CN120702337A - High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion - Google Patents

High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion

Info

Publication number
CN120702337A
CN120702337A CN202510972722.1A CN202510972722A CN120702337A CN 120702337 A CN120702337 A CN 120702337A CN 202510972722 A CN202510972722 A CN 202510972722A CN 120702337 A CN120702337 A CN 120702337A
Authority
CN
China
Prior art keywords
data
coal
volume
error
measurement
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
CN202510972722.1A
Other languages
Chinese (zh)
Inventor
杨磊
马战南
马青
韩强
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.)
Beijing Zhongsheng Bofang Intelligent Technology Co ltd
Original Assignee
Beijing Zhongsheng Bofang Intelligent Technology Co ltd
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 Beijing Zhongsheng Bofang Intelligent Technology Co ltd filed Critical Beijing Zhongsheng Bofang Intelligent Technology Co ltd
Priority to CN202510972722.1A priority Critical patent/CN120702337A/en
Publication of CN120702337A publication Critical patent/CN120702337A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a high-precision measurement and calculation method for the storage volume of a digital coal yard based on laser radar and vision fusion, and relates to the technical field of digital coal yards, and the method comprises the following specific steps: the invention effectively reduces the interference of environmental factors on data acquisition by monitoring the environmental parameters in real time and automatically adjusting the working modes and parameters of the sensors, greatly improves the accuracy of data, ensures the normal operation of the sensors by increasing the laser radar transmitting power, adjusting the exposure of the vision sensor, the parameters of the filter and the like according to different environmental conditions such as high dust, and simultaneously establishes an error model and performs error compensation by utilizing historical data, further reduces measurement errors, thereby realizing high-precision measurement of the bulk of the coal yard and providing a reliable basis for the accurate management of links such as coal production, storage, transportation and the like.

Description

Digital coal yard stock volume high-precision measurement and calculation based on laser radar and vision fusion
Technical Field
The invention relates to the technical field of digital coal yards, in particular to a high-precision measurement and calculation method for the volume of a digital coal yard stock based on laser radar and vision fusion.
Background
In the production, storage and transportation processes of coal industry, accurate measurement of the bulk material volume of a coal yard is a vital task, the accurate measurement has non-negligible significance for a plurality of links such as inventory management, cost accounting and the like, along with rapid development of technology, various measurement technologies are continuously emerging, and more possibilities are provided for bulk material volume measurement of the coal yard, wherein a laser radar and a vision sensor technology gradually become research hotspots in the field by virtue of unique advantages of the technology, the laser radar can acquire three-dimensional space information of a target object by emitting laser beams and measuring time of reflected light, the characteristics of high precision and high resolution are achieved, and the vision sensor can acquire two-dimensional image information of the target object and comprises abundant visual characteristics such as colors and textures.
However, the traditional method for measuring the volume of the coal yard stock has various defects, such as manual measurement and some simple instrument measurement, the manual measurement is low in efficiency, the measurement accuracy is greatly influenced by human factors, the accuracy of the measurement result is difficult to ensure, the simple instrument measurement is not attractive when facing complex and changeable coal yard environments, the coal yard environments have the characteristics of unstable illumination conditions, high dust concentration, large temperature and humidity fluctuation and the like, the factors can generate serious interference on data acquisition of the laser radar and the visual sensor, for example, the high dust concentration can lead to scattering of laser beams of the laser radar, the accuracy of three-dimensional point cloud data is reduced, the image acquired by the visual sensor is overexposed or underexposed due to the change of illumination conditions, the quality of the image is influenced, in addition, the existing measurement system lacks self-adaptive capacity for environmental change, the working mode and parameters of the sensor cannot be automatically adjusted according to the change of the environmental parameters, the modern measurement error is large, meanwhile, the traditional system is difficult to track the dynamic change of the coal yard in real time, and the three-dimensional model and the volume data of the coal yard cannot be updated in time, and the requirements on the accuracy of the management of the coal yard are not met.
Disclosure of Invention
The invention aims to make up the defects of the prior art, and provides a digital coal yard stock volume high-precision measuring and calculating method based on laser radar and vision fusion, which can collect environmental parameters such as illumination conditions, dust concentration, temperature, humidity and the like of a coal yard in real time and accurately by reasonably arranging various environmental sensors, automatically adjust working modes and parameters of the laser radar and the vision sensors according to the change of the environmental parameters, reduce the interference of environmental factors on the data collection, and then, the method comprises the steps of processing collected three-dimensional point cloud data and two-dimensional image data by adopting a specific fusion method to form more comprehensive and accurate coal yard stock fusion data, and meanwhile, carrying out error compensation on the collected data by establishing a relation model between environmental parameters and measurement errors to further improve measurement accuracy.
The invention provides the following technical scheme for solving the technical problems, namely, the high-precision measurement and calculation of the volume of the digital coal yard stock based on the fusion of the laser radar and the vision, and the method comprises the following specific steps:
The environmental parameter monitoring and sensor adjustment comprises the steps of arranging environmental sensors at different positions of a coal yard, acquiring parameters in real time, transmitting the parameters to a data processing center, and automatically adjusting the working modes and parameters of a laser radar and a vision sensor to adapt to environmental changes according to the comparison result of the parameters and a preset threshold value and the influence degree of the environmental parameters on the sensor performance;
The laser radar scans according to the mode after adjusting to obtain the three-dimensional point cloud data of the coal yard stock, the vision sensor shoots according to the parameter after adjusting to obtain the two-dimensional image data at the same time, and carry on characteristic extraction and match association to the data, fuse the dataset comprising three-dimensional space and vision information;
Establishing a historical data storage library to record environmental parameters and error data measured each time, analyzing error change rules under different environmental parameters, comprehensively evaluating predicted measurement errors by combining a historical error average value, a current and historical average environmental parameter difference value and residual errors obtained by training a machine learning model, and correcting acquired data;
Continuously acquiring real-time data of a coal yard stockpile by using a laser radar and a vision sensor, comparing and analyzing the data of the coal pile at different moments, judging the shape, the volume change and the material flow condition of the coal pile, and calculating the shape change rate;
And (3) volume measurement, namely preprocessing the fused coal yard stacking data and the updated coal pile three-dimensional model, dividing the model into simple geometric shapes, calculating the respective volumes, summing to obtain the total volume of the coal pile, outputting the result and storing related data and information.
Further, in the environmental parameter monitoring and sensor adjusting step, environmental sensors are arranged at different positions of the coal yard to collect parameters in real time and transmit the parameters to a data processing center, and the sensors comprise an illumination sensor, a dust concentration sensor, a temperature sensor and a humidity sensor.
Furthermore, in the environmental parameter monitoring and sensor adjusting step, the working modes and parameters of the laser radar and the vision sensor are automatically adjusted, and the adjusting formula is as follows: , wherein, Is the parameter value of the sensor after adjustment,Is to adjust the parameter value of the front sensor,Is an environmental parameter adjustment coefficient, is a constant determined according to the sensor type and the degree of influence of environmental parameters on the sensor performance,Is the amount of change in the environmental parameter.
Furthermore, in the error analysis and compensation step, a historical data storage library is established, environmental parameter data and corresponding measurement error data during each measurement are recorded and stored in detail, data in the historical data storage library are arranged and analyzed regularly, the change rule of measurement errors under different environmental parameter conditions is observed, and according to the relation between the environmental parameters obtained through analysis and the measurement errors, when the real-time environmental parameter data are obtained during each measurement, errors possibly occurring in the current measurement are predicted, and the data acquired by the laser radar and the vision sensor are corrected correspondingly according to the predicted errors.
Further, in the error analysis and compensation step, the error possibly occurring in the current measurement is predicted, and the prediction formula is as follows: , wherein, Is a predicted measurement error, for error compensation of the acquired data,The influence coefficients of the history error, the environment parameter variation error and the residual error are respectively,Is an average of the historical measurement errors, reflects the overall level of error in the past measurements,Is a difference vector between the current environmental parameter and the historical average environmental parameter,Is a vector of historical average environmental parameters,The residual error is obtained through training of a machine learning model and is used for capturing an error part which cannot be explained by using a historical error and environmental parameter change.
Further, in the step of modeling and updating the dynamic coal pile, the laser radar and the vision sensor are utilized to continuously collect real-time data of the coal yard material, whether the shape and the volume of the coal pile change or not is analyzed by comparing the data collected at different moments, the material flow condition of the surface of the coal pile is observed, when the change of the shape or the volume of the coal pile is detected, the three-dimensional model of the coal pile is updated according to the newly collected data, including the modification of the coordinates of points on the surface of the coal pile in the model and the adjustment of the shape parameters of the model, and meanwhile, the volume data of the coal pile is recalculated according to the updated three-dimensional model, so that the real-time property and the accuracy of the volume data are ensured.
Furthermore, in the step of modeling and updating the dynamic coal pile, by comparing the data acquired at different moments, whether the shape and the volume of the coal pile change is analyzed, and an analysis formula is as follows: , wherein, Is the change rate of the shape of the coal pile, comprehensively reflects the change condition of the volume and the surface area of the coal pile,Is the variation of the volume of the coal pile, i.e,Is the volume of the coal pile at the last moment,Is the variation of the surface area of the coal pile, i.e,Is the surface area of the coal pile at the previous time.
Furthermore, in the step of measuring and calculating the volume, the model is divided into simple geometric shapes, the volumes are calculated, and then the volumes are summed to obtain the total volume of the coal pile, wherein the calculation formula is as follows: , wherein, Is the total volume of the coal pile,Is the number of tetrahedrons into which the three-dimensional point cloud data of the coal pile is partitioned,Is the firstThree-dimensional coordinate vectors of four vertices of a tetrahedron.
Compared with the prior art, the high-precision measurement and calculation of the digital coal yard stock volume based on the fusion of the laser radar and the vision has the following beneficial effects:
1. according to the invention, through monitoring the environmental parameters in real time and automatically adjusting the working modes and parameters of the sensor, the interference of environmental factors on data acquisition is effectively reduced, the accuracy of data is greatly improved, the normal operation of the sensor is ensured by increasing the laser radar transmitting power, adjusting the exposure and filter parameters of the vision sensor and the like according to different environmental conditions such as high dust, meanwhile, an error model is built and error compensation is carried out by utilizing historical data, and the measurement error is further reduced, so that the high-precision measurement of the coal yard stacking volume is realized, and a reliable basis is provided for the accurate management of links such as coal production, storage and transportation.
2. According to the invention, through dynamic coal pile modeling and updating, the shape change and material flow condition of the coal pile can be tracked in real time, and the three-dimensional model and volume data of the coal pile can be updated in time, so that the requirement on real-time monitoring of the volume of the coal pile is met, related personnel can master the dynamic information of the coal pile at any time, and timely and accurate data support is provided for the work such as coal inventory management and cost accounting.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is an operation chart of a high-precision measurement flow of a digital coal yard stock volume based on laser radar and vision fusion;
FIG. 2 is a flow chart of high-precision measurement and calculation of the stockpile volume of a digital coal yard based on laser radar and vision fusion.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description will refer to the specific implementation, structure, characteristics and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
Example 1
A large thermal power plant is provided with a plurality of large coal yards for storing coal required for power generation, and the coal yards have huge coal reserves and frequent coal loading, unloading and using operations every day, so accurate measurement of the volume of a coal pile is important for inventory management and cost accounting, and if the volume of the coal pile cannot be mastered timely and accurately, insufficient coal supply can influence power generation production or cause inventory backlog to increase cost.
In different positions of a coal yard, including the top of a coal pile, edges and the open area of the coal yard, high-precision illumination sensors, dust concentration sensors, temperature sensors and humidity sensors are installed, the sensors have high sensitivity and stability, environmental parameters of the coal yard can be monitored accurately in real time, as shown in fig. 1, for example, the illumination sensors can accurately measure small changes of illumination intensity, the dust concentration sensors can detect small fluctuation of dust particle concentration in air, the sensors can rapidly transmit environmental parameter data acquired in real time to a data processing center through an advanced wireless communication technology, and the data processing center is provided with a high-performance server and professional data processing software, so that a large amount of environmental parameter data can be analyzed and processed in real time.
When the dust concentration of the coal yard is found to be increased due to coal loading and unloading operation, the data processing center uses the formulaTo adjust sensor parameters, whereCorresponding to the four environmental parameters of illumination, dust concentration, temperature and humidity, for(First)Influence coefficient of environmental parameters on sensor parameter adjustment), in preliminary determination, by testing the measurement accuracy and signal strength of the laser radar in environments with different dust concentrations, the relation between the dust concentration change and the laser radar performance change is recorded, and an initial influence coefficient is given to the dust concentration parameters according to the relationIn the same way, similar experimental tests are carried out on parameters such as illumination, temperature, humidity and the like, in the experimental process, the performance index (such as measurement error, signal stability and the like) of the sensor is taken as the basis for measuring the influence degree of environmental parameters, and the larger the performance index changes, the correspondingThe larger the value is, the more the actual data between the environmental parameter change and the sensor performance is collected as the system operates and data accumulates, and the actual data pairs are utilizedOptimizing and adjusting, adopting regression algorithm in machine learning, taking environmental parameter change as input, sensor performance change as output, and adjusting by training modelTo enable the model to more accurately predict sensor performance changes, thereby achieving more reasonableThe weight of the material to be weighed,The (initial parameter values of the sensor) is determined by factory settings or initial calibration of the sensor,(First)Actual measured values of the environmental parameters) are acquired in real time by corresponding environmental sensors,(First)A reference value for an environmental parameter) is determined from the sensor technology document and the ideal operating environment requirements.
After calculation according to the above formula, the data processing center sends an instruction to the laser radar, the intensity of the emitted signal is properly improved to enhance the dust penetrating capability, and simultaneously sends an instruction to the vision sensor, the exposure time is adjusted to prolong the exposure time, a special filter is started to reduce the interference of dust to image acquisition, when the illumination intensity changes and exceeds the optimal working illumination range of the vision sensor, the data processing center can adjust the exposure parameters of the vision sensor, such as changing the aperture size and adjusting the sensitivity, so as to ensure that the acquired image is clear and accurate, if the temperature and humidity changes exceed the set range, the data processing center can finely adjust the internal parameters of the laser radar and the vision sensor to compensate the influence of environmental changes on the sensor performance, for example, by adjusting the working voltage, current and other parameters of the electronic elements of the sensor, the data processing center is adapted to different temperature and humidity conditions.
The laser radar carries out omnibearing scanning on a plurality of coal piles of a coal yard with high frequency and high precision according to an adjusted working mode, the emitted laser beam can rapidly and accurately measure the distance information of each point on the surface of the coal pile, so as to obtain accurate three-dimensional point cloud data, the point cloud data describe the shape and the spatial structure of the coal pile in detail, the vision sensor synchronously collects two-dimensional image data of the coal pile, the vision sensor has the characteristics of high resolution and wide visual angle, the vision characteristics of the color, texture, shape and the like of the coal pile can be captured, the quality of the collected image is high, the detail is rich, and a data set containing three-dimensional space and vision information is fused through an advanced image collection technology.
Establishing a long-term historical data storage library, recording the environmental parameters, the measurement results and the errors with the actual volume measured each time in detail, establishing an accurate error prediction model by deep analysis of a large amount of historical data and applying a machine learning algorithm and a statistical method, wherein when the environmental temperature and the humidity change greatly, a formula is used by the systemTo predict measurement errors and compensate, whereinFor the predicted measurement errors, for error compensation of the acquired data,Is calculated statistically from the historical measurement data for the average value of the historical measurement errors,Is obtained by statistical analysis of real-time data and historical environmental data acquired by an environmental sensor for the difference vector between the current environmental parameter and the historical average environmental parameter,For the historical average environmental parameter vector to be,In order to train the residual error obtained by machine learning model, the machine learning algorithm is used to train the historical data, the difference value between the model predicted value and the actual measured value is the residual error,Influence coefficients of history error, environment parameter variation error, residual error, respectively, andPreliminary determination ofIn this case, the measurement errors are primarily set based on experience and simple analysis of the historical data, such as the historical data showing that the measurement errors are primarily related to the historical measurement errorsIf the environmental parameter change is found to have a significant effect on the measurement error, then the appropriate increaseFor residual error, a smaller value can be initially set because of the error part which is reflected by the residual error and is difficult to explain, the contribution rate of different factors to the measurement error is calculated by carrying out statistical analysis on the historical data, the initial weight value is determined based on the contribution rate, during adjustment, the weight is optimized and adjusted by adopting methods such as cross validation and the like, the historical data is divided into a training set and a validation set, and different attempts are attempted on the training setCalculating prediction error (such as mean square error) by using the value combination, and adjusting the value combination according to the prediction error performance on the verification set, and continuously optimizing until finding out the minimum prediction errorAnd (3) taking a value, correspondingly correcting the data acquired by the laser radar and the vision sensor according to the prediction result, for example, if the prediction that the measured distance of the laser radar possibly deviates, adjusting the measured distance data, and if the prediction that the image acquired by the vision sensor deforms, correcting the image.
The method is characterized in that the state of a coal pile is continuously monitored by utilizing real-time data of a laser radar and a vision sensor and adopting an advanced data analysis algorithm, when new coal is conveyed to a coal yard and added to the coal pile, the system can rapidly detect the volume and shape change of the coal pile, the degree and direction of the change are judged by calculating the shape change rate of the coal pile, and a formula is used when calculating the shape change rateWhereinThe change rate of the shape of the coal pile is comprehensively reflected to the change condition of the volume and the surface area of the coal pile,For the variation of the volume of the coal pile, i.e.,AndThe three-dimensional model of the coal pile at the front moment and the rear moment is obtained by carrying out volume calculation,For variation of surface area of coal pile, i.e.,AndThe three-dimensional model of the coal pile is obtained by carrying out surface area calculation on the three-dimensional model of the coal pile at the front moment and the rear moment, once the change of the coal pile reaches a certain threshold value, the system immediately starts a three-dimensional model updating program, the three-dimensional model of the coal pile is accurately updated by utilizing a three-dimensional reconstruction technology according to the newly acquired data, the updating process comprises the steps of recalculating the point cloud coordinates of the surface of the coal pile, adjusting the geometric shape and texture information of the model and the like, the updated three-dimensional model can accurately reflect the real-time state of the coal pile, meanwhile, the volume data of the coal pile is recalculated, the inventory information is updated in real time, and a reliable basis is provided for coal purchasing and production scheduling of a power plant.
Preprocessing the fused data and the updated three-dimensional model, removing noise and abnormal points by using an advanced filtering algorithm and a data cleaning technology, then dividing the coal pile model into a plurality of tetrahedrons, and obtaining the model according to a formulaCalculating the volume of each tetrahedron, whereinIs the total volume of the coal pile,In order to divide the three-dimensional point cloud data of the coal pile into tetrahedrons, the tetrahedrons are obtained by processing the three-dimensional point cloud data of the coal pile through a tetrahedron division algorithm,Is the firstThree-dimensional coordinate vectors of four vertexes of each tetrahedron are obtained from three-dimensional point cloud data acquired by a laser radar, the point cloud data are used for tetrahedron segmentation after being preprocessed, finally, the volumes of all tetrahedrons are added to obtain the total volume of a coal pile, a calculation result is displayed in real time through a monitoring system of a power plant, management staff can check the volume information of the coal pile at any time and any place through terminal equipment such as a computer, a mobile phone and the like, meanwhile, the volume data can be stored in a database for subsequent inquiry, analysis and statistics, the database can record time, environmental parameter and other information of volume measurement at each time, historical data tracing and analysis are conveniently carried out by management staff, rules are summarized, and coal yard management is further optimized.
Example two
The coal logistics transfer yard bears the storage and transfer tasks of a large amount of coal, the throughput of the coal is huge every day, the loading, unloading and transferring operations of the coal are frequent, the shape and the volume of the coal pile are dynamically changed at all times due to the changes of the loading and unloading modes of different batches of coal, and the accurate measurement of the volume of the coal pile has a key meaning for logistics dispatching (such as reasonably arranging transportation vehicles and loading and unloading equipment) and cost settlement (such as accurately calculating storage cost and transportation cost), and if the volume measurement is inaccurate, the logistics resource waste is possibly caused, the operation cost is increased, and even the business disputes are caused.
In the different regions of transition, including coal pile intensive region, loading and unloading operation district and peripheral open area, environmental sensor has been rationally and evenly arranged, these sensors have covered high accuracy's illumination sensor, can detect the dust concentration sensor of tiny dust particle concentration, but the temperature sensor of accurate measurement temperature variation and humidity sensor sensitive to humidity variation, all kinds of sensors all possess interference killing feature, characteristics fast response speed, the sensor passes through low-power consumption, high bandwidth wireless communication network, environmental parameter data that will gather in real time is transmitted to data processing center with extremely fast speed, as shown in fig. 2, data processing center is equipped with powerful data analysis server and intelligent data processing software system, can carry out real-time reception to the environmental parameter data of mass, save and degree of depth analysis, when meetting light condition variation (such as cloudy day, fog etc.) and leading to, the data processing center reacts rapidly, according to the corresponding relation model of environmental parameter and sensor performance that establish in advance, automatically regulated vision sensor's exposure parameter, the light sensitivity is not increased, the accuracy of the light sensitivity is little, the accuracy is increased to the accuracy is improved, the full range of data is transmitted to the data, the full range is guaranteed, the laser window is more accurate, the full range of power is transmitted to the data is clear, the laser window is more accurate, the full range is transmitted to the data is more accurate, the full range of power is guaranteed, the laser window is more accurate, the full power is more accurate, the window is more accurate, the accuracy is more than the data, can be more than is convenient, when.
The laser radar adopts an advanced scanning technology, a coal pile in a transfer field is rapidly scanned in a high resolution and a wide coverage range according to an adjusted working mode, the emitted laser beam can accurately measure three-dimensional space coordinates of all points on the surface of the coal pile, high-precision three-dimensional point cloud data are obtained, the three-dimensional form and the spatial distribution of the coal pile are presented in detail by the point cloud data, a high-performance image sensor and a high-quality optical lens are equipped for a vision sensor, two-dimensional image data of the coal pile are synchronously acquired, rich color information, unique texture characteristics and integral shape outline of the coal pile can be captured, the acquired image is ensured to have high definition, high contrast and accurate color reduction degree through an optimized image acquisition algorithm, and a data set containing the three-dimensional space and the vision information is fused.
The method comprises the steps of establishing a historical data storage library, comprehensively recording environmental parameters (including detailed information such as illumination, dust, temperature, humidity and the like) measured each time, measurement results (such as measured coal pile volume, shape and the like) and errors of actual volumes (obtained by comparing with high-precision measurement equipment or methods), carrying out deep analysis and mining on massive historical data by utilizing a data mining technology and a machine learning algorithm, when the change of the environmental parameters is detected, automatically inputting the current environmental parameters into an error prediction model trained by a large amount of data by a system, predicting possible measurement errors according to complex relations between the environmental parameters and the measurement errors in the historical data, wherein when the temperature and the humidity are changed greatly, the model predicts that the measurement accuracy of the laser radar is possibly influenced, and further influences the propagation speed and reflection characteristics of the laser due to the fact that the change of the temperature and the humidity possibly causes the change of a propagation medium of the laser.
The system can detect the volume reduction and accurately judge the specific change of the shape of the coal pile, such as the concave position and degree of the surface of the coal pile, and the like when coal is transported out of the coal pile.
The method comprises the steps of accurately calculating the shape change rate of a coal pile, setting a reasonable threshold value to judge the change amplitude, immediately starting a three-dimensional model updating program by a system once the change of the coal pile exceeds the threshold value, rapidly and accurately updating the three-dimensional model of the coal pile by using an advanced three-dimensional reconstruction algorithm according to newly acquired high-precision data, accurately adjusting the geometric shape of the model to enable the geometric shape of the model to be completely matched with the shape of an actual coal pile, simultaneously updating texture information of the model to enable the texture information to truly reflect the appearance characteristics of the coal pile, synchronously calculating the volume data of the coal pile by the system according to the newly acquired high-precision data, ensuring the real-time property and the accuracy of the volume data, and providing a reliable basis for cost settlement.
Preprocessing the fused coal pile data and the updated three-dimensional model, removing noise points by using a plurality of advanced data processing algorithms, such as a median filtering algorithm, identifying and removing abnormal points based on a statistical analysis method, dividing the coal pile model into a plurality of regular tetrahedrons, accurately calculating the volume of each tetrahedron according to the vertex coordinates of the tetrahedrons by using a high-precision geometrical calculation method, adding the volumes of all tetrahedrons to obtain the total volume of the coal pile, feeding the calculation result back to related personnel in real time through a visual interface of a logistics management system, and meanwhile, the related personnel can check the volume information of the coal pile at any time and any place through terminal equipment such as a computer, a tablet computer or a smart phone, and the like, meanwhile, the volume data can be safely and reliably stored in a database, the database can also record the time of each volume calculation, the environmental parameters, the related data in the measurement process and the like in detail, the subsequent inquiry, analysis and statistics are convenient, the logistics transfer field can be used for outputting coal storage and transfer costs through the analysis of the historical volume data, the logistics scheduling scheme is optimized, the efficiency is improved, and meanwhile, the volume data can be accurately calculated, and the operational disputed is avoided due to the fact that the volume measurement cost is accurately and the measurement cost is not caused.
The present invention is not limited in any way by the above-described preferred embodiments, but is not limited to the above-described preferred embodiments, and any person skilled in the art will appreciate that the present invention can be embodied in the form of a program for carrying out the method of the present invention, while the above disclosure is directed to equivalent embodiments capable of being modified or altered in some ways, it is apparent that any modifications, equivalent variations and alterations made to the above embodiments according to the technical principles of the present invention fall within the scope of the present invention.

Claims (8)

1.基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，该方法包括以下具体步骤：1. High-precision measurement of the volume of stockpiled materials in a digital coal yard based on the fusion of laser radar and vision, characterized in that the method includes the following specific steps: 环境参数监测与传感器调整：在煤场不同位置布置环境传感器实时采集参数并传输至数据处理中心，依据参数与预设阈值对比结果，结合环境参数对传感器性能的影响程度，自动调整激光雷达和视觉传感器的工作模式和参数以适应环境变化；Environmental parameter monitoring and sensor adjustment: Environmental sensors are deployed at different locations in the coal yard to collect parameters in real time and transmit them to the data processing center. Based on the comparison results with preset thresholds and the impact of environmental parameters on sensor performance, the operating mode and parameters of the lidar and vision sensors are automatically adjusted to adapt to environmental changes. 数据采集与融合：激光雷达按调整后的模式扫描获取煤场堆料三维点云数据，同时视觉传感器按调整后的参数拍摄获取二维图像数据，并对数据进行特征提取和匹配关联，融合得到包含三维空间与视觉信息的数据集;Data acquisition and fusion: The LiDAR scans the coal yard using an adjusted pattern to obtain 3D point cloud data. Simultaneously, the visual sensor captures 2D image data using adjusted parameters. Feature extraction and matching are performed on the data, and the resulting data set is fused to include both 3D spatial and visual information. 误差分析与补偿：建立历史数据存储库记录每次测量的环境参数和误差数据，分析不同环境参数下误差变化规律，结合历史误差平均值、当前与历史平均环境参数差值以及机器学习模型训练得到的残差误差，综合评估预测测量误差，并对采集的数据进行修正；Error analysis and compensation: Establish a historical data repository to record the environmental parameters and error data of each measurement, analyze the error variation pattern under different environmental parameters, combine the historical error average, the difference between the current and historical average environmental parameters, and the residual error obtained from machine learning model training, comprehensively evaluate and predict the measurement error, and correct the collected data; 动态煤堆建模与更新：利用激光雷达和视觉传感器持续采集煤场堆料实时数据，对比分析煤堆不同时刻的数据，判断其形状、体积变化及物料流动情况，计算形状变化速率；Dynamic coal pile modeling and updating: Using lidar and vision sensors to continuously collect real-time data on coal piles, we compare and analyze data at different times to determine their shape, volume changes, material flow, and calculate the rate of shape change. 体积测算：对融合后的煤场堆料数据和更新后的煤堆三维模型进行预处理，将模型划分为简单几何形状计算各自体积后求和得煤堆总体积，输出结果并存储相关数据及信息。Volume measurement: Preprocess the fused coal yard stockpile data and the updated coal pile 3D model, divide the model into simple geometric shapes, calculate the volumes of each, and sum them up to obtain the total volume of the coal pile. Output the results and store relevant data and information. 2.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述环境参数监测与传感器调整步骤中，在煤场不同位置布置环境传感器实时采集参数并传输至数据处理中心，传感器包括光照传感器、粉尘浓度传感器、温度传感器和湿度传感器。2. The high-precision measurement of stockpile volume in a digital coal yard based on laser radar and vision fusion according to claim 1 is characterized in that, in the environmental parameter monitoring and sensor adjustment step, environmental sensors are arranged at different locations in the coal yard to collect parameters in real time and transmit them to a data processing center. The sensors include light sensors, dust concentration sensors, temperature sensors, and humidity sensors. 3.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述环境参数监测与传感器调整步骤中，自动调整激光雷达和视觉传感器的工作模式和参数，其调整公式为：，其中，是调整后传感器的参数值，是调整前传感器的参数值，是环境参数调整系数，是根据传感器类型和环境参数对传感器性能影响程度确定的常数，是环境参数变化量。3. The high-precision measurement of stockpile volume in a digital coal yard based on laser radar and vision fusion according to claim 1 is characterized in that, in the environmental parameter monitoring and sensor adjustment step, the operating mode and parameters of the laser radar and vision sensor are automatically adjusted, and the adjustment formula is: ,in, is the parameter value of the sensor after adjustment, It is to adjust the parameter value of the front sensor. Is the environmental parameter adjustment coefficient, which is a constant determined by the type of sensor and the degree of influence of environmental parameters on sensor performance. is the change in environmental parameters. 4.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述误差分析与补偿步骤中，建立历史数据存储库，将每次测量时的环境参数数据和对应的测量误差数据进行详细记录和存储，并定期对历史数据存储库中的数据进行整理和分析，观察不同环境参数条件下测量误差的变化规律，根据分析得到的环境参数与测量误差之间的关系，在每次测量时，当获取到实时环境参数数据后，预测当前测量可能出现的误差，针对预测到的误差，对激光雷达和视觉传感器采集到的数据进行相应的修正。4. The high-precision measurement of the volume of stockpiles in a digital coal yard based on the fusion of laser radar and vision according to claim 1 is characterized in that, in the error analysis and compensation step, a historical data repository is established, and the environmental parameter data and the corresponding measurement error data of each measurement are recorded and stored in detail, and the data in the historical data repository are regularly sorted and analyzed to observe the changing pattern of the measurement error under different environmental parameter conditions. According to the relationship between the environmental parameters and the measurement error obtained by analysis, in each measurement, after obtaining the real-time environmental parameter data, the possible error of the current measurement is predicted, and the data collected by the laser radar and the vision sensor are corrected accordingly based on the predicted error. 5.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述误差分析与补偿步骤中，预测当前测量可能出现的误差，其预测公式为：，其中，是预测的测量误差，用于对采集的数据进行误差补偿，分别是历史误差、环境参数变化误差、残差误差的影响系数，是历史测量误差的平均值，反映过去测量中误差的总体水平，是当前环境参数与历史平均环境参数的差值向量，是历史平均环境参数向量，是通过机器学习模型训练得到的残差误差，用于捕捉无法用历史误差和环境参数变化解释的误差部分。5. The high-precision measurement of stockpile volume in a digital coal yard based on laser radar and vision fusion according to claim 1 is characterized in that, in the error analysis and compensation step, the error that may occur in the current measurement is predicted, and the prediction formula is: ,in, is the predicted measurement error, which is used to compensate the error of the collected data. are the influence coefficients of historical error, environmental parameter change error, and residual error, is the average value of historical measurement errors, reflecting the overall level of errors in past measurements. is the difference vector between the current environmental parameters and the historical average environmental parameters, is the historical average environmental parameter vector, It is the residual error obtained through machine learning model training, which is used to capture the error part that cannot be explained by historical errors and changes in environmental parameters. 6.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述动态煤堆建模与更新步骤中，利用激光雷达和视觉传感器持续不断地采集煤场堆料的实时数据，通过对不同时刻采集到的数据进行对比，分析煤堆的形状和体积是否发生变化，并且观察煤堆表面的物料流动情况，当检测到煤堆的形状或体积发生变化时，根据新采集到的数据，对煤堆的三维模型进行更新，包括修改模型中煤堆表面的点的坐标、调整模型的形状参数，同时，根据更新后的三维模型，重新计算煤堆的体积数据，确保体积数据的实时性和准确性。6. The high-precision measurement of the volume of digital coal yard stockpiles based on the fusion of laser radar and vision according to claim 1 is characterized in that, in the dynamic coal pile modeling and updating step, laser radar and vision sensors are used to continuously collect real-time data of the coal yard stockpiles, and by comparing the data collected at different times, the shape and volume of the coal pile are analyzed to see if they have changed, and the material flow on the surface of the coal pile is observed. When a change in the shape or volume of the coal pile is detected, the three-dimensional model of the coal pile is updated according to the newly collected data, including modifying the coordinates of the points on the surface of the coal pile in the model and adjusting the shape parameters of the model. At the same time, the volume data of the coal pile is recalculated according to the updated three-dimensional model to ensure the real-time and accuracy of the volume data. 7.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述动态煤堆建模与更新步骤中通过对不同时刻采集到的数据进行对比，分析煤堆的形状和体积是否发生变化，其分析公式为： ，其中，是煤堆形状变化速率，综合反映煤堆体积和表面积的变化情况，是煤堆体积的变化量，即，是上一时刻煤堆的体积，是煤堆表面积的变化量，即，是上一时刻煤堆的表面积。7. The high-precision measurement of stockpile volume in a digital coal yard based on laser radar and vision fusion according to claim 1 is characterized in that the dynamic coal pile modeling and updating step compares data collected at different times to analyze whether the shape and volume of the coal pile have changed. The analysis formula is: ,in, It is the rate of change of the shape of the coal pile, which comprehensively reflects the changes in the volume and surface area of the coal pile. is the change in the volume of the coal pile, that is, , is the volume of the coal pile at the previous moment, is the change in the surface area of the coal pile, that is, , is the surface area of the coal pile at the previous moment. 8.根据权利要求1所述的基于激光雷达与视觉融合的数字化煤场堆料体积高精度测算，其特征在于，所述体积测算步骤中，将模型划分为简单几何形状计算各自体积后求和得煤堆总体积，计算公式为：，其中，是煤堆的总体积，是将煤堆三维点云数据分割成的四面体的数量，是第个四面体的四个顶点的三维坐标向量。8. The high-precision volume calculation method for digital coal yards based on laser radar and vision fusion according to claim 1 is characterized in that, in the volume calculation step, the model is divided into simple geometric shapes, the volumes of each shape are calculated, and the total volume of the coal pile is obtained by summing them up. The calculation formula is: ,in, is the total volume of the coal pile, is the number of tetrahedrons into which the three-dimensional point cloud data of the coal pile is divided, It is The three-dimensional coordinate vectors of the four vertices of a tetrahedron.
CN202510972722.1A 2025-07-15 2025-07-15 High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion Pending CN120702337A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510972722.1A CN120702337A (en) 2025-07-15 2025-07-15 High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510972722.1A CN120702337A (en) 2025-07-15 2025-07-15 High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion

Publications (1)

Publication Number Publication Date
CN120702337A true CN120702337A (en) 2025-09-26

Family

ID=97109370

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510972722.1A Pending CN120702337A (en) 2025-07-15 2025-07-15 High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion

Country Status (1)

Country Link
CN (1) CN120702337A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120846255A (en) * 2025-09-22 2025-10-28 成都秦川物联网科技股份有限公司 Workpiece flatness measurement method, device, medium and equipment based on industrial Internet of Things
CN121363915A (en) * 2025-12-19 2026-01-20 江苏新蓝天钢结构有限公司 Intelligent detection and comparison method for bridge jig accuracy based on design reference

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120846255A (en) * 2025-09-22 2025-10-28 成都秦川物联网科技股份有限公司 Workpiece flatness measurement method, device, medium and equipment based on industrial Internet of Things
CN121363915A (en) * 2025-12-19 2026-01-20 江苏新蓝天钢结构有限公司 Intelligent detection and comparison method for bridge jig accuracy based on design reference

Similar Documents

Publication Publication Date Title
CN120702337A (en) High-precision calculation of stockpile volume in digital coal yard based on laser radar and vision fusion
CN120404847B (en) Photovoltaic panel surface defect detection method and system based on physical characteristic analysis
CN119991100B (en) Intelligent inspection system and method for coal conveyor belt of thermal power unit based on artificial intelligence
CN119295677B (en) Multi-angle LED detection light source switching method, device, equipment and storage medium
CN118657772B (en) Accurate detection method and system for concrete pavement changes based on high-resolution remote sensing images
CN118298001A (en) Measuring and calculating method, system and device for sand carrier measuring party
CN120628021A (en) A settlement monitoring system based on computer vision
CN121067715A (en) Machine vision-based three-dimensional measurement method and device for large-size parts
CN121415243A (en) A Three-Dimensional Intelligent Identification System and Method for Tunnel Defects Based on a Large Model
CN121053426A (en) Intelligent Acceptance Methods and Terminal Equipment for Materials
CN120397614A (en) Belt tear laser scanning detection device and belt longitudinal tear laser detection method
CN120339282A (en) A UAV visual target tracking method and system
Chen et al. Irregular object measurement method based on improved adaptive slicing method
CN120126037A (en) A building measurement system and method based on drone mapping
CN119722584A (en) A nondestructive testing system for industrial parts production based on 3D point cloud matching
CN119380170A (en) Performance detection data processing and analysis method and system for denture engraving machine
US12529654B2 (en) Detecting changes in forest composition
CN118351169A (en) Bulk material volume online monitoring method, equipment and medium based on laser three-dimensional reconstruction
CN121074116B (en) Shield slag earth volume estimation method and system based on image processing
CN120806822B (en) Intelligent Warehouse Management Method for Stone Panels Based on Machine Vision
CN121482031B (en) Fine decoration air crack seepage quality problem detection method and device based on multi-source image data fusion
CN120252553B (en) Battery cell size measurement method and system based on machine vision
CN120027742B (en) Wall surface flatness detection method based on laser area array radar
CN120908102B (en) A visual data acquisition system and method for water meter calibration process
CN119359711B (en) Automatic detection and classification system for thermos cup surface defects based on image recognition

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