A highway weighing platform network operation monitoring system

Abstract

The present invention discloses a networked operation monitoring system for a highway weighing platform, which belongs to the technical field of highway weighing platform monitoring and comprises: a data acquisition module, used for acquiring real-time monitoring data, accessory data and historical record data of all key accessories of the highway weighing platform; wherein the real-time monitoring data comprises: abnormal state and normal state; the accessory data comprises: accessory number data, accessory location and accessory type; a display module, used for associating the real-time monitoring data, historical record data and key accessory data to form an associated data group and to display it in a polling manner; an abnormal alarm module, used for generating alarm information according to the real-time monitoring data and sending it to an administrator; and an accessory pre-allocation module, used for generating an accessory pre-storage plan within a preset period according to the historical record data and key accessory data.

Description

Technical Field

[0001] The invention belongs to the technical field of highway weighing platform monitoring, and in particular relates to a highway weighing platform networked operation monitoring system. Background Art

[0002] High-speed weighing platforms are a core component of the highway toll collection system and a key data source. They are primarily composed of three key components: data collection, data processing, and data publishing. Data collection primarily involves separating individual vehicles through a vehicle separator, identifying vehicle types through axle (tire) identifiers, acquiring vehicle weight data through weighing sensors, and transmitting this sensor data in real time via wired transmission to a weighing meter. The weighing meter calculates vehicle weight based on the integrated sensor data using specific calculation rules. The toll collection system then calculates tolls, and finally displays the weighing data on the toll display and other related systems.

[0003] During actual operation, we often encounter various abnormal failures. The main manifestation is that the toll collection system has no weight or abnormal weight, which prevents the toll collection work from being completed in time, causing traffic congestion at the entrance and exit. Common problems include sensor failure, vehicle separator failure, axle identification failure, weighing instrument failure, etc. These failures require professional technicians and parts to repair, and the processing time generally takes several hours. However, if the service station does not have all the parts, the delay will be longer. At the same time, due to the professional nature of the problem, the service unit may replace all the usable parts at the same time, resulting in increased maintenance costs. Summary of the Invention

[0004] In view of this, the present invention provides a highway scale platform network operation monitoring system for solving the problem that when a highway scale fails, professional technicians are required to repair it, which increases maintenance costs.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The present invention provides a highway weighing platform network operation monitoring system, comprising:

[0007] The data acquisition module is used to obtain real-time monitoring data, accessory data, and historical record data of all key accessories of the highway scale platform; the real-time monitoring data includes: abnormal status and normal status; the accessory data includes: accessory number data, accessory location, and accessory type;

[0008] Display module, used to associate real-time monitoring data, historical record data and key accessories data to form associated data groups and poll and display them;

[0009] Abnormal alarm module, used to generate alarm information based on real-time monitoring data and send it to the administrator;

[0010] The accessories pre-allocation module is used to generate an accessories pre-storage plan within a preset period based on historical record data and key accessories data.

[0011] As an embodiment of the present invention, the display module performs the following operations:

[0012] Select any key accessory as the target key component;

[0013] Determine the associated data group of key components based on the component data, historical record data and real-time monitoring data of the target key component; wherein the historical record data includes: component maintenance data, component replacement data and component abnormality data;

[0014] Repeat the above steps until the associated data groups of all key accessories are obtained;

[0015] Periodically obtain real-time monitoring data to update the associated data group to obtain the target associated data group;

[0016] Grouping all target associated data groups to obtain multiple data display packages; wherein one data display package includes all associated data groups on the same highway weighing platform;

[0017] Based on the preset polling method, multiple data display packages are displayed.

[0018] As an embodiment of the present invention, the abnormal alarm module performs the following operations:

[0019] Determine whether there are any abnormalities in key components based on real-time monitoring data; if the real-time monitoring data is abnormal, the key component is determined to be abnormal and an alert is issued to the administrator;

[0020] If the real-time monitoring data is normal, obtain the assembly time of all key accessories;

[0021] Determine whether the key component is in the critical period based on the assembly time; if not, periodically obtain the assembly time for judgment; if so, treat the key component as a critical key component;

[0022] The usage data of critical key components is input into the pre-trained critical state judgment model to obtain the critical state of the critical key components. The usage data includes: component type, assembly time, number of times the scale platform is used, and average temperature and humidity during assembly. The critical state includes: severe performance degradation and continued use.

[0023] Determine whether the critical state indicates a serious performance degradation; if so, issue a reminder to the administrator; if not, periodically obtain the critical state for judgment.

[0024] As an embodiment of the present invention, the accessory provisioning module performs the following operations:

[0025] Get the highway weighing platform in any area as the target weighing platform;

[0026] Determine the preset parts update time period of the target scale platform according to the preset parts update time span;

[0027] When the highway weighing platform completes the use of a pre-parts update time period and needs to update the pre-parts, the next pre-parts update time period is used as the target update time period;

[0028] Obtaining accessory replacement data for multiple pre-accessory update time periods before the target update time period; wherein the accessory replacement data is the number of replacements for each type of key accessory;

[0029] Generate spare parts pre-storage plan based on spare parts replacement data.

[0030] As an embodiment of the present invention, generating a spare parts pre-storage plan based on spare parts replacement data includes:

[0031] Select any key component as the target key component, and determine the abnormal time period based on the number of replacements of the target key component; wherein the pre-component update time period with a replacement number greater than the preset replacement number is the abnormal time period;

[0032] The abnormal coefficient is calculated based on the number of abnormal time periods. The calculation formula is as follows:

[0033] , where is the abnormal coefficient, Update the number of time slots for the pre-installed components to be obtained. is the number of abnormal time periods, is a linear normalization function;

[0034] The number of pre-assembled parts for the target key parts during the target update period is calculated based on the abnormal coefficient. The calculation formula is as follows:

[0035] , where The provisioned quantity of the target key components for the target update time period, The number of replacements of the target key parts in the previous pre-parts update period of the target update period. The mean number of replacement times for the obtained pre-installed parts during the update period;

[0036] Repeat the above steps to calculate the pre-provision quantity of all key accessories of the target foundation and determine the pre-storage plan.

[0037] As an embodiment of the present invention, it further includes: a monitoring strategy adjustment module for adjusting the uploading scheme of the real-time monitoring data of all highway weighing platforms;

[0038] Specifically:

[0039] Obtain the current status parameters of each highway scale in the monitoring system; wherein the current status parameters include the operating status and network environment of the highway scale; status parameters include: network latency, bandwidth, real-time monitoring data packaging efficiency, monitoring system processing efficiency and scale failure rate;

[0040] Randomly select any highway weighing platform as the target weighing platform and determine the target state parameters of the target weighing platform;

[0041] Input each target state parameter into the pre-trained upload plan dynamic adjustment model to obtain the upload plan for the real-time monitoring data of the target scale;

[0042] Repeat the above steps to determine the upload plan for the real-time monitoring data of all highway weighing platforms.

[0043] As an embodiment of the present invention, a training method for dynamically adjusting a model for uploading a scheme includes:

[0044] Building an upload plan dynamic adjustment model based on a deep Q network, and configuring an upload plan adjustment set of the upload plan dynamic adjustment model; wherein the upload plan adjustment set includes multiple upload plans;

[0045] Obtain sample state parameters of sample highway scales to train a dynamic adjustment model for upload schemes, so that the monitoring strategy adjustment module learns the relationship between the state parameters of different highway scales and different adjustment schemes, and obtains a trained dynamic adjustment model for upload schemes;

[0046] Among them, the dynamic adjustment model of the uploaded plan is configured with a loss function and a reward function; the reward function is used to calculate the instant reward that the environment feeds back to the monitoring strategy adjustment module after selecting the uploaded plan based on the sample state parameters of the sample highway scale platform; the loss function is determined based on the feedback state and instant reward fed back to the monitoring strategy adjustment module by the environment.

[0047] The beneficial effects of the present invention are: by real-time monitoring of any key accessory of any highway scale platform, when any key accessory has an abnormality, the monitoring system can give a reminder and provide the administrator with the accessory data of the key accessory with the abnormality, so that the administrator can quickly notify the corresponding maintenance personnel to accurately replace the abnormal key accessory, solving the problem that when a highway scale platform fails, professional technicians are needed to repair it, which increases maintenance costs, and assists the administrator to prepare for replacement of accessories; at the same time, the accessories that may need to be replaced in a subsequent period of time on any highway scale platform are accurately pre-equipped through the provided accessories pre-equipped module, avoiding the problem of long maintenance time caused by incomplete accessories at the service station, and at the same time, avoiding the problem of increased accessories storage and maintenance costs, accessories damaged due to being left for too long, and increased operating costs due to pre-equipping too many accessories for a service station.

[0048] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or those skilled in the art can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to make the purpose, technical solutions and beneficial effects of the present invention more clear, the present invention provides the following drawings for illustration:

[0050] Figure 1 It is a schematic diagram of a module of the present invention;

[0051] Figure 2 Schematic diagram of the process of the abnormal alarm module of the present invention;

[0052] Figure 3 A schematic diagram of the process flow of the accessory pre-configuration module of the present invention. DETAILED DESCRIPTION

[0053] like Figures 1-3 As shown, the present invention provides a highway weighing platform network operation monitoring system, comprising:

[0054] The data acquisition module is used to obtain real-time monitoring data, accessory data, and historical record data of all key accessories of the highway scale platform; the real-time monitoring data includes: abnormal status and normal status; the accessory data includes: accessory number data, accessory location, and accessory type;

[0055] Display module, used to associate real-time monitoring data, historical record data and key accessories data to form associated data groups and poll and display them;

[0056] Abnormal alarm module, used to generate alarm information based on real-time monitoring data and send it to the administrator;

[0057] The accessories pre-allocation module is used to generate an accessories pre-storage plan within a preset period based on historical record data and key accessories data.

[0058] The working principle of the above technical solution: during the use of the highway weighing platform, all key accessories of the highway weighing platform are monitored through the data acquisition module to obtain real-time monitoring data; wherein, the key accessories include: steel structures at key positions of the weighing platform, load-bearing instruments, axle identification devices, vehicle separators and various sensors, etc., wherein, the real-time monitoring data of electronic components such as sensors are directly read through their own chips, and the steel structures at key positions of the weighing platform are imaged by CCD cameras installed at corresponding positions, and compared with the corresponding standard images for similarity (the image similarity comparison here belongs to conventional technical means and will not be elaborated on here). When the similarity is greater than the preset value, it indicates that the real-time monitoring status of the steel structure at the key position of the weighing platform is normal; the historical record data is the number of times the components in use are used, the replacement time, etc.; through the data acquisition module After obtaining the real-time monitoring data, accessory data and historical record data of key accessories, these data are associated and displayed in a polling manner on the corresponding human-computer interaction interface (display module), so that the administrator can monitor the weighing platforms of various local highways in real time. At the same time, the monitoring system will also monitor various key accessories based on the real-time monitoring data obtained. When any key accessory is in an abnormal state, the abnormal alarm module will generate an alarm message and send the corresponding accessory data to the administrator. At the same time, in order to avoid the service unit not having the corresponding key accessories to replace when any key component is abnormal, resulting in longer maintenance time, and to avoid the problem of the service unit storing a key accessory for too long, the accessory pre-allocation module is used to predict the reserved key accessories that may be needed before the next accessory replenishment time, and determine the number of reserved accessories for each service unit.

[0059] The beneficial effects of the above technical solution: Through the above technical solution, by real-time monitoring of any key accessory of any highway scale platform, when any key accessory has an abnormality, the monitoring system can give a reminder and provide the administrator with the accessory data of the key accessory with the abnormality, so that the administrator can quickly notify the corresponding maintenance personnel to accurately replace the abnormal key accessory, solving the problem that when a highway scale platform fails, professional technicians are needed to repair it, which increases maintenance costs, and assists the administrator to prepare for replacement of accessories; at the same time, the accessories pre-configuration module is used to accurately pre-configure the accessories that may need to be replaced in a subsequent period of time for any highway scale platform, avoiding the problem of long maintenance time caused by incomplete accessories at the service station, and at the same time, avoiding the problem of increased accessories storage and maintenance costs, accessories damaged for too long, and increased operating costs caused by pre-configuration of too many accessories for a service station.

[0060] In one embodiment, the display module performs the following operations:

[0061] Select any key accessory as the target key component;

[0062] Determine the associated data group of key components based on the component data, historical record data and real-time monitoring data of the target key component; wherein the historical record data includes: component maintenance data, component replacement data and component abnormality data;

[0063] Repeat the above steps until the associated data groups of all key accessories are obtained;

[0064] Periodically obtain real-time monitoring data to update the associated data group to obtain the target associated data group;

[0065] Grouping all target associated data groups to obtain multiple data display packages; wherein one data display package includes all associated data groups on the same highway weighing platform;

[0066] Based on the preset polling method, multiple data display packages are displayed.

[0067] The working principle of the above technical solution is: in the process of monitoring the highway weighing platform, in order to facilitate the administrator to monitor any key accessories of the weighing platform; select any key accessory as the target key component; filter out the accessory data, historical record data and real-time monitoring data corresponding to the target key component from all accessory data, historical record data and real-time monitoring data to obtain a data association group; then, filter and determine the associated data groups of all key accessories; then, take a highway weighing platform as a unit, combine and package all the associated data groups of a highway weighing platform to obtain a data display package; then display the data of a data display package on the interactive interface to facilitate the administrator to monitor the highway weighing platform. The highway weighing platforms are monitored; at the same time, the data display packages of the highway weighing platforms in different places are displayed on the interactive interface through a preset polling method; wherein the preset polling method is to classify the highway weighing platforms according to the number of abnormalities of the key accessories of the highway weighing platforms, and then extract a corresponding number of display data packets for each class according to a preset ratio to form a display set, and then randomly display the display data packets in the display set; at the same time, in the process of displaying the display data of the highway weighing platforms, the monitoring system will also periodically obtain real-time monitoring data, and then update the real-time status data of the associated data groups in the display data packets to ensure the accuracy of the display data packets.

[0068] Beneficial effects of the above technical solution: Through the above technical solution, by packaging all data of any highway scale platform, it is convenient for administrators to monitor all data of any highway scale platform at one time, thereby improving monitoring efficiency.

[0069] In one embodiment, the abnormality alarm module performs the following operations:

[0070] Determine whether there are any abnormalities in key components based on real-time monitoring data; if the real-time monitoring data is abnormal, the key component is determined to be abnormal and an alert is issued to the administrator;

[0071] If the real-time monitoring data is normal, obtain the assembly time of all key accessories;

[0072] Determine whether the key component is in the critical period based on the assembly time; if not, periodically obtain the assembly time for judgment; if so, treat the key component as a critical key component;

[0073] The usage data of critical key components is input into the pre-trained critical state judgment model to obtain the critical state of the critical key components. The usage data includes: component type, assembly time, number of times the scale platform is used, and average temperature and humidity during assembly. The critical state includes: severe performance degradation and continued use.

[0074] Determine whether the critical state indicates a serious performance degradation; if so, issue a reminder to the administrator; if not, periodically obtain the critical state for judgment.

[0075] The working principle of the above technical solution is: when monitoring any key accessory of the highway weighing platform, judgment is made through the real-time monitoring data of the key accessory. When the real-time monitoring data is in an abnormal state, it is determined that the key accessory is abnormal, a reminder is sent to the administrator, and the accessory data of the key accessory is sent at the same time to facilitate the administrator to replace it; at the same time, when the real-time monitoring data is normal, the assembly time of all key accessories is obtained, and it is determined whether the key accessory is in the critical period based on the assembly time; that is, when the assembly time of the key accessory is greater than the preset assembly time, it is determined that the key accessory is in the critical period, and the key accessory is used as a critical key accessory; when the assembly time of the key accessory is not greater than the preset assembly time, it is determined that the key accessory is not in the critical period. During a critical period, when a critical key component exists, the usage data of the critical key component is obtained and input into a pre-trained critical state judgment model to obtain the critical state of the critical key component. The usage data includes: component category (sensor, steel structure at key positions of the scale), assembly time, number of scale usages (number of weighing times after the critical component is assembled), and average temperature and humidity during assembly. Critical states include: severe performance degradation and continued use. The training method of the critical state judgment model includes: obtaining usage data of several key components, labeling the corresponding usage data by experts, and then training the usage data and the corresponding labels together in a data-based neural network model until convergence to obtain a critical state judgment model.

[0076] The beneficial effects of the above technical solution are as follows: Through the above technical solution, by real-time monitoring of the status of key accessories, abnormal situations can be discovered in time and administrators can be reminded so that faulty accessories can be quickly replaced; it can avoid sudden failure or inaccurate measurement of the scale platform due to accessory failure during use, ensure the continuous and stable operation of the scale platform, and improve the accuracy of highway toll collection, overload detection and other tasks; at the same time, it can determine whether the key accessories are in a critical period and further determine their critical state, which helps administrators to reasonably plan the replacement plan of accessories, avoid unnecessary replacement when the performance of accessories has not yet declined significantly, and reduce resource waste; at the same time, for accessories with severe performance degradation, replacement can be arranged in advance to avoid emergency situations caused by accessory failure and affect traffic operations and measurement accuracy; collect usage data of key accessories and use them to train critical state judgment models; this not only provides a scientific basis for judging critical states, but also provides valuable data support for subsequent equipment optimization and maintenance strategy adjustments.

[0077] In one embodiment, the accessory provisioning module performs the following operations:

[0078] Get the highway weighing platform in any area as the target weighing platform;

[0079] Determine the preset parts update time period of the target scale platform according to the preset parts update time span;

[0080] When the highway weighing platform completes the use of a pre-parts update time period and needs to update the pre-parts, the next pre-parts update time period is used as the target update time period;

[0081] Obtaining accessory replacement data for multiple pre-accessory update time periods before the target update time period; wherein the accessory replacement data is the number of replacements for each type of key accessory;

[0082] Generate spare parts pre-storage plan based on spare parts replacement data;

[0083] The above technical solution works as follows: First, the module identifies highway scales within a specific area as target scales and determines a pre-parts update period for these target scales based on a preset parts update time span. When a pre-parts update period ends, the system automatically sets the next period as the target update period, ensuring continuity and planning of maintenance work. To generate an accurate parts pre-stocking plan, the system retrospectively analyzes parts replacement data from multiple time periods prior to the target update period. This data details the replacement frequency of each key part type, providing a historical basis for predicting future replacement needs. Based on this replacement data, the system generates a parts pre-stocking plan. This plan not only takes into account past replacement practices but also incorporates the specific needs of the target update period to predict the types and quantities of parts likely to need replacement during the next maintenance cycle. This proactive approach allows the system to pre-stock necessary key parts, avoiding maintenance delays caused by parts shortages and reducing the costs and resource waste associated with over-stocking.

[0084] The beneficial effects of the above technical solution: Through the above technical solution, the solution helps to reduce operating costs. By accurately predicting the demand for parts replacement, it avoids unnecessary parts inventory backlogs, reduces capital occupation and storage costs; in addition, the solution also enhances the reliability and stability of the system; by ensuring the timely replacement of key parts, it reduces the risk of equipment failure, extends the service life of the equipment, and improves the reliability and stability of the entire highway weighing platform system; finally, this predictive maintenance strategy helps to improve the overall service quality.

[0085] In one embodiment, generating a spare parts pre-storage plan based on spare parts replacement data includes:

[0086] Select any key component as the target key component, and determine the abnormal time period based on the number of replacements of the target key component; wherein the pre-component update time period with a replacement number greater than the preset replacement number is the abnormal time period;

[0087] The abnormal coefficient is calculated based on the number of abnormal time periods. The calculation formula is as follows:

[0088] , where is the abnormal coefficient, Update the number of time slots for the pre-installed components to be obtained. is the number of abnormal time periods, is a linear normalization function;

[0089] The number of pre-assembled parts for the target key parts during the target update period is calculated based on the abnormal coefficient. The calculation formula is as follows:

[0090] , where The provisioned quantity of the target key components for the target update time period, The number of replacements of the target key parts in the previous pre-parts update period of the target update period. The mean number of replacement times for the obtained pre-installed parts during the update period;

[0091] Repeat the above steps to calculate the pre-provision quantity of all key accessories of the target foundation and determine the pre-storage plan.

[0092] The working principle of the above technical solution is as follows: the system analyzes the replacement data of each key accessory and identifies abnormal time periods in which the number of replacements exceeds the preset number of replacements; specifically, the system selects any key accessory as the target key accessory and counts the number of replacements within each pre-accessory update time period; when the number of replacements within a certain time period exceeds the preset number of replacements, the time period is marked as an abnormal time period. Based on the number of abnormal time periods and the total number of all pre-accessory update time periods, the system calculates an abnormal coefficient. This coefficient reflects the relationship between the replacement frequency of key accessories within the abnormal time period and the overall replacement frequency, thereby quantifying the degree of abnormal replacement of accessories. Furthermore, the system uses the abnormal coefficient to predict the number of pre-accessories for the target key accessory in the upcoming target update time period. The prediction formula comprehensively considers the number of replacements in the previous time period and the average number of replacements in all time periods to derive a reasonable pre-allocation quantity. The system repeats this process for all key accessories and ultimately determines a comprehensive accessories pre-storage plan to ensure the timely supply of key accessories and effectively avoid over-stocking or out-of-stock situations.

[0093] The beneficial effects of this technical solution include: By precisely identifying abnormal time periods and calculating abnormal coefficients, the system can more accurately predict the replacement needs of key parts, improving the accuracy of parts pre-stocking solutions. Furthermore, this solution significantly reduces maintenance costs. By rationally predicting parts demand, unnecessary inventory backlogs are avoided, reducing capital and storage costs.

[0094] In one embodiment, the invention further comprises: a monitoring strategy adjustment module for adjusting the uploading scheme of the real-time monitoring data of all highway weighing platforms;

[0095] Specifically:

[0096] Obtain the current status parameters of each highway scale in the monitoring system; wherein the current status parameters include the operating status and network environment of the highway scale; status parameters include: network latency, bandwidth, real-time monitoring data packaging efficiency, monitoring system processing efficiency and scale failure rate;

[0097] Randomly select any highway weighing platform as the target weighing platform and determine the target state parameters of the target weighing platform;

[0098] Input each target state parameter into the pre-trained upload plan dynamic adjustment model to obtain the upload plan for the real-time monitoring data of the target scale;

[0099] Repeat the above steps to determine the upload plan for real-time monitoring data of all highway weighing platforms;

[0100] Upload a solution to dynamically adjust the model training method including:

[0101] Building an upload plan dynamic adjustment model based on a deep Q network, and configuring an upload plan adjustment set of the upload plan dynamic adjustment model; wherein the upload plan adjustment set includes multiple upload plans;

[0102] Obtain sample state parameters of sample highway scales to train a dynamic adjustment model for upload schemes, so that the monitoring strategy adjustment module learns the relationship between the state parameters of different highway scales and different adjustment schemes, and obtains a trained dynamic adjustment model for upload schemes;

[0103] Among them, the dynamic adjustment model of the uploaded plan is configured with a loss function and a reward function; the reward function is used to calculate the instant reward that the environment feeds back to the monitoring strategy adjustment module after selecting the uploaded plan based on the sample state parameters of the sample highway scale platform; the loss function is determined based on the feedback state and instant reward fed back to the monitoring strategy adjustment module by the environment.

[0104] The working principle of the above technical solution is as follows: During real-time monitoring of multiple highway scales, data from these scales is transmitted to a centralized control center for processing and storage to facilitate centralized monitoring and data storage by administrators. However, the centralized control center has limited data reception and processing capabilities. To prevent data uploaded by highway scales from being lost and to ensure timely processing, this technical solution uses a monitoring strategy adjustment module to dynamically optimize the upload plan for real-time monitoring data for all highway scales. The system first collects the current state parameters of each scale, including network latency, bandwidth, data packaging efficiency, system processing efficiency, and failure rate. It then randomly selects a scale as the target and inputs the relevant state parameters into a dynamic upload plan adjustment model based on deep reinforcement learning to generate the most optimal upload plan. By learning the relationship between different scale state parameters and upload plans, the model intelligently adjusts the upload frequency, data volume, or upload time to ensure efficient data transmission and timely processing. The system repeats this process to generate a personalized upload plan for each scale. This adaptive adjustment mechanism ensures efficient data transmission under varying network conditions, reduces bandwidth resources and server load, and improves monitoring reliability and data integrity. In addition, the module can quickly adapt to newly added scales and changing monitoring requirements, improving the system's scalability and management efficiency. By optimizing data packaging and upload efficiency, the system can more quickly process and analyze monitoring data, promptly identify and respond to potential issues, and thus improve the effectiveness and responsiveness of the entire monitoring system. The upload solution adjustment set includes different adjustment options for data compression level, upload frequency, and upload interval. For example, when a highway scale has a low failure rate, the model will match it with an upload solution that has a high compression rate and a low number of uploads.

[0105] Furthermore, in the networked operation monitoring system for highway weighing platforms, training a model for dynamically adjusting upload plans is crucial for ensuring efficient transmission and processing of monitoring data. This model is based on the Deep Q-Network (DQN), a reinforcement learning algorithm that excels at optimizing decision-making strategies through trial-and-error learning in complex environments. During model training, a set of adjustments is first defined, encompassing various upload plans. These plans cover various parameter combinations, such as upload frequency, data size, and upload interval, to adapt to diverse network environments and monitoring requirements.

[0106] The training data is derived from the historical state parameters of sample highway weighing platforms, including key indicators such as network latency, bandwidth, data packaging efficiency, system processing efficiency, and failure rate. By inputting these sample state parameters into the DQN model, the model learns the optimal upload solution under different combinations of state parameters. This learning process is achieved through interaction with the environment. The model selects an upload solution based on the current state parameters and executes it, then receives an immediate reward signal from the environment. The reward function is designed to provide positive rewards when the upload solution can effectively utilize current network resources and reduce data loss and latency, and penalties when it fails. The loss function is used to measure the difference between the Q value predicted by the model (i.e., expected reward) and the actual reward obtained. The model parameters are continuously adjusted through the backpropagation algorithm, enabling the model to more accurately predict the optimal upload solution under different conditions.

[0107] As training progresses, the model gradually learns the mapping between the state parameters of different highway scale platforms and the optimal upload plan. Training is considered complete when the model reaches convergence, indicating that it has the ability to dynamically generate the optimal upload plan based on real-time state parameters. In practice, the monitoring strategy adjustment module collects the state parameters of each scale platform in real time and inputs them into the trained model. The model quickly outputs the corresponding upload plan to guide the scale platform in uploading data.

[0108] The beneficial effects of the above technical solution are: the system can dynamically adjust the data upload plan according to the real-time network environment and the operating status of the scale; automatically reduce the upload frequency or compress the data volume during network congestion, and increase the upload frequency or improve the data resolution during network idle periods, thereby ensuring the efficiency and stability of data transmission; through intelligent upload strategies, the system can prioritize the upload of key data when the network is unstable or fails, reduce the risk of data loss, and improve the integrity and availability of monitoring data; the optimized data upload mechanism reduces unnecessary data traffic and server load, thereby saving bandwidth resources and cloud computing resources, and reducing overall operating costs; as the network environment and monitoring needs change, the model can continue to learn and adapt, providing the optimal upload plan for new scales or changing monitoring conditions, ensuring the long-term and effective operation of the system.

[0109] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. A highway weighing platform network operation monitoring system, characterized in that: include: The data acquisition module is used to obtain real-time monitoring data, accessory data, and historical record data of all key accessories of the highway scale platform; the real-time monitoring data includes: abnormal status and normal status; the accessory data includes: accessory number data, accessory location, and accessory type; Display module, used to associate real-time monitoring data, historical record data and key accessories data to form associated data groups and poll and display them; Abnormal alarm module, used to generate alarm information based on real-time monitoring data and send it to the administrator; The spare parts pre-allocation module is used to generate spare parts pre-storage plans within a preset period based on historical record data and key spare parts data; The accessory provisioning module performs the following operations: Get the highway weighing platform in any area as the target weighing platform; Determine the preset parts update time period of the target scale platform according to the preset parts update time span; When the highway weighing platform completes the use of a pre-parts update time period and needs to update the pre-parts, the next pre-parts update time period is used as the target update time period; Obtaining accessory replacement data for multiple pre-accessory update time periods before the target update time period; wherein the accessory replacement data is the number of replacements for each type of key accessory; Generate spare parts pre-storage plan based on spare parts replacement data.

2. A highway weighing platform network operation monitoring system according to claim 1, characterized in that: Display module, performs the following operations: Select any key accessory as the target key component; Determine the associated data group of key components based on the component data, historical record data and real-time monitoring data of the target key component; wherein the historical record data includes: component maintenance data, component replacement data and component abnormality data; Repeat the above steps until the associated data groups of all key accessories are obtained; Periodically obtain real-time monitoring data to update the associated data group to obtain the target associated data group; Grouping all target associated data groups to obtain multiple data display packages; wherein one data display package includes all associated data groups on the same highway weighing platform; Based on the preset polling method, multiple data display packages are displayed.

3. A highway weighing platform network operation monitoring system according to claim 1, characterized in that: The abnormal alarm module performs the following operations: Determine whether there are any abnormalities in key components based on real-time monitoring data; if the real-time monitoring data is abnormal, the key component is determined to be abnormal and an alert is issued to the administrator; If the real-time monitoring data is normal, obtain the assembly time of all key accessories; Determine whether key components are in a critical period based on assembly time; if not, periodically obtain assembly time for determination; If in, treat the key component as a critical key component; The usage data of critical key components is obtained and input into the pre-trained critical state judgment model to obtain the critical state of the critical key components. The usage data includes: component type, assembly time, number of times the scale platform is used, and average temperature and humidity during assembly. The critical state includes: severe performance degradation and continued use. Determine whether the critical state indicates a serious performance degradation; if so, issue a reminder to the administrator; if not, periodically obtain the critical state for judgment.

4. A highway weighing platform network operation monitoring system according to claim 1, characterized in that: Generate spare parts pre-storage plan based on spare parts replacement data, including: Select any key component as the target key component, and determine the abnormal time period based on the number of replacements of the target key component; wherein the pre-component update time period with a replacement number greater than the preset replacement number is the abnormal time period; Calculate the abnormal coefficient based on the number of abnormal time periods; Calculate the number of pre-assembled parts for the target key parts during the target update period based on the abnormal coefficient; Repeat the above steps to calculate the pre-provision quantity of all key accessories of the target foundation and determine the pre-storage plan.

5. The highway weighing platform network operation monitoring system according to claim 1, characterized in that: It also includes: a monitoring strategy adjustment module for adjusting the upload scheme of real-time monitoring data of all highway weighing platforms; Specifically: Obtain the current status parameters of each highway scale in the monitoring system; wherein the current status parameters include the operating status and network environment of the highway scale; status parameters include: network latency, bandwidth, real-time monitoring data packaging efficiency, monitoring system processing efficiency and scale failure rate; Randomly select any highway weighing platform as the target weighing platform and determine the target state parameters of the target weighing platform; Input each target state parameter into the pre-trained upload plan dynamic adjustment model to obtain the upload plan for the real-time monitoring data of the target scale; Repeat the above steps to determine the upload plan for the real-time monitoring data of all highway weighing platforms.

6. A highway weighing platform network operation monitoring system according to claim 5, characterized in that: Upload a solution to dynamically adjust the model training method including: Building an upload plan dynamic adjustment model based on a deep Q network, and configuring an upload plan adjustment set of the upload plan dynamic adjustment model; wherein the upload plan adjustment set includes multiple upload plans; Obtain sample state parameters of sample highway scales to train a dynamic adjustment model for upload schemes, so that the monitoring strategy adjustment module learns the relationship between the state parameters of different highway scales and different adjustment schemes, and obtains a trained dynamic adjustment model for upload schemes; Among them, the dynamic adjustment model of the uploaded plan is configured with a loss function and a reward function; the reward function is used to calculate the instant reward that the environment feeds back to the monitoring strategy adjustment module after selecting the uploaded plan based on the sample state parameters of the sample highway scale platform; the loss function is determined based on the feedback state and instant reward fed back to the monitoring strategy adjustment module by the environment.

Images