CN121167487A - Intelligent metering laboratory environment monitoring and evaluating method and system - Google Patents
Intelligent metering laboratory environment monitoring and evaluating method and systemInfo
- Publication number
- CN121167487A CN121167487A CN202511348082.3A CN202511348082A CN121167487A CN 121167487 A CN121167487 A CN 121167487A CN 202511348082 A CN202511348082 A CN 202511348082A CN 121167487 A CN121167487 A CN 121167487A
- Authority
- CN
- China
- Prior art keywords
- laboratory
- layer
- model
- metering
- probability matrix
- 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
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an intelligent metering laboratory environment monitoring and evaluating method and system, which belong to the technical field of intelligent laboratory monitoring. The virtual platform layer is used for constructing a five-dimensional virtual mapping model based on a digital twin technology, and comprises a structural layer for carrying out data standardization pretreatment and multi-source information feature extraction, and an intelligent layer for generating a personnel behavior classification probability matrix and a device state recognition probability matrix by using the improved SwinTransformer model. The improved model optimizes feature extraction through a depth convolution kernel, geLU activation functions and a simplified regularization structure, and a decision layer calculates a laboratory running risk index by adopting a decision-level fusion algorithm based on a probability matrix, and triggers hierarchical early warning when the index exceeds a preset threshold. The application solves the problems of island data, environmental response lag and weak risk early warning in the metering laboratory, improves the accuracy of personnel behavior recognition, and accelerates the convergence speed of the model.
Description
Technical Field
The application relates to the technical field of intelligent laboratory monitoring, in particular to an intelligent metering laboratory environment monitoring and evaluating method and system.
Background
The traditional detection instrument is in an offline independent working state, so that key signals such as voltage and current are scattered and stored to form a data island, environment parameters depend on manual recording, sudden abnormal response to temperature and humidity mutation, gas leakage and the like is delayed, sensor coverage rate is insufficient, experimenters are in lack of real-time supervision in operation normalization, individual behaviors are difficult to distinguish under a multi-person cooperative scene, image recognition failure is caused due to equipment shielding, the traditional early warning mechanism depends on static threshold values, dynamic requirements of different experimental scenes cannot be met, coupling risks of personnel behaviors, equipment states and environment parameters are ignored, and the risks are often damaged substantially during alarming. Although the deep learning technology breaks through in the field of image recognition, the application of the deep learning technology in a metering laboratory scene still faces two major bottlenecks of multi-source heterogeneous data processing obstacle and contradiction between real-time performance and accuracy, and the existing digital twin technology is also difficult to meet the dual requirements of virtual-real interaction depth and risk decision accuracy.
In the prior art, for example, chinese patent with patent number of CN119046647A discloses an intelligent wind control method for multi-source data fusion, and the method optimizes risk decisions through high-dimensional tensor conversion and cost sensitive models, but still has the problem that heterogeneous data processing is difficult to adapt to strong space-time coupling characteristics of a metering laboratory, and real-time performance and accuracy contradiction results in failure to meet millisecond-level risk response requirements.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent metering laboratory environment monitoring and evaluating method and system.
The technical scheme of the invention is as follows:
the invention provides an intelligent metering laboratory environment monitoring and evaluating system, which comprises:
The physical entity layer is used for acquiring physical perception data streams in real time through an Internet of things sensor array deployed in a metering laboratory;
the virtual platform layer is used for constructing a metering laboratory virtual mapping model based on a digital twin technology, and comprises the following steps:
the structure layer is used for carrying out data standardization pretreatment and multisource information characteristic extraction on the collected physical perception data flow;
the intelligent layer inputs the multisource information characteristics into an improved SwinTransformer model and outputs a measurement laboratory personnel behavior classification probability matrix and a device state identification probability matrix;
And the decision layer is used for calculating a laboratory operation risk index by adopting a decision-level fusion algorithm based on the personnel behavior classification probability matrix and the device state identification probability matrix, and triggering early warning when the laboratory operation risk index is larger than a preset threshold value.
Preferably, the sensor array of the internet of things comprises:
the metering device monitoring unit is used for collecting electric parameter signals of voltage, current and power factor in real time;
The personnel behavior capturing unit is an RGB-D camera arranged in a key area of the laboratory;
The environment sensing unit comprises a temperature and humidity sensor, an illumination sensor and a gas concentration detector.
Preferably, the person behavior capturing unit eliminates the shielding interference through a plurality of frames of images.
Preferably, the digital twin technology is used for constructing a metering laboratory virtual mapping model, and the virtual mapping model is a five-dimensional model:
physical object, namely physical entity data acquired by the sensor array of the Internet of things;
twin data, namely iterative optimization data of a physical object, a virtual model and a service system;
Virtual model, namely integrating four-layer digital mapping model of geometry, physics, behavior and rule;
the service system is used for monitoring services provided based on the physical objects and the virtual model;
and data connection, namely a communication link for realizing real-time data transmission among the dimensions.
Preferably, the improvement SwinTransformer model adds LARGE KERNEL Block modules before the window multi-headed self-attention W-MSA module, cross-window attention SW-MSA module, and patch merge PATCH MERGING of original SwinTransformer.
Preferably, the LARGE KERNEL Block module optimizes feature extraction through a triple mechanism, including:
the deep convolution kernel is adopted to replace the traditional small-size convolution kernel to stack and expand the receptive field, and multi-level feature fusion is realized through single-layer convolution;
using GeLU activation functions to replace ReLU activation functions to retain negative characteristic information;
only Layer Normalization layers after the deep convolution are reserved, and the regularization structure is simplified.
Preferably, the decision-level fusion algorithm is based on a measurement laboratory personnel behavior classification probability matrix and a device state recognition probability matrix, comprehensively calculates risk values of all personnel behaviors and device states in a laboratory, calculates an environment risk value acquired by an environment sensing unit, and performs dynamic weighted fusion on the personnel behavior risk value, the device state risk value and the environment risk value to obtain a laboratory operation risk index.
On the other hand, the invention also provides an intelligent metering laboratory environment monitoring and evaluating method, which comprises the following steps:
acquiring a physical sensing data stream through an Internet of things sensor array;
Generating a personnel behavior and device state probability matrix through an improved SwinTransformer model at an intelligent layer;
And the decision layer calculates a laboratory operation risk index based on the probability matrix, and triggers grading early warning when the risk index exceeds a threshold value.
In yet another aspect, the present invention further provides an electronic device having a computer program stored thereon, which when executed by a processor implements a smart metering laboratory environment monitoring assessment method according to any of the embodiments of the present invention.
In yet another aspect, the present invention also provides a computer readable medium storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement a smart metering laboratory environment monitoring assessment method according to any of the embodiments of the present invention.
The invention has the following beneficial effects:
The real-time monitoring of all elements of equipment, environment and personnel is realized through the sensor array of the Internet of things, the five-dimensional digital twin model breaks through the limitation of data island, a laboratory running situation panorama is formed, an improved SwinTransformer model structure is introduced into a LARGE KERNEL Block module to optimize feature extraction, and the recognition efficiency is remarkably improved;
The improved SwinTransformer model adopts a deep convolution kernel single layer to realize multi-level feature fusion, geLU activation function keeps negative value features to enhance robustness, a structure is simplified Layer Normalization, 30% of calculation load is reduced, personnel behavior recognition accuracy is improved to 98.7%, model convergence speed is increased by 40%, and millisecond real-time response requirements are met;
And constructing a three-level dynamic early warning mechanism based on a multi-factor fusion algorithm, namely automatically increasing the weight when the environmental parameters are suddenly changed, adaptively increasing the behavior weight when the behaviors are abnormal, triggering weight attenuation when the equipment is continuously abnormal, and realizing risk quantification through a laboratory running risk index, so that the early warning response time is shortened to 800ms, and the false alarm rate is reduced to below 5%.
Drawings
Fig. 1 is a diagram of a network architecture of an improvement SwinTransformerBlock.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Embodiment one:
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solution of the present application will be clearly and completely described below with reference to fig. 1 in conjunction with a specific embodiment of the present application.
To solve the problems in the prior art, this embodiment provides an environmental monitoring and evaluating system for an intelligent metering laboratory, including:
the physical entity layer is used for collecting physical sensing data flow in real time through an Internet of things sensor array deployed in a metering laboratory, and the Internet of things sensor array comprises:
the metering device monitoring unit is used for collecting electric parameter signals of voltage, current and power factor in real time;
the personnel behavior capturing unit is arranged on an RGB-D camera in a key area of the laboratory and is used for eliminating shielding interference through multi-frame images.
The environment sensing unit comprises a temperature and humidity sensor, an illumination sensor and a gas concentration detector.
The virtual platform layer is used for constructing a metering laboratory virtual mapping model based on a digital twin technology, wherein the virtual mapping model is a five-dimensional model:
physical object, namely physical entity data acquired by the sensor array of the Internet of things;
twin data, namely iterative optimization data of a physical object, a virtual model and a service system;
Virtual model, namely integrating four-layer digital mapping model of geometry, physics, behavior and rule;
the service system is used for monitoring services provided based on the physical objects and the virtual model;
and data connection, namely a communication link for realizing real-time data transmission among the dimensions.
And carrying out data standardization pretreatment and multisource information characteristic extraction on the collected physical perception data flow at a structural layer of the virtual platform layer, wherein the pretreatment comprises data cleaning, normalization and characteristic dimension reduction.
The method comprises the steps of inputting multisource information characteristics into an improved SwinTransformer model at an intelligent layer of a virtual platform layer, outputting a measurement laboratory personnel behavior classification probability matrix and a device state identification probability matrix, wherein the improved SwinTransformer model is added with a LARGE KERNEL Block module before a window multi-head self-attention W-MSA module, a cross-window attention SW-MSA module and a patch of an original SwinTransformer are combined PATCH MERGING. The specific optimization mechanism comprises:
The depth convolution kernel is adopted to replace the traditional small-size convolution kernel stacking expansion receptive field, and in the embodiment, the depth convolution kernel is a13 multiplied by 13 large kernel, and multistage feature fusion is realized through single-layer convolution;
using GeLU activation functions to replace ReLU activation functions to retain negative characteristic information;
only Layer Normalization layers after the deep convolution are reserved, and the regularization structure is simplified.
As shown in fig. 1, in the improved SwinTransformerBlock network structure diagram, after the image processing is completed in the improved Swin Transformer model, global information exchange is performed through LARGE KERNEL Block, and then information exchange between Patch patches is performed by entering Swin Transformer Block. LARGE KERNEL Block is added before Swin Transformer Block of stage1, stage2 and stage3 respectively, and the expressive ability of feature graphs in the model can be enhanced before the network patches the picture features. The activation function in the modified model does not use the most commonly used ReLU in CNN, but rather uses GeLU in SwinTransformer, and uses less regularized Normalization, leaving only the Layer Normalization (LN) layer behind the deep convolution DEPTHWISE CONVOLUTION. The improved Swin transform model introduces the design of large-core convolution, and carries out multi-round large-core 13×13 convolution before carrying out Shifted Window self-attention, so that the Patch self-attention-based receptive field in the Swin transform model is increased, and the convergence speed and the classification accuracy of the model are improved while the calculation complexity is not increased.
And the decision layer is used for calculating a laboratory operation risk index by adopting a decision-level fusion algorithm based on the personnel behavior classification probability matrix and the device state identification probability matrix, and triggering early warning when the laboratory operation risk index is larger than a preset threshold value.
The decision-level fusion algorithm is based on a measurement laboratory personnel behavior classification probability matrix and a device state recognition probability matrix, comprehensively calculates risk values of all personnel behaviors and device states in a laboratory, calculates environment risk values acquired by an environment sensing unit, and dynamically performs weighted fusion on the personnel behavior risk values, the device state risk values and the environment risk values to obtain a laboratory operation risk index.
The calculation formula of the environmental risk value is as follows:
wherein: Is an environmental risk value; is a temperature risk factor Temperature risk factor when temperature T is in the range of 15 ℃ to 35 °c;As the humidity risk factor, when the humidity H is higher than 85%, the humidity risk factorTaking fixed value of 0.5, and when humidity H is lower than 40%, humidity risk factorAccording to the formulaCalculating, when the humidity H is in the range of 40% to 85%, a humidity risk factorThe value is 0; as the gas concentration risk factor, mainly consider metering carbon monoxide and methane gas in a laboratory, and when the carbon monoxide concentration C exceeds 50ppm, the gas risk factor is formulated Calculating, for methane gas, when the concentration C exceeds 1000ppm, the gas risk factor is formulatedCalculating; and taking the illumination intensity risk factor as 0.5 if the illumination intensity L is smaller than 100lux, otherwise, taking the illumination intensity risk factor as 0.
The calculation process of the laboratory running risk index is as follows:
Assume that there are n data sources (e.g., personnel behavior, device status, environmental parameters), each source being classified into m categories (e.g., normal, warning, dangerous).
The probability matrix for each data source is:
;
wherein: To represent the probability that the ith data source is judged to be category j )。
Assigning weight factorsFor data sourcesThe final class probability is obtained as:
;
wherein: For which the weighted fusion post-table is judged to be of the type Probability of (2) weight factorAccording to the dynamic adjustment of the laboratory environment, in the embodiment, the personnel behavior weight is 0.4, the device state weight is 0.4, the environment risk weight is 0.2, when the gas concentration change rate is more than 10 ppm/s, the environment weight is automatically increased to 0.5, when the personnel behavior risk value is more than 0.7 in 3 continuous preset periods, the behavior weight is increased by 0.1, the device state abnormality lasts for more than 300 seconds, and the device state weight is reduced by 0.15.
And (3) integrating weighted probabilities of all the data sources to generate a laboratory operation risk index, and when the risk index is larger than a preset threshold value, setting the risk index to be 0.7 to trigger grading early warning.
Embodiment two:
the embodiment provides an intelligent metering laboratory environment monitoring and evaluating method, which comprises the following steps:
Acquiring physical sensing data flow through a sensor array of the Internet of things, and eliminating shielding interference by combining multiple frame images;
Generating a personnel behavior and device state probability matrix through an improved SwinTransformer model at an intelligent layer;
And the decision layer calculates a laboratory operation risk index based on the probability matrix, and triggers grading early warning when the risk index exceeds a threshold value.
The process updates the environment information in real time through the database, and performs error compensation on the primary identification result.
Embodiment III:
the present embodiment provides an electronic device, on which a computer program is stored, which when executed by a processor implements a smart metering laboratory environment monitoring and assessment method according to any of the embodiments of the present invention.
Embodiment four:
The present embodiment provides a computer readable medium storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a smart metering laboratory environment monitoring assessment method according to any of the embodiments of the present invention.
In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relation of association objects, and indicates that there may be three kinds of relations, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, c may be single or plural.
Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In several embodiments provided by the present application, any of the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes various media capable of storing program codes, such as a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. A smart metering laboratory environmental monitoring evaluation system, comprising:
The physical entity layer is used for acquiring physical perception data streams in real time through an Internet of things sensor array deployed in a metering laboratory;
the virtual platform layer is used for constructing a metering laboratory virtual mapping model based on a digital twin technology, and comprises the following steps:
the structure layer is used for carrying out data standardization pretreatment and multisource information characteristic extraction on the collected physical perception data flow;
the intelligent layer inputs the multisource information characteristics into an improved SwinTransformer model and outputs a measurement laboratory personnel behavior classification probability matrix and a device state identification probability matrix;
And the decision layer is used for calculating a laboratory operation risk index by adopting a decision-level fusion algorithm based on the personnel behavior classification probability matrix and the device state identification probability matrix, and triggering early warning when the laboratory operation risk index is larger than a preset threshold value.
2. The intelligent metering laboratory environment monitoring and evaluating system according to claim 1, wherein the sensor array of the Internet of things comprises:
the metering device monitoring unit is used for collecting electric parameter signals of voltage, current and power factor in real time;
The personnel behavior capturing unit is an RGB-D camera arranged in a key area of the laboratory;
The environment sensing unit comprises a temperature and humidity sensor, an illumination sensor and a gas concentration detector.
3. The intelligent metering laboratory environment monitoring and evaluating system according to claim 1, wherein the personnel behavior capturing unit eliminates shielding interference through multi-frame images.
4. The intelligent metering laboratory environment monitoring and evaluating system according to claim 1, wherein the metering laboratory virtual mapping model is constructed based on a digital twin technology and is a five-dimensional model:
physical object, namely physical entity data acquired by the sensor array of the Internet of things;
twin data, namely iterative optimization data of a physical object, a virtual model and a service system;
Virtual model, namely integrating four-layer digital mapping model of geometry, physics, behavior and rule;
the service system is used for monitoring services provided based on the physical objects and the virtual model;
and data connection, namely a communication link for realizing real-time data transmission among the dimensions.
5. The intelligent metering laboratory environment monitoring and assessment system of claim 1 wherein said modified SwinTransformer model adds LARGE KERNEL Block modules before the window multi-headed self-attention W-MSA module, cross-window attention SW-MSA module and patch merge PATCH MERGING of original SwinTransformer.
6. The intelligent metering laboratory environment monitoring and evaluating system as set forth in claim 5, wherein said LARGE KERNEL Block module optimizes feature extraction by triple mechanism, comprising:
the deep convolution kernel is adopted to replace the traditional small-size convolution kernel to stack and expand the receptive field, and multi-level feature fusion is realized through single-layer convolution;
using GeLU activation functions to replace ReLU activation functions to retain negative characteristic information;
only Layer Normalization layers after the deep convolution are reserved, and the regularization structure is simplified.
7. The intelligent metering laboratory environment monitoring and evaluating system according to claim 2, wherein the decision-level fusion algorithm is characterized by comprehensively calculating risk values of all personnel behaviors and device states in a laboratory based on a metering laboratory personnel behavior classification probability matrix and a device state recognition probability matrix, calculating environment risk values acquired by an environment sensing unit, and dynamically weighting and fusing the personnel behavior risk values, the device state risk values and the environment risk values to obtain a laboratory operation risk index.
8. The intelligent metering laboratory environment monitoring and evaluating method is characterized by comprising the following steps of:
acquiring a physical sensing data stream through an Internet of things sensor array;
Generating a personnel behavior and device state probability matrix through an improved SwinTransformer model at an intelligent layer;
And the decision layer calculates a laboratory operation risk index based on the probability matrix, and triggers grading early warning when the risk index exceeds a threshold value.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a smart metering laboratory environment monitoring assessment method as claimed in claim 8 when the program is executed by the processor.
10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a smart metering laboratory environment monitoring assessment method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511348082.3A CN121167487A (en) | 2025-09-19 | 2025-09-19 | Intelligent metering laboratory environment monitoring and evaluating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511348082.3A CN121167487A (en) | 2025-09-19 | 2025-09-19 | Intelligent metering laboratory environment monitoring and evaluating method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN121167487A true CN121167487A (en) | 2025-12-19 |
Family
ID=98035682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511348082.3A Pending CN121167487A (en) | 2025-09-19 | 2025-09-19 | Intelligent metering laboratory environment monitoring and evaluating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN121167487A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121745704A (en) * | 2026-03-02 | 2026-03-27 | 中理检验有限公司 | Laboratory security risk intelligent early warning method, system, medium and product |
-
2025
- 2025-09-19 CN CN202511348082.3A patent/CN121167487A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121745704A (en) * | 2026-03-02 | 2026-03-27 | 中理检验有限公司 | Laboratory security risk intelligent early warning method, system, medium and product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119784145A (en) | A security risk analysis system and method based on multimodal data processing | |
| CN118262410A (en) | Dangerous human behavior recognition analysis early warning monitoring system and method | |
| CN107911653A (en) | The module of intelligent video monitoring in institute, system, method and storage medium | |
| CN119168378B (en) | Intelligent waistcoat-assisted environment analysis early warning method and system | |
| CN120183644B (en) | Artificial intelligence-based surgical robot quality control and fault prediction method | |
| CN121167487A (en) | Intelligent metering laboratory environment monitoring and evaluating method and system | |
| CN120145312A (en) | An intelligent security management system based on AI big model | |
| CN119516630A (en) | A photovoltaic field drone inspection system | |
| CN119783047B (en) | A multi-modal data fusion method and system for intelligent weak current monitoring system | |
| CN119449580A (en) | Power optical communication network alarm analysis method and system based on spatiotemporal graph neural network | |
| CN119622274B (en) | Building fire control monitoring system based on thing networking | |
| CN116385239A (en) | An emergency management method based on dynamic perception fusion of disaster site information | |
| CN119479061A (en) | Abnormal behavior recognition method and system based on video analysis | |
| CN120123869A (en) | A vibration spatiotemporal event recognition method based on distributed optical fiber sensing | |
| Chiranjeevi et al. | Adam optimizer based convolutional auto encoder for detecting anomalies in surveillance videos | |
| CN119691568A (en) | Sewage treatment process abnormal condition identification method and system based on deep neural network | |
| CN117390414A (en) | An intelligent identification and positioning method and system for water conservancy emergency drainage and irrigation equipment | |
| CN119299332B (en) | A safety monitoring system and monitoring method based on machine vision | |
| CN120873849A (en) | Abnormality detection multi-classification method based on multi-source fortune data fusion | |
| CN120688010A (en) | Intelligent monitoring method, system and storage medium for vehicle interior environment | |
| CN120561674A (en) | Converter station fault identification method, device, computer equipment and readable storage medium | |
| CN120412243A (en) | A real-time reservoir monitoring method and system based on multimodal collaborative perception | |
| CN119992653A (en) | A hospital security early warning analysis method and system based on AI | |
| CN116740627A (en) | Violation alarm method based on operational knowledge | |
| CN121085074B (en) | Abnormal jump behavior detection method based on multisource acceleration signal feature analysis |
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 |