providing emergency power supply when the solar power supply and the energy storage battery are not available at the same time, so that the basic operation of the terminal is ensured;
The power state monitoring unit is used for monitoring the running states of the solar power supply unit, the energy storage battery unit and the standby power supply unit in real time, including electric quantity, output power and running efficiency, and transmitting monitoring results to the equipment self-maintenance module.
10. The internet of things-based highway environment monitoring terminal according to claim 1, further comprising:
The equipment self-maintenance module is connected with the environment monitoring module, the edge computing module, the Internet of things communication module and the power module in the terminal, and is used for monitoring the running state of each module, executing automatic detection and diagnosis of equipment faults and transmitting fault diagnosis reports to the intelligent linkage module;
The device self-maintenance module comprises:
the state monitoring unit is used for monitoring the running states of the environment monitoring module, the edge computing module, the Internet of things communication module, the power module and the intelligent linkage module in real time, and comprises a working state, a data transmission state, a power state and a device connection state;
The fault detection unit is connected with the state monitoring unit and is used for analyzing the monitoring data and identifying the abnormality or fault in the operation of the module, including sensor failure, communication interruption, insufficient electric quantity and module hardware fault;
The diagnosis unit is connected with the fault detection unit and is used for generating a fault diagnosis report based on a fault detection result, wherein the fault diagnosis report comprises fault reasons, influence ranges and priority evaluation;
the fault response unit is connected with the diagnosis unit and is used for automatically taking corresponding response measures according to the fault diagnosis report, and the fault response unit comprises a restarting module, a communication path switching module, a standby power supply starting module or a fault alarm sending module;
the fault report unit is used for sending a fault diagnosis report and response measures to the cloud analysis module or the traffic management center through the communication module of the Internet of things;
the log recording unit is used for recording the equipment operation log and the fault diagnosis log, including time, position, fault type and processing result, and storing the log in the cloud storage unit.
CN202510606306.XA 2025-05-12 2025-05-12 Highway environment monitoring terminal based on the Internet of Things Pending CN120126328A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510606306.XA CN120126328A (en) 2025-05-12 2025-05-12 Highway environment monitoring terminal based on the Internet of Things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510606306.XA CN120126328A (en) 2025-05-12 2025-05-12 Highway environment monitoring terminal based on the Internet of Things

Publications (1)

Publication Number Publication Date
CN120126328A true CN120126328A (en) 2025-06-10

Family

ID=95929719

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510606306.XA Pending CN120126328A (en) 2025-05-12 2025-05-12 Highway environment monitoring terminal based on the Internet of Things

Country Status (1)

Country Link
CN (1) CN120126328A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120496336A (en) * 2025-07-09 2025-08-15 苏州申亿通智慧运营管理有限公司 LSTM-based road surface icing monitoring system
CN120547521A (en) * 2025-06-26 2025-08-26 广州时泽云科技有限公司 Internet of Things data acquisition system and method

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110503832A (en) * 2019-08-28 2019-11-26 广东利通科技投资有限公司 Command processing method, device, equipment and medium based on wisdom traffic system
AU2020100946A4 (en) * 2019-10-18 2020-07-16 Chang'an University Multi-source traffic information sensing roadside device for smart highway
CN112991785A (en) * 2021-05-17 2021-06-18 武汉中科通达高新技术股份有限公司 Traffic guiding method and device
CN114819501A (en) * 2022-03-25 2022-07-29 云南省交通规划设计研究院有限公司 Road traffic meteorological Internet of things multi-source heterogeneous data processing method and system
CN114999180A (en) * 2022-05-12 2022-09-02 广东省韶关市气象局 Expressway severe weather traffic early warning system and method based on Internet of things
CN117333046A (en) * 2023-09-13 2024-01-02 海南省气象信息中心 Multisource meteorological data integration and quality control system
CN118470991A (en) * 2024-06-14 2024-08-09 中建照明有限公司 Intelligent traffic control system and method for smart city based on 5G
CN118675324A (en) * 2024-06-06 2024-09-20 南京东控智能交通研究院有限公司 Traffic flow prediction system based on deep learning and dynamic network analysis and application method thereof
CN119131732A (en) * 2024-09-06 2024-12-13 重庆赛力斯凤凰智创科技有限公司 Road puddle identification method, system, electronic device and storage medium
CN119168149A (en) * 2024-09-14 2024-12-20 安徽大学 A multivariate prediction method for air quality based on Attention-LSTM
CN119202597A (en) * 2024-09-10 2024-12-27 中国环境科学研究院 A method for analyzing the sources of atmospheric particulate matter based on deep learning
CN119479316A (en) * 2025-01-14 2025-02-18 广东申创光电科技有限公司 Intelligent traffic data processing method and system based on edge computing
CN119723899A (en) * 2025-03-03 2025-03-28 北京洞微科技发展有限公司 A method and system for optimizing traffic special situation based on large model
CN119811106A (en) * 2024-12-19 2025-04-11 中科芯(苏州)微电子科技有限公司 A smart traffic data processing method and system based on 5G communication system
CN119881208A (en) * 2024-12-16 2025-04-25 江苏省苏力环境科技有限责任公司 Remote intelligent quality control system based on unmanned on duty

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110503832A (en) * 2019-08-28 2019-11-26 广东利通科技投资有限公司 Command processing method, device, equipment and medium based on wisdom traffic system
AU2020100946A4 (en) * 2019-10-18 2020-07-16 Chang'an University Multi-source traffic information sensing roadside device for smart highway
CN112991785A (en) * 2021-05-17 2021-06-18 武汉中科通达高新技术股份有限公司 Traffic guiding method and device
CN114819501A (en) * 2022-03-25 2022-07-29 云南省交通规划设计研究院有限公司 Road traffic meteorological Internet of things multi-source heterogeneous data processing method and system
CN114999180A (en) * 2022-05-12 2022-09-02 广东省韶关市气象局 Expressway severe weather traffic early warning system and method based on Internet of things
CN117333046A (en) * 2023-09-13 2024-01-02 海南省气象信息中心 Multisource meteorological data integration and quality control system
CN118675324A (en) * 2024-06-06 2024-09-20 南京东控智能交通研究院有限公司 Traffic flow prediction system based on deep learning and dynamic network analysis and application method thereof
CN118470991A (en) * 2024-06-14 2024-08-09 中建照明有限公司 Intelligent traffic control system and method for smart city based on 5G
CN119131732A (en) * 2024-09-06 2024-12-13 重庆赛力斯凤凰智创科技有限公司 Road puddle identification method, system, electronic device and storage medium
CN119202597A (en) * 2024-09-10 2024-12-27 中国环境科学研究院 A method for analyzing the sources of atmospheric particulate matter based on deep learning
CN119168149A (en) * 2024-09-14 2024-12-20 安徽大学 A multivariate prediction method for air quality based on Attention-LSTM
CN119881208A (en) * 2024-12-16 2025-04-25 江苏省苏力环境科技有限责任公司 Remote intelligent quality control system based on unmanned on duty
CN119811106A (en) * 2024-12-19 2025-04-11 中科芯(苏州)微电子科技有限公司 A smart traffic data processing method and system based on 5G communication system
CN119479316A (en) * 2025-01-14 2025-02-18 广东申创光电科技有限公司 Intelligent traffic data processing method and system based on edge computing
CN119723899A (en) * 2025-03-03 2025-03-28 北京洞微科技发展有限公司 A method and system for optimizing traffic special situation based on large model

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120547521A (en) * 2025-06-26 2025-08-26 广州时泽云科技有限公司 Internet of Things data acquisition system and method
CN120496336A (en) * 2025-07-09 2025-08-15 苏州申亿通智慧运营管理有限公司 LSTM-based road surface icing monitoring system

Similar Documents

Publication Publication Date Title
CN119443922B (en) An efficient and accurate pollution source monitoring quality control system and method
CN120126328A (en) Highway environment monitoring terminal based on the Internet of Things
CN120562742A (en) Smart Park Full Lifecycle Management System and Method Based on Digital Twin and Internet of Things
CN116614177B (en) Optical fiber state multidimensional parameter monitoring system
CN120146330B (en) A method and system for predicting power consumption in a smart park based on artificial intelligence
CN118249314A (en) New energy generated power prediction optimization system and method based on AI large model technology
CN120336973A (en) Intelligent diagnosis method, system and medium for urban rail equipment health based on cloud platform
CN120675276B (en) Multi-mode data fusion type digital twin real-time monitoring system and method for power transmission line
CN119255445A (en) A road lighting system based on the Internet of Things
CN118916807B (en) A method and system for intelligently identifying abnormal energy consumption of tunnel equipment based on cloud-edge collaboration
CN120127836A (en) Intelligent power distribution integrated monitoring system integrating IoT and cloud computing
CN120697602A (en) Safety monitoring system for liquid-cooled supercharging piles
CN120511654A (en) Industrial park load prediction method based on artificial intelligence
CN118818970A (en) A real-time monitoring method and system based on interval observation
CN120778580A (en) Building site big data raise dust monitoring system based on big data
CN116937819B (en) Remote power distribution cabinet monitoring system with learning function
CN120686676B (en) Building energy consumption comprehensive intelligent regulation and control method, device and medium based on artificial intelligence
CN119520311B (en) An obstacle-aware cloud-edge-end collaborative industrial wireless network channel prediction method
CN120122541A (en) Adjustment method and system for terminal box environment controller, electronic device, and storage medium
CN120408444A (en) Sanitation equipment SOC module anomaly detection and prediction method and system
CN120498381A (en) Photovoltaic module fault early warning method and system based on string current data mining
CN118675323B (en) Traffic operation security situation dynamic prediction system and method based on AI technology
Zhang et al. Elevator dynamic monitoring and early warning system based on machine learning algorithm
CN118472316A (en) Cloud-edge collaborative hydrogen fuel cell fault real-time early warning method and system
Hu et al. The early warning model of dust concentration in smart construction sites based on long short term memory network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20250610