Wagon balance compliance monitoring method and system based on monitoring rules

Abstract

The invention discloses a wagon balance compliance monitoring method and system based on a monitoring rule, and relates to the technical field of wagon balance compliance monitoring, and the system comprises the following components: an intelligent monitoring algorithm module which carries out the learning and analysis of preprocessed data through employing an advanced machine learning or deep learning algorithm, and carries out the analysis of the data; the module can automatically identify and extract the compliance mode of the wagon balance, the monitoring accuracy and efficiency are improved, the intelligent monitoring algorithm module adopts a neural network model, the compliance mode is automatically learned and identified from a large amount of wagon balance weighing data, the efficiency and accuracy of the system are greatly improved, and the system reliability is improved. And meanwhile, the neural network model has strong data processing capability, can process massive real-time data and extract key information and characteristics from the data, so that the system can monitor the compliance state of the wagon balance in real time and find abnormal or illegal behaviors in time.

Description

Technical Field

[0001] The present invention relates to the technical field of compliance monitoring of a weighbridge, and in particular to a method and system for compliance monitoring of a weighbridge based on monitoring rules. Background Art

[0002] With the continuous growth and complexity of the global logistics industry, the accuracy and compliance monitoring of weighing scales, as indispensable weighing equipment in logistics transportation, has become particularly important. The compliance monitoring of weighing scales is directly related to the fairness and efficiency of logistics transactions, and also plays a vital role in preventing cheating and overloading violations.

[0003] However, traditional compliance monitoring methods for weighbridges mainly rely on manual inspection and fixed monitoring rules. Manual inspection is not only inefficient, but also easily affected by human factors, resulting in false alarms or missed reports. With the rapid development of the logistics industry, the frequency of use of weighbridges and the amount of data processed have increased dramatically. Manual inspection methods can no longer meet actual needs, and fixed monitoring rules are often difficult to adapt to changing business needs and operating environments. The use scenarios of weighbridges in the logistics industry are complex and diverse. The type, weight and mode of transportation of goods may affect the compliance of the weighbridge. Fixed monitoring rules often cannot fully cover various situations, resulting in poor monitoring results.

[0004] Therefore, how to construct a weighbridge compliance monitoring method and system based on intelligent monitoring algorithms has become an important direction for the development of current weighbridge compliance monitoring technology. However, most of the weighbridge compliance monitoring methods and systems based on monitoring rules on the market can only meet some of the requirements of the above-mentioned characteristics, and cannot automatically learn and identify the compliance mode of the weighbridge, process large amounts of real-time data, and automatically adjust the monitoring rules. Therefore, developing a weighbridge compliance monitoring method and system based on monitoring rules that can comprehensively realize the above-mentioned characteristics is of great significance to improving monitoring efficiency and accuracy and reducing false alarm rates. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a compliance monitoring method and system for weighbridges based on monitoring rules. The method and system can automatically learn and identify the compliance patterns of weighbridges through an intelligent monitoring algorithm module using a neural network model and an optimization algorithm. The system can also process a large amount of real-time data and automatically adjust the monitoring rules to adapt to the ever-changing business needs and operating environment. The system can improve monitoring efficiency and accuracy, reduce the false alarm rate, and provide a more comprehensive, efficient and intelligent solution for compliance monitoring of weighbridges in the logistics industry.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a weighbridge compliance monitoring system and method, the system comprising the following components: Data acquisition module: responsible for real-time and accurate collection of weighing data from the scale, including vehicle weight, timestamp, and operator information. The real-time and accuracy of the data are ensured by connecting to the sensor or controller of the scale. The collected data will be transmitted to the subsequent data preprocessing module for further processing; Data preprocessing module: responsible for cleaning, screening and formatting the collected raw data, eliminating noise, outliers and redundant information in the data, ensuring the quality of data for subsequent algorithm processing, and making it easier for the intelligent monitoring algorithm module to understand and analyze; Intelligent monitoring algorithm module: By adopting advanced machine learning or deep learning algorithms to learn and analyze pre-processed data, this module can automatically identify and extract compliance patterns of weighbridges, and automatically adjust monitoring rules based on historical data and real-time data, so that the system can adapt to changing business needs and operating environments, and improve the accuracy and efficiency of monitoring; Result output module: responsible for displaying the analysis results of the intelligent monitoring algorithm module to the user in an intuitive and easy-to-understand manner, including the compliance status of the scale, detailed information on abnormal or illegal behaviors, and corresponding processing suggestions. This module can send results to users in a variety of ways (such as interface display, SMS notification, and email) to ensure that users can understand the compliance status of the scale in a timely manner.

[0007] Furthermore, the data acquisition module uses real-time data acquisition technology to ensure the real-time and accuracy of the data, and its data acquisition frequency meets the requirements of its formula , where: Frequency represents the data collection frequency of the data collection module, measured in times per second (Hz); MaxTolerableLatency represents the maximum delay time that the system can tolerate, that is, the maximum time interval from the generation to the collection of data that the system can accept, measured in seconds (s); real-time data collection technology ensures that the system can quickly obtain the weighing data and other relevant information of the scale, thereby monitoring the compliance status of the scale in real time.

[0008] Furthermore, the data preprocessing module uses a standardized formula to preprocess the original data to improve data quality and ensure data consistency and comparability. The standardized formula is: ,in: Represents raw data, i.e. unprocessed weighing data or other related data. Represents the mean of the original data, that is, the arithmetic mean of all data values. Represents the standard deviation of the original data, reflecting the degree of dispersion of the data values. It represents the data after standardization, with a mean of 0 and a standard deviation of 1. The standardized data is obtained by calculating the mean and standard deviation of the original data and then using the standardized formula to process the original data. The standardized data has better comparability and interpretability, and can improve the accuracy and efficiency of subsequent intelligent monitoring algorithms.

[0009] Furthermore, the intelligent monitoring algorithm module has the following specific steps: (1) Feature extraction: Obtain the formatted data set from the preprocessing module and extract features related to the compliance of the weighbridge from the data set, such as weight change and time distribution; (2) Model training and evaluation: Use historical data to train machine learning or deep learning models to enable them to identify and predict compliance patterns of weighbridges, and evaluate the trained models to check their accuracy and generalization ability; (3) Real-time monitoring: input real-time data into the trained model to conduct real-time monitoring and judgment of the compliance of the weighbridge; (4) Rule adjustment: Based on real-time monitoring results and feedback, the monitoring rules are automatically adjusted to adapt to changing business needs and operating environment.

[0010] Furthermore, the intelligent monitoring algorithm module uses a neural network model to extract features from input data and calculate compliance scores. For any network layer: Through this algorithm, the input data is processed by linear transformation and nonlinear activation functions of multiple network layers, and finally the compliance score is output. By continuously optimizing the structure and parameters of the neural network model, the accuracy and efficiency of compliance monitoring of the weighbridge can be improved.

[0011] Furthermore, the intelligent monitoring algorithm module performs compliance judgment on the real-time data processed by the data preprocessing module, and finally the result output module displays the compliance result. The compliance judgment formula is: ,in: Compliance score is a quantitative indicator used to evaluate the compliance of weighbridge operations. The higher the score, the better the compliance; the lower the score, the more likely there is non-compliant operation. It is a model trained by machine learning or deep learning algorithms that can calculate compliance scores based on real-time data from weighbridges. The data representing the weighing of the scale is one of the core information of the scale operation. The system monitors the weighing data of the scale in real time to determine whether it is within the specified weight range. Represents timestamp information, used to record the specific time of weighbridge operation. Represents operator information, including the operator's identity and authority. The system can determine whether the operation is performed by a person with corresponding authority based on the operator information. This module uses the trained model to process the data and calculate the compliance score. It also performs binary classification judgment by setting thresholds, i.e., compliance or non-compliance. At the same time, it performs multi-classification judgment based on the score to more carefully evaluate the degree of compliance.

[0012] Furthermore, the intelligent monitoring algorithm module uses an optimization algorithm based on the gradient descent method to adjust the model parameters to improve the accuracy and efficiency of monitoring. The formula is: , the intelligent monitoring algorithm module first uses the initial parameter set The real-time data of the weighbridge is processed and the compliance score is calculated. The optimization algorithm is based on the loss function The value of the gradient is calculated , and use formulas to update parameters and repeat until a certain stopping condition is met. By automatically adjusting the optimization algorithm of the monitoring rules, the system can continuously learn from new data and improve its performance, which helps to improve the accuracy and efficiency of compliance monitoring of the weighbridge and reduce false alarms and missed reports.

[0013] Furthermore, the result output module uses visualization technology to display the monitoring results to the user. The visualization technology includes charts and reports. Specifically, the data points displayed in the visualization chart satisfy the formula: ,in: It is a timestamp, which indicates the specific time of weighbridge operation or data recording, and is used to identify the time dimension of data points in the chart. It is the compliance score, which is a quantitative indicator calculated by the system through an intelligent monitoring algorithm. It is used to evaluate the compliance level of the weighbridge operation. The score is used to represent the value or height of a data point in the chart so that users can intuitively understand the compliance status at each point in time. A detailed monitoring report will be generated to notify users of the compliance status of the weighbridge via SMS or email to ensure that users can understand the compliance status of the weighbridge in a timely manner. Based on the monitoring results, corresponding processing suggestions or solutions will be provided to users to help them better manage the weighbridge.

[0014] Furthermore, the system also includes a user management function, allowing users to set and adjust monitoring rules, view historical records and perform other related operations.

[0015] Furthermore, the specific steps of the method are: (1) System startup and preparation: Start the weighbridge compliance monitoring system, ensure that the data collection module, data preprocessing module, intelligent monitoring algorithm module and result output module are in normal working condition, and configure system parameters, including data collection frequency, data preprocessing rules, and intelligent monitoring algorithm parameter settings, to adapt to specific business needs and operating environment; (2) Data collection: The data collection module starts to collect weighing data from the scale in real time, including vehicle weight, timestamp, and operator information. The system stores the collected data in a database for subsequent processing and analysis. (3) Data preprocessing: The data preprocessing module cleans, filters and formats the collected raw data to eliminate noise, missing values ​​and outliers and improve data quality. The preprocessed data will be transmitted to the intelligent monitoring algorithm module for further analysis and processing; (4) Operation of intelligent monitoring algorithm: The intelligent monitoring algorithm module uses advanced machine learning or deep learning algorithms to learn and analyze pre-processed data, automatically identify and extract compliance patterns of the scales, and automatically adjust the monitoring rules based on historical data and real-time data to adapt to changing business needs and operating environments. The calculated compliance score or other relevant indicators are passed as output results to the result output module; (5) Result output and feedback: The result output module outputs the compliance status of the weighbridge based on the analysis results of the intelligent monitoring algorithm module. If the weighbridge operation is compliant, the system will display it normally; if an abnormality or violation is found, the system will immediately generate an alarm, and the system will send the alarm information to relevant personnel via SMS, email, or system notification so that timely measures can be taken to intervene or adjust; (6) Monitoring and maintenance: Regularly monitor and inspect the system to ensure that the data collection, preprocessing, algorithm operation and result output modules are in normal working condition. Adjust system parameters and algorithm settings in a timely manner according to business needs and environmental changes to maintain the optimal performance of the system. At the same time, regularly maintain and upgrade the system to fix potential problems, add new functions and improve system performance; (7) Data analysis and reporting: The system can generate detailed data analysis reports, including the compliance of weighbridge operations, statistics and analysis of abnormal or illegal behaviors. The reports can be customized as needed to meet the needs of different users and management.

[0016] Compared with the prior art, the monitoring rule-based weighbridge compliance monitoring method and system have the following beneficial effects: 1. The present invention adopts a neural network model through an intelligent monitoring algorithm module to automatically learn and identify compliance patterns from a large amount of weighing data of the scale, greatly improving the efficiency and accuracy of the system. At the same time, the neural network model has powerful data processing capabilities, can process massive real-time data, and extract key information and features from it, so that the system can monitor the compliance status of the scale in real time and detect abnormalities or violations in a timely manner.

[0017] 2. The present invention adopts an optimization algorithm through an intelligent monitoring algorithm module to enable the system to more accurately identify and judge the compliance status of the scale. By continuously optimizing and adjusting the model parameters, the system can reduce system crashes or misjudgments caused by improper model parameter settings or environmental changes. The system can reduce false alarm rates and missed alarm rates and improve the precision and accuracy of monitoring. At the same time, through accurate monitoring and timely feedback, the system can also help enterprises avoid economic losses caused by cheating or errors.

[0018] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a compliance monitoring method for weighbridges based on monitoring rules and a system process operation diagram. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1 This embodiment describes in detail the specific implementation of the weighbridge compliance monitoring method and system based on the neural network model. First, the data acquisition module adopts real-time data acquisition technology to ensure that the data acquisition frequency is: , in is the maximum delay time that the system can tolerate. The real-time collected data includes the weighing data, timestamp and operator information of the scale. The data preprocessing module uses a standardized formula to preprocess the data. The formula is: , Among them, among them: Represents raw data, i.e. unprocessed weighing data or other related data. Represents the mean of the original data, that is, the arithmetic mean of all data values. Represents the standard deviation of the original data, reflecting the degree of dispersion of the data values. It represents the data after standardization, with a mean of 0 and a standard deviation of 1. The intelligent monitoring algorithm module uses a neural network model to make compliance judgments. The neural network model consists of multiple network layers, and each layer performs linear transformation and nonlinear activation function processing. Taking the lth layer as an example, its output can be expressed as: , in is the output (or input data) of the previous layer, and are the weights and biases of the lth layer, Is the activation function. During the model training process, the neural network model is trained using historical data, and the model parameters are adjusted using an optimization algorithm based on gradient descent. The update formula of the optimization algorithm is: , in, are model parameters, is the learning rate, is the loss function. After the model training is completed, the real-time monitoring module inputs the real-time data into the trained model to conduct real-time monitoring and judgment of the compliance of the weighbridge. The compliance judgment formula is: , in, represents the neural network model, and are the weights and biases of the model, and Data is real-time data. Based on the calculated compliance score, the system can determine the compliance status of the scale and output the corresponding results. The result output module uses visualization technology to display the monitoring results to the user, including a time series chart of the compliance score and a detailed report. The data points of the visualization chart meet the formula: , in, Indicates the specific time of weighbridge operation or data recording. It is a quantitative indicator calculated by the system through an intelligent monitoring algorithm, which is used to evaluate the compliance level of the weighbridge operation. The score is used to represent the value or height of a data point in the chart so that users can intuitively understand the compliance status at each point in time. A detailed monitoring report will be generated to notify users of the compliance status of the weighbridge via SMS or email, ensuring that users can understand the compliance status of the weighbridge in a timely manner. Based on the monitoring results, corresponding processing suggestions or solutions will be provided to users to help them better manage the weighbridge.

[0023] To sum up, the weighbridge compliance monitoring method and system based on the neural network model in this embodiment realizes real-time monitoring and judgment of the compliance of the weighbridge through real-time data collection, data preprocessing, intelligent monitoring algorithm and result output module. The system can automatically learn and adapt to new data, improve the accuracy and efficiency of monitoring, and provide an effective solution for the compliance management of the weighbridge.

[0024] Example 2 This embodiment introduces in detail the compliance monitoring rule adjustment mechanism of the weighbridge based on the gradient descent optimization algorithm. During the real-time monitoring process, when the system detects abnormal or illegal behavior, it can automatically collect new data samples and adjust the parameters of the neural network model through the gradient descent optimization algorithm to adapt to the new situation and improve the accuracy and efficiency of monitoring. The system uses the trained neural network model to process the real-time collected weighbridge weighing data and calculate the compliance score. The calculation formula is: , in, represents the neural network model, and It is the weight and bias item of the model. Data is real-time data. The score reflects the compliance degree of the weighbridge operation and is an important basis for the system to judge whether there are abnormalities or violations. The system sets one or more compliance score thresholds to judge whether the compliance score calculated in real time is abnormal. When the compliance score is lower than the preset threshold, the system considers that there may be abnormalities or violations and triggers the rule adjustment mechanism. Once the system detects abnormalities or violations, it will enter the rule adjustment stage, which includes several steps: (1) Data collection: The system collects data samples related to abnormal or illegal behaviors, including weighing data, timestamps, and operator information. These data will be used as new training samples to adjust the parameters of the neural network model; (2) Model parameter adjustment: Use an optimization algorithm based on gradient descent to adjust the parameters of the neural network model. Based on the new training samples, the system calculates the gradient of the loss function with respect to the model parameters and updates the model parameters based on the gradient. The update formula of the optimization algorithm is: , Through continuous iteration and optimization, the model can better identify and handle new anomalies or violations; (3) Model evaluation: After each parameter update, the system uses the validation set to evaluate the model. The validation set is a data set independent of the training set and the test set, which is used to check the accuracy and generalization ability of the model. If the performance of the model on the validation set meets the requirements (such as the accuracy and recall rate indicators reach the preset threshold), the rule adjustment is completed; otherwise, the system will continue to execute steps 2 and 3 until the stopping condition is met (such as reaching the maximum number of iterations and the validation set performance no longer improves).

[0025] When the model adjustment is completed, the system will apply the updated monitoring rules to real-time monitoring. The new rules are based on the latest data and model parameters and can more accurately identify and judge the compliance of the scale. The system will continue to process and analyze new real-time data to ensure the compliance of the scale operation.

[0026] In summary, this embodiment introduces a rule adjustment mechanism based on the gradient descent optimization algorithm, so that the weighbridge compliance monitoring system can automatically learn from new data and improve its performance. When the system detects an abnormality or violation, it can automatically collect new data samples and adjust the parameters of the neural network model to adapt to the new situation. This adaptive monitoring rule adjustment mechanism improves the accuracy and efficiency of the system, enabling it to better cope with the complex and changeable weighbridge operating environment.

[0027] Example 3 The steps of the system based on Example 1 and Example 2 are as follows: (1) System startup and preparation: Start the weighbridge compliance monitoring system, ensure that the data collection module, data preprocessing module, intelligent monitoring algorithm module and result output module are in normal working condition, and configure system parameters, including data collection frequency, data preprocessing rules, and intelligent monitoring algorithm parameter settings, to adapt to specific business needs and operating environment; (2) Data collection: The data collection module starts to collect weighing data from the scale in real time, including vehicle weight, timestamp, and operator information. The system stores the collected data in a database for subsequent processing and analysis. (3) Data preprocessing: The data preprocessing module cleans, filters and formats the collected raw data to eliminate noise, missing values ​​and outliers and improve data quality. The preprocessed data will be transmitted to the intelligent monitoring algorithm module for further analysis and processing; (4) Operation of intelligent monitoring algorithm: The intelligent monitoring algorithm module uses advanced machine learning or deep learning algorithms to learn and analyze pre-processed data, automatically identify and extract compliance patterns of the scales, and automatically adjust the monitoring rules based on historical data and real-time data to adapt to changing business needs and operating environments. The calculated compliance score or other relevant indicators are passed as output results to the result output module; (5) Result output and feedback: The result output module outputs the compliance status of the weighbridge based on the analysis results of the intelligent monitoring algorithm module. If the weighbridge operation is compliant, the system will display it normally; if an abnormality or violation is found, the system will immediately generate an alarm, and the system will send the alarm information to relevant personnel via SMS, email, or system notification so that timely measures can be taken to intervene or adjust; (6) Monitoring and maintenance: Regularly monitor and inspect the system to ensure that the data collection, preprocessing, algorithm operation and result output modules are in normal working condition. Adjust system parameters and algorithm settings in a timely manner according to business needs and environmental changes to maintain the optimal performance of the system. At the same time, regularly maintain and upgrade the system to fix potential problems, add new functions and improve system performance; (7) Data analysis and reporting: The system can generate detailed data analysis reports, including the compliance of weighbridge operations, statistics and analysis of abnormal or illegal behaviors. The reports can be customized as needed to meet the needs of different users and management.

[0028] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method and system for monitoring compliance of a weighbridge based on monitoring rules, characterized in that: The system consists of the following components: Data acquisition module: responsible for real-time and accurate collection of weighing data from the scale, including vehicle weight, timestamp and operator information. The real-time and accuracy of the data are ensured by connecting to the sensor or controller of the scale. The collected data will be transmitted to the subsequent data preprocessing module for further processing. Data preprocessing module: responsible for cleaning, screening and formatting the collected raw data, eliminating noise, outliers and redundant information in the data, ensuring the quality of data for subsequent algorithm processing, and making it easier for the intelligent monitoring algorithm module to understand and analyze; Intelligent monitoring algorithm module: By adopting advanced machine learning or deep learning algorithms to learn and analyze pre-processed data, this module can automatically identify and extract compliance patterns of weighbridges, and automatically adjust monitoring rules based on historical data and real-time data, so that the system can adapt to changing business needs and operating environments, and improve the accuracy and efficiency of monitoring; Result output module: responsible for displaying the analysis results of the intelligent monitoring algorithm module to the user in an intuitive and easy-to-understand manner, including the compliance status of the scale, detailed information on abnormal or illegal behaviors, and corresponding processing suggestions. This module can send results to users in a variety of ways (such as interface display, SMS notification, and email) to ensure that users can understand the compliance status of the scale in a timely manner.

2. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The data acquisition module adopts real-time data acquisition technology to ensure the real-time and accuracy of the data, and its data acquisition frequency meets the requirements of its formula , where: Frequency represents the data collection frequency of the data collection module, measured in times per second (Hz); MaxTolerableLatency represents the maximum delay time that the system can tolerate, that is, the maximum time interval from the generation to the collection of data that the system can accept, measured in seconds (s); real-time data collection technology ensures that the system can quickly obtain the weighing data and other relevant information of the scale, thereby monitoring the compliance status of the scale in real time.

3. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The data preprocessing module uses a standardized formula to preprocess the original data to improve data quality and ensure data consistency and comparability. The standardized formula is: ,in: Represents raw data, i.e. unprocessed weighing data or other related data. Represents the mean of the original data, that is, the arithmetic mean of all data values. Represents the standard deviation of the original data, reflecting the degree of dispersion of the data values. It represents the data after standardization, with a mean of 0 and a standard deviation of 1. The standardized data is obtained by calculating the mean and standard deviation of the original data and then using the standardized formula to process the original data. The standardized data has better comparability and interpretability, and can improve the accuracy and efficiency of subsequent intelligent monitoring algorithms.

4. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The specific steps of the intelligent monitoring algorithm module are as follows: (1) Feature extraction: Obtain the formatted data set from the preprocessing module and extract features related to the compliance of the weighbridge from the data set, such as weight change and time distribution; (2) Model training and evaluation: Use historical data to train machine learning or deep learning models to enable them to identify and predict compliance patterns of weighbridges, and evaluate the trained models to check their accuracy and generalization ability; (3) Real-time monitoring: input real-time data into the trained model to conduct real-time monitoring and judgment of the compliance of the weighbridge; (4) Rule adjustment: Based on real-time monitoring results and feedback, the monitoring rules are automatically adjusted to adapt to changing business needs and operating environment.

5. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The intelligent monitoring algorithm module uses a neural network model to extract features from input data and calculate compliance scores. For any network layer: Through this algorithm, the input data is processed by linear transformation and nonlinear activation functions of multiple network layers, and finally the compliance score is output. By continuously optimizing the structure and parameters of the neural network model, the accuracy and efficiency of compliance monitoring of the weighbridge can be improved.

6. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 3, characterized in that: The intelligent monitoring algorithm module performs compliance judgment on the real-time data processed by the data preprocessing module, and finally the compliance result is displayed by the result output module. The compliance judgment formula is: ,in: Compliance score is a quantitative indicator used to evaluate the compliance of weighbridge operations. The higher the score, the better the compliance; the lower the score, the more likely there is non-compliant operation. It is a model trained by machine learning or deep learning algorithms that can calculate compliance scores based on real-time data from weighbridges. The data representing the weighing of the scale is one of the core information of the scale operation. The system monitors the weighing data of the scale in real time to determine whether it is within the specified weight range. Represents timestamp information, used to record the specific time of weighbridge operation. Represents operator information, including the operator's identity and authority. The system can determine whether the operation is performed by a person with corresponding authority based on the operator information. This module uses the trained model to process the data and calculate the compliance score. It also performs binary classification judgment by setting thresholds, i.e., compliance or non-compliance. At the same time, it performs multi-classification judgment based on the score to more carefully evaluate the degree of compliance.

7. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 4, characterized in that: The intelligent monitoring algorithm module uses an optimization algorithm based on the gradient descent method to adjust the model parameters to improve the accuracy and efficiency of monitoring. The formula is: , the intelligent monitoring algorithm module first uses the initial parameter set The real-time data of the weighbridge is processed and the compliance score is calculated. The optimization algorithm is based on the loss function The value of the gradient is calculated , and use the formula to update the parameters and repeat until a certain stopping condition is met. By automatically adjusting the optimization algorithm of the monitoring rules, the system can continuously learn from new data and improve its performance, which helps to improve the accuracy and efficiency of compliance monitoring of the weighbridge and reduce the false alarm rate and missed alarm rate.

8. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 5, characterized in that: The result output module uses visualization technology to display the monitoring results to the user. The visualization technology includes charts and reports. Specifically, the data points displayed in the visualization chart satisfy the formula: ,in: It is a timestamp, which indicates the specific time of weighbridge operation or data recording, and is used to identify the time dimension of data points in the chart. It is the compliance score, which is a quantitative indicator calculated by the system through an intelligent monitoring algorithm. It is used to evaluate the compliance level of the weighbridge operation. The score is used to represent the value or height of a data point in the chart so that users can intuitively understand the compliance status at each point in time. A detailed monitoring report will be generated to notify users of the compliance status of the weighbridge via SMS or email to ensure that users can understand the compliance status of the weighbridge in a timely manner. Based on the monitoring results, corresponding processing suggestions or solutions will be provided to users to help them better manage the weighbridge.

9. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The system also includes a user management function that allows users to set and adjust monitoring rules, view historical records, and perform other related operations.

10. The method and system for monitoring compliance of a weighbridge based on monitoring rules according to claim 1, characterized in that: The specific steps of the method are: (1) System startup and preparation: Start the weighbridge compliance monitoring system, ensure that the data collection module, data preprocessing module, intelligent monitoring algorithm module and result output module are in normal working condition, and configure system parameters, including data collection frequency, data preprocessing rules, and intelligent monitoring algorithm parameter settings, to adapt to specific business needs and operating environment; (2) Data collection: The data collection module starts to collect weighing data from the scale in real time, including vehicle weight, timestamp, and operator information. The system stores the collected data in a database for subsequent processing and analysis. (3) Data preprocessing: The data preprocessing module cleans, filters and formats the collected raw data to eliminate noise, missing values ​​and outliers and improve data quality. The preprocessed data will be transmitted to the intelligent monitoring algorithm module for further analysis and processing; (4) Operation of intelligent monitoring algorithm: The intelligent monitoring algorithm module uses advanced machine learning or deep learning algorithms to learn and analyze pre-processed data, automatically identify and extract compliance patterns of the scales, and automatically adjust the monitoring rules based on historical data and real-time data to adapt to changing business needs and operating environments. The calculated compliance score or other relevant indicators are passed as output results to the result output module; (5) Result output and feedback: The result output module outputs the compliance status of the weighbridge based on the analysis results of the intelligent monitoring algorithm module. If the weighbridge operation is compliant, the system will display it normally; if an abnormality or violation is found, the system will immediately generate an alarm, and the system will send the alarm information to relevant personnel via SMS, email, or system notification so that timely measures can be taken to intervene or adjust; (6) Monitoring and maintenance: Regularly monitor and inspect the system to ensure that the data collection, preprocessing, algorithm operation and result output modules are in normal working condition. Adjust system parameters and algorithm settings in a timely manner according to business needs and environmental changes to maintain the optimal performance of the system. At the same time, regularly maintain and upgrade the system to fix potential problems, add new functions and improve system performance; (7) Data analysis and reporting: The system can generate detailed data analysis reports, including the compliance of weighbridge operations, statistics and analysis of abnormal or illegal behaviors. The reports can be customized as needed to meet the needs of different users and management.

Images