Intelligent detection and early warning method for traffic overload control system

Abstract

The present application provides an intelligent detection and early warning method for a traffic overload control system, which relates to the field of intelligent early warning technology, including: by deploying a sensor group in a pre-test area and collecting vehicle data; configuring the test frequency of the load sensor through the vehicle speed data in the vehicle data set; establishing a load data set using the configured load sensor; obtaining speed measurement data in the test area; inputting the speed measurement data and the load data set into the load compensation model; establishing a first early warning with the vehicle information call result and the load measurement result, performing linkage analysis based on the image recognition result and the load measurement result, establishing a second early warning, and performing intelligent detection abnormality reporting. The present application can solve the technical problem that overloading behavior cannot be identified in a timely manner in the prior art, achieve the technical goal of dynamic monitoring of vehicle load status, and achieve the technical effect of improving road traffic management efficiency and reducing the impact of overloading behavior on road infrastructure.

Description

Technical Field

[0001] The present application relates to the field of intelligent early warning technology, and in particular to an intelligent detection and early warning method for a traffic overload control system. Background Art

[0002] In the field of modern traffic management, vehicle load detection is an important means to ensure road safety, protect road facilities and regulate transportation behavior. However, with the rapid development of the logistics and transportation industry, the problem of overloaded vehicles remains serious, posing a huge threat to road infrastructure and traffic safety.

[0003] At present, traditional vehicle load detection mainly relies on fixed weighbridge inspection stations. Although it can screen overloaded vehicles to a certain extent, it has obvious limitations. First, weighbridge inspection stations require vehicles to slow down or even stop for detection, and the detection efficiency is low, which is not suitable for high-traffic road environments. Secondly, due to the limited number of inspection stations and insufficient coverage, it is difficult to timely detect overload behaviors scattered in a vast road network. Thirdly, the fixed detection method lacks effective monitoring of the dynamic changes in the vehicle loading status and cannot identify potential abnormal loading conditions in real time. In addition, traditional detection systems also have deficiencies in data collection and analysis. For example, the load measurement results are single, and other information about the vehicle (such as vehicle model, historical load data, loading distribution, etc.) cannot be combined for comprehensive analysis, resulting in low accuracy and credibility of the detection results. Summary of the invention

[0004] The purpose of this application is to provide an intelligent detection and early warning method for a traffic overload control system, so as to solve the technical problems in the prior art that overloading behavior cannot be identified in a timely, comprehensive and accurate manner due to the low detection efficiency, limited coverage and lack of effective monitoring of the dynamic changes in the vehicle loading status of fixed weighbridge inspection stations, further affecting the efficiency and safety of road traffic management.

[0005] In view of the above problems, the present application provides an intelligent detection and early warning method for a traffic overload control system, including: establishing a vehicle data set by deploying a sensor group in a pre-test area and collecting vehicle data; activating a load sensor in the test area, and configuring the test frequency of the load sensor through the vehicle speed data in the vehicle data set; establishing a load data set using the configured load sensor, the load data set having a time stamp; acquiring speed measurement data in the test area based on the time stamp, the speed measurement data including real-time speed data and acceleration data; inputting the speed measurement data and the load data set into a load compensation model to establish a load measurement result; calling vehicle information according to license plate data, establishing a first early warning with the vehicle information call result and the load measurement result, performing image recognition on the vehicle loading image, performing linkage analysis based on the image recognition result and the load measurement result, establishing a second early warning, and performing intelligent detection abnormality reporting according to the first early warning and the second early warning.

[0006] The technical solution provided in this application has the following technical effects: by achieving the technical goal of dynamic, real-time and efficient monitoring and abnormal identification of vehicle load status, the technical effect of comprehensively improving road traffic management efficiency and reducing the impact of overloading on road infrastructure and traffic safety is achieved.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1 A flow chart of the intelligent detection and early warning method for the traffic overload control system for this application; Figure 2 A flow chart of establishing load measurement results in the intelligent detection and early warning method of the traffic overload control system in this application. DETAILED DESCRIPTION

[0010] This application provides an intelligent detection and early warning method for a traffic overload control system, which solves the technical problem in the prior art that due to the low detection efficiency, limited coverage and lack of effective monitoring of the dynamic changes in the vehicle loading status of fixed weighbridge detection stations, overloading behavior cannot be identified in a timely, comprehensive and accurate manner, further affecting the efficiency and safety of road traffic management. The technical goal of dynamic, real-time and efficient monitoring and abnormal identification of vehicle loading status is achieved, achieving the technical effect of comprehensively improving the efficiency of road traffic management and reducing the impact of overloading on road infrastructure and traffic safety.

[0011] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0012] Please see attached Figure 1 The present application provides an intelligent detection and early warning method for a traffic overload control system, which specifically includes: Step 1: deploying a sensor group in a pre-test area and collecting vehicle data to establish a vehicle data set.

[0013] Specifically, the pre-test area refers to an area that is pre-demarcated and equipped with sensor equipment before traffic control, so that all monitored information is more accurate. The sensor group is a device composed of multiple sensors, which is used to collect various data related to the vehicle, such as speed, license plate number, loading status, etc. The sensor group is deployed in the pre-test area, and the sensor group is used to collect vehicle data so as to effectively monitor the vehicles entering the predetermined area.

[0014] Next, the collected data is established as a vehicle data set. The vehicle data set is a database that stores all information related to a specific vehicle, such as the vehicle's driving speed in the pre-test area, license plate data, and visual information of the vehicle's load. Among them, the vehicle's driving speed, that is, the vehicle speed data is collected by the speed sensor in the sensor group, such as a radar or laser speed meter; the license plate data is obtained by license plate recognition technology, such as a license plate recognition camera in the sensor group; the visual information of the vehicle's load, that is, the vehicle's load image is collected by the image acquisition device in the sensor group, such as a camera or image sensor. The vehicle data set is established, and then through subsequent analysis and processing, it is evaluated whether the vehicle is overloaded, and then an intelligent early warning is made.

[0015] Step 2: Activate the load-carrying sensor in the test area, and configure the test frequency of the load-carrying sensor according to the vehicle speed data in the vehicle data set.

[0016] Specifically, the test area refers to the actual monitoring area during the traffic control process. The load sensor is a sensor that measures the weight of the vehicle. In the test area, the load sensor is activated and put into working state to measure the weight of the vehicle.

[0017] Subsequently, the test frequency of the load sensor is configured using the vehicle speed data in the vehicle data set. Configuring the test frequency means adjusting the sampling frequency of the load sensor according to the vehicle speed to ensure that the load sensor can accurately collect the vehicle weight data. The faster the vehicle speed, the higher the sampling frequency required by the load sensor to capture accurate weight data, and vice versa, so as to ensure data accuracy and avoid energy waste caused by excessive operation of the load sensor.

[0018] Step three: using the configured load sensor to establish a load data set, wherein the load data set has a time stamp.

[0019] Specifically, after the load sensor is debugged and set up in the early stage, such as the sampling frequency, it collects and stores the weight information of the vehicle and establishes a load data set. For example, the load sensor is installed on the road surface or on a bridge. When a vehicle passes by, the load sensor will sense its weight and convert it into data, thereby completing the weight collection.

[0020] The load data set refers to the weight information data collected by the load sensor, including the weight of the vehicle, the time of passing, and other information. That is, the load data set has a time stamp. The time stamp includes the specific time of data collection, which is used to ensure the timeliness and accuracy of the data.

[0021] Step 4: acquiring speed measurement data in the test area based on the time stamp, wherein the speed measurement data includes real-time speed data and acceleration data.

[0022] Specifically, according to the time stamp recorded in the load data set, the vehicle speed information at the time corresponding to the time stamp is extracted from the speed sensor in the sensor group in the test area to obtain the speed measurement data. Speed ​​measurement data refers to the relevant information recorded about the vehicle's driving speed, which can reflect the dynamic behavior of the vehicle in the test area. Speed ​​measurement data includes real-time speed data and acceleration data. Real-time speed data refers to the driving speed of the vehicle at a specific moment, which is usually collected continuously in units of time and can reflect the current speed state of the vehicle. Acceleration data represents the rate of change of speed over time and is used to describe the dynamic situation of vehicle acceleration or deceleration. Acceleration is the derivative of speed change and can be obtained by calculating the difference between adjacent speed data.

[0023] Step 5: Input the speed measurement data and the load data set into a load compensation model to establish a load measurement result.

[0024] Specifically, the speed measurement data and the load data set are input into the load compensation model, which is used to calculate and process the load compensation model to obtain a more accurate load measurement result. The load compensation model is used to correct or compensate the load data according to environmental parameters (such as temperature, humidity, etc.). The load compensation model can adjust the load data according to the influence of environmental factors and vehicle dynamics. After being processed by the load compensation model, the final load measurement data is output to establish the load measurement result.

[0025] Step six: call vehicle information based on the license plate data, establish a first warning based on the vehicle information call result and the load measurement result, perform image recognition on the vehicle loading image, perform linkage analysis based on the image recognition result and the load measurement result, establish a second warning, and perform intelligent detection and abnormality reporting based on the first warning and the second warning.

[0026] Specifically, the vehicle information is called based on the license plate data, the unique identification information of the vehicle is obtained through license plate recognition technology, and then the detailed information of the vehicle is retrieved from the database using the unique identification information of the vehicle to obtain the vehicle information. The vehicle information includes vehicle type, manufacturer, owner, vehicle history, etc., so as to be used in subsequent detection and analysis.

[0027] The first warning is established based on the vehicle information call result and the load measurement result. After obtaining the vehicle information, the vehicle information is combined with the load measurement result to determine whether there is overloading or other loading conditions that do not meet the regulations. The load measurement result is the vehicle load data measured by sensors, instruments and other equipment. If the vehicle load exceeds the prescribed standard, an early warning is established to alert relevant personnel.

[0028] The loading images of vehicles are captured by cameras and other equipment, and image recognition technology is used to analyze the loading images of vehicles to identify the items loaded on the vehicle and their distribution. Image recognition technology usually classifies and measures the goods in the image and checks whether they meet the loading standards, and uses visual recognition to assist in determining whether there are any problems with the loading of the vehicle.

[0029] According to the image recognition results and load measurement results, linkage analysis is performed. After obtaining the image recognition results and load measurement data, the information of the two is combined for comprehensive analysis to establish a second warning. For example, image recognition may show that the vehicle is loaded with a large volume of cargo, while the load measurement results may indicate that the vehicle's load is close to or exceeds the standard, and then through linkage analysis, it is more accurately determined whether there is overloading or other loading problems. The second warning means that if abnormal loading or load mismatch is found, a higher level warning is generated. For example, if the first warning only shows load deviation, the second warning may indicate serious overloading or unstable loading, which prompts more urgent processing. According to the first and second warnings, intelligent detection abnormality reports are performed, and the existence of abnormalities is further confirmed by intelligent detection algorithms, and abnormalities are automatically reported.

[0030] The intelligent detection and early warning method of the traffic overload control system can achieve the technical goal of dynamic, real-time and efficient monitoring of vehicle load status and abnormal identification, and achieve the technical effect of comprehensively improving road traffic management efficiency and reducing the impact of overloading behavior on road infrastructure and traffic safety.

[0031] For further information, please see the attached Figure 2 The present application also includes: synchronizing the load data set to the environmental compensation layer of the load compensation model; using environmental monitoring sensors to perform environmental monitoring of the test area and establish an environmental data set, wherein the environmental data set includes temperature data, humidity data, and road surface condition data; synchronizing the environmental data set to the environmental compensation layer and performing compensation of the load data set; synchronizing the compensated load data set and the speed measurement data to the calculation layer to generate a load measurement result.

[0032] Specifically, the load compensation model is used to deal with errors related to the load to ensure that the weight data is more accurate. The environmental compensation layer is a layer in the load compensation model, which is used to integrate the impact of environmental factors such as temperature and humidity on the load data to ensure data accuracy. Among them, a large amount of basic data is collected, including the original load data of the vehicle, environmental data (such as temperature, humidity and road conditions, etc.) and other related parameters. The basic data is collected in real time by load sensors, environmental monitoring sensors and other equipment installed in the test area. Select appropriate machine learning or statistical modeling methods to train the load compensation model, such as linear regression, support vector machine (SVM) and neural network, etc., to predict and compensate the error of the load sensor based on the input basic data. After the training is completed, the load compensation model is verified using part of the basic data divided in advance to evaluate whether the compensation effect of the load compensation model meets expectations. The load data set is synchronized to the environmental compensation layer of the load compensation model, that is, the collected vehicle weight data is transferred to the environmental compensation layer of the load compensation model for load error compensation to obtain compensated load data.

[0033] Environmental monitoring sensors are devices in the sensor group that detect and record ambient environmental conditions. Environmental monitoring sensors are used to monitor the temperature, humidity, and road conditions in the test area, and establish an environmental data set, which includes temperature data, humidity data, and road condition data. Temperature data records the ambient temperature, humidity data records the moisture content in the air, and road condition data reflects the actual conditions of the road, such as whether it is slippery or whether there is water accumulation.

[0034] The environmental data set is synchronized to the environmental compensation layer, and the environmental data set is used in the environmental compensation layer to correct or compensate the load data set, eliminating the interference of environmental factors on the measurement data and improving the accuracy of the data. The compensated load data set and speed measurement data are synchronously sent to the calculation layer to generate the load measurement result. The load measurement result refers to the actual load value of the vehicle after considering factors such as environmental compensation and speed changes, which is used to determine whether the vehicle is overloaded or provide a basis for other management decisions.

[0035] Furthermore, the present application also includes: establishing dynamic weights of parameters, as follows: ;in, Characterization The dynamic weights of the environmental parameters, For the The sensitivity coefficient of each environmental parameter is For the Real-time values ​​of environmental parameters, is the total number of environmental parameters; dynamic weight compensation and interactive compensation are performed based on the dynamic weights of the parameters, as follows: ;in, Characterize dynamic weight compensation, , Characterizes the basic compensation coefficient, Characterization The influencing factor function of environmental parameters is Characterizing interactive compensation, , Characterization Environmental parameters and The interaction coefficient of the environmental parameters is Characterization Dynamic weights of environmental parameters.

[0036] Specifically, the parameter dynamic weight refers to the dynamic weight used in the environmental compensation layer to quantify the impact of each environmental data set on the load data. By setting the parameter dynamic weight, the environmental compensation layer can be made more flexible and can adjust the environmental data set in real time to adapt to environmental changes.

[0037] in, Characterization Dynamic weights of environment parameters are used to represent the weights of specific environment parameters through variables. For the The sensitivity coefficient of each environmental parameter is used to quantify the response of each environmental parameter to the load data. For the The real-time value of the environmental parameter. The actual value of an environmental parameter at the current moment. is the total number of environmental parameters, which refers to the total number of all relevant environmental factors. An integer greater than 0.

[0038] Perform dynamic weight compensation and interactive compensation based on the dynamic weight of the parameters to obtain the compensated result Dynamic weight compensation refers to adjusting the load data according to the real-time values ​​and sensitivity coefficients of different environmental parameters to make the load data more accurate. Interactive compensation refers to further considering the mutual influence between environmental parameters, which means that different environmental parameters may interact with each other and jointly affect the load data.

[0039] Characterizes dynamic weight compensation, indicating the degree of load data compensation. The degree of compensation is affected by the basic compensation coefficient. And the influence of environmental parameters. Basic compensation coefficient It is an overall estimate of the impact of all environmental parameters in the environmental compensation layer, such as the basic compensation coefficient It is a constant derived from historical data or prior knowledge. Characterization The influencing factor function of the environmental parameters represents The influence of environmental parameters on load data under different conditions is It will change with time, temperature, humidity and other factors.

[0040] Characterization Dynamic weights of environmental parameters. Characterizes the interaction compensation, reflecting the The influence of each environmental parameter on the final compensation result, which in turn indicates the compensation effect of the interaction between environmental parameters on the load data, is expressed through dynamic weights. Participate in the calculation. Among them, , is greater than 0 and less than or equal to An integer.

[0041] Furthermore, the present application also includes: the interaction influence coefficient is calculated as follows: ;in, represents the number of data samples, Characterization Parameters in the sample The value of Characterization Parameters in the sample The value of , Characterization parameters and parameters The mean of , The parameters are and parameters The standard deviation of .

[0042] Specifically, the interaction coefficient represents the joint influence between environmental parameters. The interaction coefficient calculation is used to measure the interaction value between different environmental parameters and obtain the compensation result of multiple environmental factors synergistically affecting the load data.

[0043] in, Represents the number of data samples, the total number of data points or samples used to calculate the interaction coefficient. Characterization Parameters in the sample The value of Characterization Parameters in the sample The value of indicates that each sample contains a set of environmental parameter values. is an integer greater than 0, is greater than 0 and less than or equal to An integer.

[0044] Next, the parameters The mean value of ,parameter The mean value of , the mean is obtained by adding the parameter values ​​in all samples and dividing by the number of samples. The standard deviation of ,parameter The standard deviation of , standard deviation , The parameters are and parameters The degree of fluctuation between all data samples and their mean. The standard deviation is an indicator of the degree of data dispersion. The larger the standard deviation, the wider the range of data variation, and the smaller the standard deviation, the smaller the data fluctuation. Through the mean and standard deviation, the interaction coefficient can consider the distribution characteristics between environmental parameters and measure the impact of the common changes in environmental parameters on the load data.

[0045] Furthermore, the present application also includes: calling the vehicle model information based on the license plate data, and generating the vehicle's rated load data according to the vehicle model information; using the rated load data and the load measurement result to perform load comparison and establish a load deviation value; using the license plate data to call the vehicle's historical load data and establish a vehicle load behavior abnormality coefficient; using the vehicle load behavior abnormality coefficient to pay attention to and identify the load deviation value and establish the first warning.

[0046] Specifically, the vehicle model information is called based on the license plate data, and the model information corresponding to the license plate is queried in the database. The model information includes detailed information such as the manufacturer, model, and body type of the vehicle, which is used to determine the rated load of the vehicle. The rated load of the vehicle refers to the maximum load capacity specified in the design of the model, which represents the maximum load limit of the vehicle.

[0047] The rated load data and load measurement results are used for load comparison. The actual measured vehicle load is compared with its rated load to obtain the load deviation value, which represents the difference between the actual vehicle load and its designed maximum load capacity.

[0048] The license plate data is used to call the historical load data of the vehicle. The vehicle's past load records are queried and obtained by the license plate number to analyze the vehicle's load behavior in different time periods and identify changes in its load pattern. By analyzing the historical load data, the normal fluctuation range of the vehicle's load behavior is calculated, and the degree of deviation from the normal range is evaluated to establish the vehicle's load behavior abnormality coefficient.

[0049] The load deviation value is identified by using the abnormal load behavior coefficient of the vehicle, that is, by analyzing the historical load behavior of the vehicle and combining it with the current load deviation value, it is determined whether the vehicle has abnormal behavior. If the load deviation value is large, and the abnormal load behavior coefficient of the vehicle's history also indicates that the vehicle is usually stable in load, and the deviation is more prominent this time, an alarm will be issued, indicating that the vehicle may be overloaded or have other non-compliant load behaviors. Then, according to the preset rules, further monitoring measures are taken, such as requiring the vehicle to stop for detailed inspection. If the actual load value of the vehicle is close to the rated load limit of the vehicle model, or is very close to the design load limit. At this time, although the load deviation value may not be particularly large, it may still have an adverse effect on the safety of the vehicle, road safety and transportation quality because the actual load of the vehicle is close to its load limit. Therefore, when it is judged that the load is close to the limit, more stringent response measures are taken to require the vehicle to stop for a more careful inspection.

[0050] Furthermore, the present application also includes: establishing a standard vehicle model image based on the vehicle model information; after obtaining the owner's authorization, using the license plate data to call the vehicle's loading cargo information; using the standard vehicle model image, the image recognition result, and the loading cargo information to identify loading abnormalities and establish loading specification abnormalities; establishing a loading volume prediction result based on the standard vehicle model image and the image recognition result; performing a load prediction based on the loading volume prediction result and the loading cargo information, and establishing a linked prediction abnormality; and establishing a second warning based on the loading specification abnormality and the linked prediction abnormality.

[0051] Specifically, a standard vehicle image is established based on vehicle model information. By querying and using the vehicle model data, a standard image model is generated to represent the appearance characteristics and size specifications of the vehicle type. Vehicle model information usually includes the model, manufacturer, body type, etc. A standardized vehicle image is generated based on the vehicle model information as a benchmark for subsequent processing and recognition.

[0052] After obtaining the vehicle owner's authorization and with the vehicle owner's consent, the vehicle's cargo loading information is called using the license plate data to query and obtain the vehicle's current or historical cargo loading information, including the type, weight, volume, etc. The vehicle owner's authorization is to ensure privacy and compliance, while the cargo loading information is important data that reflects the vehicle's actual loading status.

[0053] Compare the standard vehicle image with the actual vehicle image, and combine image recognition technology to analyze whether the vehicle loading situation meets the specifications. The image recognition result is the vehicle image captured by a camera or other visual device. The loading cargo information provides detailed data on the vehicle loading. The standard vehicle image, image recognition results, and loading cargo information are combined to determine whether the vehicle has loading anomalies and identify whether the vehicle's loading behavior meets the predetermined loading specifications. If the vehicle's loading situation exceeds the prescribed limit or does not match the standard vehicle image, it is considered that there is a loading specification anomaly and a loading specification anomaly is established. Such as overloading, uneven loading, or inconsistent cargo type.

[0054] Image recognition is performed through image recognition technology to obtain image recognition results. The volume of the cargo loaded on the vehicle is calculated based on the image recognition results and compared with the spatial specifications of the standard vehicle model image to establish a loading volume prediction result, which is used to evaluate whether the vehicle's cargo space meets the maximum load standard and whether the distribution of the cargo is reasonable.

[0055] The load prediction is performed based on the load volume prediction results and the loaded cargo information. The load prediction is to predict whether the vehicle is overloaded or whether there is a potential overload risk. When a deviation is found between the actual load of the vehicle and the predicted result, a linkage prediction exception is established.

[0056] If abnormal loading specifications and linkage predictions are obtained, the second warning will be triggered. The second warning is a higher-level warning for vehicle loading behavior, reminding supervisors to conduct detailed inspections and handle them, which will help strengthen supervision of vehicle loading and ensure transportation safety and compliance.

[0057] Furthermore, the present application also includes: conducting fleet detection in the pre-test area and establishing fleet detection feedback; if the fleet detection feedback is a result that a passing fleet exists, generating a migration instruction; and performing intelligent detection of vehicle loads within the fleet according to the migration instruction.

[0058] Specifically, in a pre-set pre-test area, the fleet is detected through sensors, cameras, radars and other equipment. Fleet detection refers to monitoring and analyzing the real-time operating status, speed, load, etc. of a group of vehicles in a certain area, obtaining the fleet's traffic status, establishing fleet detection feedback, and providing data support for subsequent processing.

[0059] When the fleet detection feedback indicates that the fleet has a problem passing through a certain area, that is, when there is a passing fleet result, a migration instruction is generated. The passing fleet result refers to whether the fleet passes normally on a certain road section, whether there is congestion or excessive traffic flow. The migration instruction is used to guide the fleet to change the route or adjust the driving plan to avoid stagnation or serious traffic accidents.

[0060] After receiving the migration instruction, the load detection is carried out on the vehicles in the fleet, and the load of each vehicle is measured. It may also combine factors such as vehicle speed and road conditions to intelligently determine whether there are overloaded or other abnormally loaded vehicles, to ensure that the vehicles do not have non-compliant loads during the migration process.

[0061] Furthermore, the present application also includes: matching warning levels based on the first warning and the second warning to establish an abnormal level matching result; using the warning level matching result to establish a warning response plan, and performing intelligent detection and abnormal reporting based on the abnormal level matching result and the warning response plan.

[0062] Specifically, the warning level matching is performed based on the first warning and the second warning, the warning information from different warning sources is analyzed, the warning information is classified according to certain rules, and the abnormal level matching results are established. The first warning usually refers to a preliminary alarm triggered by abnormal vehicle loading behavior or load deviation, while the second warning is a further warning based on abnormal loading specifications or linkage prediction. The purpose of warning level matching is to uniformly classify different types of warning information so that corresponding measures can be taken according to different degrees of severity. For example, if the first warning shows that the vehicle is slightly overloaded, and the second warning shows that there is a serious risk of overloading, the urgency of the problem is judged based on the matching results of the two.

[0063] Use the warning level matching results to establish a warning response plan and formulate corresponding response measures. The warning response plan is determined according to the abnormality level. High-level abnormalities may require immediate intervention, while low-level abnormalities may only require observation or follow-up inspections. For example, when a high-level warning shows that a vehicle is overloaded, the traffic police are instructed to conduct an on-site inspection or require the vehicle to be temporarily suspended; while a low-level warning may only require the vehicle to undergo further inspection at the next inspection.

[0064] According to the abnormal level matching results and early warning response plan, intelligent detection abnormality reporting is carried out, and abnormal situations are reported and responded to according to the set early warning response plan. If the detected abnormality meets a certain level, an alarm signal will be issued through automated means, and relevant personnel or departments will be notified to handle it. For example, if a vehicle is detected to be seriously overloaded, an alarm will be issued immediately to notify the traffic management department to take necessary law enforcement measures.

[0065] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0066] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The intelligent detection and early warning method of the traffic overload control system is characterized by: include: Deploy sensor groups in the pre-test area and collect vehicle data to establish a vehicle data set; activating a load sensor in a test area, and configuring a test frequency of the load sensor according to vehicle speed data in the vehicle data set; Using the configured load sensor to establish a load data set, the load data set has a time stamp; Acquire speed measurement data in the test area based on the time mark, the speed measurement data including real-time speed data and acceleration data; Inputting the speed measurement data and the load data set into a load compensation model to establish a load measurement result; The vehicle information is called up according to the license plate data, a first warning is established based on the vehicle information calling result and the load measurement result, image recognition is performed on the vehicle loading image, a linkage analysis is performed based on the image recognition result and the load measurement result, a second warning is established, and intelligent detection abnormality reporting is performed based on the first warning and the second warning.

2. The intelligent detection and early warning method for the traffic overload control system according to claim 1 is characterized in that: The step of inputting the speed measurement data and the load data set into a load compensation model to establish a load measurement result includes: synchronizing the load data set to an environmental compensation layer of the load compensation model; Using environmental monitoring sensors to monitor the environment of the test area and establish an environmental data set, wherein the environmental data set includes temperature data, humidity data, and road surface condition data; Synchronize the environmental data set to the environmental compensation layer and perform compensation for the load data set; The compensated load data set and the speed measurement data are synchronized to the computing layer to generate a load measurement result.

3. The intelligent detection and early warning method for the traffic overload control system according to claim 2 is characterized in that: The step of synchronizing the environmental data set to the environmental compensation layer and performing the load data set compensation comprises: Establish parameter dynamic weights as follows: ； in, Characterization The dynamic weights of the environmental parameters, For the The sensitivity coefficient of each environmental parameter is For the Real-time values ​​of environmental parameters, is the total number of environmental parameters; Dynamic weight compensation and interactive compensation are performed based on the dynamic weights of the parameters as follows: ； in, Characterize dynamic weight compensation, , Characterizes the basic compensation coefficient, Characterization The influencing factor function of environmental parameters is Characterizing interactive compensation, , Characterization Environmental parameters and The interaction coefficient of the environmental parameters is Characterization Dynamic weights of environmental parameters.

4. The intelligent detection and early warning method for the traffic overload control system according to claim 3 is characterized in that: The interaction coefficient is calculated as follows: ； in, represents the number of data samples, Characterization Parameters in the sample The value of Characterization Parameters in the sample The value of , Characterization parameters and parameters The mean of , The parameters are and parameters The standard deviation of .

5. The intelligent detection and early warning method for the traffic overload control system according to claim 1, characterized in that: The calling of vehicle information according to the license plate data and establishing a first warning based on the vehicle information calling result and the load measurement result include: Retrieving vehicle model information based on the license plate data, and generating the vehicle's rated load data according to the vehicle model information; Performing load comparison using the rated load data and the load measurement result to establish a load deviation value; Using the license plate data to call the historical load data of the vehicle, and establish the abnormal coefficient of vehicle load behavior; The vehicle load behavior abnormality coefficient is used to focus on and identify the load deviation value, and the first warning is established.

6. The intelligent detection and early warning method for the traffic overload control system according to claim 5, characterized in that: The performing image recognition on the vehicle loading image, performing linkage analysis based on the image recognition result and the load measurement result, and establishing a second warning includes: Establishing a standard vehicle model image according to the vehicle model information; After obtaining the vehicle owner's authorization, the vehicle's cargo loading information is retrieved using the license plate data; Using the standard vehicle model image, the image recognition result, and the loaded cargo information, loading anomaly recognition is performed to establish loading specification anomalies; Establishing a loading volume prediction result based on the standard vehicle model image and the image recognition result; Performing load prediction based on the load volume prediction result and the load cargo information, and establishing linkage prediction anomalies; A second warning is established based on the loading specification abnormality and the linkage prediction abnormality.

7. The intelligent detection and early warning method for the traffic overload control system according to claim 1, characterized in that: Also includes: Conducting fleet testing in the pre-test area and establishing fleet testing feedback; If the fleet detection feedback is that there is a passing fleet, a migration instruction is generated; Intelligent detection of vehicle loads within the fleet is performed according to the migration instructions.

8. The intelligent detection and early warning method for the traffic overload control system according to claim 1, characterized in that: The intelligent detection and abnormality reporting according to the first warning and the second warning includes: Perform warning level matching based on the first warning and the second warning, and establish an abnormal level matching result; An early warning response plan is established using the early warning level matching result, and intelligent detection and abnormality reporting are performed based on the abnormality level matching result and the early warning response plan.

Images