Vehicle-road cloud cooperative vehicle-mounted overweight full-chain intelligent supervision and disposal system

Abstract

The invention relates to the technical field of intelligent transportation, and discloses a vehicle-mounted overweight full-chain intelligent supervision and disposal system based on vehicle-road cloud cooperation. The system comprises a vehicle-mounted terminal layer, a roadside sensing layer, a cloud platform layer and a disposal execution layer, and the layers interact in real time through a V2X communication protocol. The vehicle-mounted terminal collects load, position and driving state data; the roadside sensing layer collects auxiliary load and environmental data; the cloud platform layer is internally provided with vehicle-mounted dynamic load fusion detection, overweight risk level quantitative evaluation, vehicle-road cooperative overweight verification, overweight vehicle optimal disposal path planning, multi-source disposal resource scheduling optimization and an overweight illegal behavior tracing matching algorithm to realize full-chain intelligent management and control of overweight detection, verification, evaluation, disposal and tracing; and the disposal execution layer responds to the cloud instruction to execute law enforcement and intervention operation. According to the system, through multi-sensor fusion and vehicle-road cloud cooperation, the overweight detection precision and the disposal efficiency are improved, full-chain closed-loop supervision is realized, and the road traffic safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and vehicle-road cooperative technology, specifically to a vehicle-road-cloud cooperative intelligent monitoring and handling system for the entire chain of overloaded vehicles. Background Technology

[0002] Overloading of vehicles is a major contributing factor to road traffic accidents. It not only damages road infrastructure but also increases braking distance and reduces vehicle handling stability, seriously threatening the lives and property of drivers, passengers, and other road users. Traditional methods of monitoring overloading rely heavily on static detection at fixed overload control stations, which suffers from limited detection range, susceptibility to evasion, and incomplete regulatory chains.

[0003] With the development of vehicle-road-cloud collaborative technology, real-time interaction between vehicle terminals, roadside equipment, and cloud platforms has made it possible to achieve dynamic monitoring of the entire overweight supply chain. However, existing vehicle-road-cloud collaborative technologies have shortcomings in overweight monitoring scenarios, such as insufficient detection accuracy, lack of quantitative risk assessment models, and weak targeting of disposal strategies, making it difficult to meet the needs of intelligent monitoring across the entire chain. Therefore, there is an urgent need to design a vehicle-road-cloud collaborative overweight monitoring and disposal system integrating multiple algorithms to achieve full-process control, including accurate overweight detection, real-time risk assessment, and intelligent disposal scheduling. Summary of the Invention

[0004] To address the aforementioned issues, this invention introduces a vehicle-road-cloud collaborative intelligent monitoring and handling system for overloaded vehicles across the entire supply chain, comprising an onboard terminal layer, a roadside perception layer, a cloud platform layer, and a handling execution layer.

[0005] The vehicle-mounted terminal layer is equipped with a weighing sensor, a GPS positioning module, an IMU (Inertial Measurement Unit), and a vehicle-mounted communication module, which are used to collect real-time vehicle load data, location information, and driving status data.

[0006] The roadside perception layer is equipped with radar, cameras, roadside weighing equipment and roadside communication units to collect auxiliary load data, road traffic environment data and vehicle trajectory data.

[0007] The cloud platform layer integrates a data storage module, an algorithm operation module, and a decision scheduling module;

[0008] The execution layer includes a roadside enforcement terminal, a vehicle braking assistance module, and a road maintenance early warning module. The execution layer receives instructions from the cloud platform layer via the V2X communication protocol and performs corresponding operations such as enforcement, vehicle driving intervention, and road maintenance early warning in real time.

[0009] Preferably, the algorithm operation module has built-in vehicle dynamic load fusion detection algorithm, overload risk level quantitative assessment algorithm, vehicle-road cooperative overload verification algorithm, overload vehicle optimal disposal path planning algorithm, multi-source disposal resource scheduling optimization algorithm, and overload violation tracing and matching algorithm.

[0010] Preferably, the vehicle-mounted dynamic load fusion detection algorithm is based on the fusion of data from multiple vehicle sensors to achieve accurate detection of vehicle load during dynamic driving, and the formula is as follows:

[0011] ;

[0012] in, The actual load of the merged vehicle is expressed in tons (t). The weighting coefficients for each sensor data satisfy the following conditions: The result was obtained through optimization using an adaptive genetic algorithm. ;

[0013] Real-time load data collected by the vehicle-mounted weighing sensor, in tons (t). The load data is derived from inertial measurement unit data, in tons (t), and its derivation formula is as follows: , The longitudinal inertial force detected by the IMU, in N. The longitudinal acceleration of the vehicle is expressed in m / s², and g is the acceleration due to gravity, taken as 9.8 m / s². The unloaded baseline load of the vehicle is determined by the vehicle's factory parameters and is measured in tons (t).

[0014] Preferably, the overload risk level quantitative assessment algorithm is based on the fused load data, vehicle driving status, and road environment parameters to quantitatively assess the safety risk level of vehicle overload driving, and the formula is:

[0015] ;

[0016] in, The overall risk level for overweight is 0 to 10, with 0 indicating no risk and 10 indicating extremely high risk. , , The weights of each risk factor satisfy the following conditions: ; The overload risk factor ranges from 0 to 10, and the calculation formula is as follows: , The approved load capacity of a vehicle is measured in tons (t). The vehicle driving status risk factor has a value range of 0 to 10, and the calculation formula is as follows: , The actual speed of the vehicle. The current speed limit for this section of road is in km / h. The longitudinal acceleration for vehicle safety is set at 2.5 m / s². The road environmental risk factor has a value range of 0 to 10, and the calculation formula is as follows: , For the quantity of environmental factors, For the first The weights of environmental factors are preset, with weight coefficients for six categories of environmental factors. The total is 10, which is the weighting coefficient of the single factor. Based on risk level: Snowy weather Foggy days ,rain Construction area School section ,at night When multiple environmental factors are present, For each The sum, with a maximum value of 10, is calculated if snowy days, foggy days, and rainy days coexist. , For environmental factors, state variables, when this environmental factor exists ,otherwise .

[0017] Preferably, the vehicle-road cooperative overload verification algorithm integrates on-board terminal detection data and roadside perception data to perform secondary verification of the overload state, as shown in the formula:

[0018] ;

[0019] in, For the overweight verification results, This indicates that the weight is confirmed to be overweight. This indicates that you are not overweight. The absolute value is the overweight percentage, that is... , hour, This represents the actual percentage of overweight individuals. At that time, it represents the proportion of those who were not overweight or whose test data deviated. This is a sign function; it returns 1 for a positive input, -1 for a negative input, and 0 for a zero input. The weights for roadside data range from 0.3 to 0.5. The actual load capacity of the merged vehicle. The rated load capacity of the vehicle is expressed in tons (t). Vehicle load data collected by roadside weighing equipment, in tons (t).

[0020] Preferably, the optimal handling path planning algorithm for overweight vehicles plans a handling path for vehicles confirmed to be overweight, taking into account real-time road conditions, the location of the overweight vehicle control station, and road restrictions. The formula is as follows:

[0021] ;

[0022] in, This is the optimal handling path; The set of all feasible disposal paths; For path The estimated travel time, in minutes, is calculated using the following formula: , The path element is a infinitesimal element, with units of km. For path infinitesimal elements Real-time driving speed at the location, in km / h; For path The total length, in km; For path The safety risk coefficient, ranging from 0 to 1, is calculated using the following formula:

[0023] ,

[0024] For path The number of curves on the road For path The length, in km. For path The elevation difference, in kilometers. For path Average traffic flow The saturation traffic volume for the road segment is expressed in vehicles per hour. , These are the weighting coefficients, and , .

[0025] Preferably, the multi-source disposal resource scheduling optimization algorithm optimizes disposal resources and improves disposal efficiency based on the location, risk level, and enforcement resource status of each overload control station. The formula is as follows:

[0026] ;

[0027] in, Resources to be optimally scheduled; A collection of available disposal resources; To dispose of resources Arrival of overweight vehicles Estimated time at location, in minutes; To dispose of resources The scheduling cost, in yuan, includes labor costs and equipment depreciation costs. To dispose of resources Overweight vehicles The straight-line distance, in km; The overall risk level of overweight vehicles; , , These are the weighting coefficients, and =0.4, =0.3, =0.3, With a base weight of 0.3, when the risk level... When the weighting coefficients are adjusted, the following applies: .

[0028] Preferably, the overweight violation tracing and matching algorithm combines vehicle historical driving data, load data, roadside perception records, and violation information stored in the cloud to achieve accurate tracing and matching of overweight violations, as shown in the formula:

[0029] ;

[0030] in, To track the matching degree, the value ranges from 0 to 1. The match is considered successful at that time. The number of historical data samples to be matched; For the first The fused load data of historical samples, in tons; This is the overweight determination function; when the input is >0... ,otherwise ; The time matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The collection time of each historical sample, The time of the suspected illegal activity The time matching threshold is set to 30 minutes. The position matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The vehicle location plane coordinates of each historical sample are Gauss-Kruger projection coordinates, in km. The location coordinates of the suspected illegal activity are Gauss-Kruger projection coordinates, with units of km, and Euclidean distance is used for distance calculation. The location matching threshold is set to 1km. The rated load capacity of a vehicle is specified in tons (t).

[0031] Preferably, the vehicle terminal layer, roadside perception layer, cloud platform layer, and processing execution layer achieve real-time data transmission through V2X, i.e., vehicle-to-everything (V2X) communication protocol.

[0032] Preferably, the workflow of the vehicle-road-cloud collaborative intelligent monitoring and handling system for overloaded vehicles includes the following steps:

[0033] S1. Data Acquisition: The vehicle terminal layer and the roadside perception layer respectively collect corresponding data and upload them to the cloud platform layer; S2. Overload Detection: The cloud platform layer calculates the fused load through the vehicle dynamic load fusion detection algorithm to preliminarily determine whether it is overloaded;

[0034] S3. Secondary verification: The cloud platform layer integrates roadside load data through the vehicle-road cooperative overload verification algorithm to confirm the overload status;

[0035] S4. Risk Assessment: The cloud platform layer assesses the overall risk level of overweight through a quantitative assessment algorithm for overweight risk levels.

[0036] S5. Path planning and resource scheduling: The cloud platform layer plans the disposal path through the optimal disposal path planning algorithm for overweight vehicles and schedules disposal resources through the multi-source disposal resource scheduling optimization algorithm.

[0037] S6. Enforcement and Traceability: The enforcement layer executes enforcement operations, while the cloud platform layer uses an algorithm to trace and match serious violations, forming a regulatory closed loop.

[0038] Beneficial effects

[0039] This invention achieves intelligent monitoring and handling of overloaded vehicles across the entire supply chain through the synergistic effect of a vehicle-road-cloud collaborative architecture and algorithms, offering the following advantages compared to existing technologies:

[0040] Accuracy: Through multi-sensor data fusion of the vehicle-mounted dynamic load fusion detection algorithm and secondary verification of the vehicle-road cooperative overload verification algorithm, the overload detection accuracy is greatly improved;

[0041] Comprehensiveness: The algorithm covers the entire chain of overweight detection, verification, evaluation, disposal, and traceability, solving the problem of incomplete traditional regulatory chains;

[0042] Intelligentization: By combining the optimal path planning algorithm for the optimal disposal of overweight vehicles with the resource scheduling optimization algorithm for multi-source disposal resources, disposal efficiency is improved and regulatory costs are reduced.

[0043] Reliability: Through the tracking and matching algorithm for excessive illegal acts, reliable evidence is provided for law enforcement and evidence collection, ensuring the fairness and authority of supervision. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0045] Figure 1 This is a flowchart of the algorithm logic of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] This invention discloses a vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain, comprising an on-board terminal layer, a roadside perception layer, a cloud platform layer, and a handling execution layer. Each layer achieves efficient and reliable data interaction through a vehicle-to-the-world (V2X) communication protocol. The specific interaction logic is as follows: The on-board terminal layer, acting as the front-end data acquisition end, uploads raw vehicle weighing data, GPS / IMU positioning data, and vehicle driving status data to the roadside perception layer via a vehicle-to-the-road (V2I) link using the V2X communication protocol; simultaneously, it connects to the cloud (V2N) via the V2X communication protocol. The link synchronizes the aforementioned data to the cloud platform layer, enabling real-time data interaction across multiple terminals. The roadside sensing subsystem receives vehicle-mounted data via the V2I link and then uploads its collected roadside dynamic weighing data and UWB positioning deviation data to the cloud-based monitoring subsystem via the V2N link. Simultaneously, it feeds back roadside calibration benchmark information to the vehicle-mounted terminal via the V2I link. The cloud-based monitoring subsystem receives multi-source data from both the vehicle and roadside via the V2N link. After algorithm processing, it generates overload judgment results, risk warning information, and dispatch instructions, which are then distributed to the roadside sensing subsystem and the vehicle-mounted terminal subsystem via the V2N link. It also issues dispatch instructions to the enforcement terminal for handling resources via the V2N link. The adopted V2X communication protocol is compatible with the IEEE 802.11p standard, supporting low-latency and high-reliability communication requirements. It can adapt to the real-time data interaction needs in dynamic driving scenarios and ensures data transmission security through encryption and authentication mechanisms, preventing data tampering or theft. This provides communication support for the real-time performance, accuracy, and security of the entire monitoring chain.

[0048] The vehicle-mounted terminal layer is equipped with a weighing sensor, a GPS positioning module, an inertial measurement unit, and a vehicle communication module. It is used to collect real-time vehicle load data, location information, and driving status data, and upload them to the roadside perception layer and the cloud platform layer. At the same time, it receives early warning information and handling instructions issued by the cloud.

[0049] The roadside perception layer is equipped with radar, cameras, roadside weighing equipment, and roadside communication units to assist in verifying vehicle load data, monitoring road traffic conditions and vehicle trajectories, and transmitting perception data to the vehicle terminal layer and cloud platform layer.

[0050] The cloud platform layer integrates data storage, algorithm operation, and decision scheduling modules. Through vehicle-mounted dynamic load fusion detection algorithm, overload risk level quantitative assessment algorithm, vehicle-road cooperative overload verification algorithm, overload vehicle optimal disposal path planning algorithm, multi-source disposal resource scheduling optimization algorithm, and overload violation traceability and matching algorithm, it achieves functions such as accurate overload identification, risk assessment, path planning, and disposal scheduling, and issues instructions to each layer.

[0051] The enforcement layer includes roadside enforcement terminals, vehicle braking assistance modules, and road maintenance early warning modules, which are used to respond to cloud commands and carry out enforcement actions, vehicle interventions, and maintenance reminders.

[0052] The vehicle-mounted dynamic load fusion detection algorithm is based on the fusion of data from multiple vehicle sensors to achieve accurate detection of vehicle load during dynamic driving, solving the problem of large detection errors by a single sensor under bumpy or turning conditions; the specific formula is as follows:

[0053] ;

[0054] in, The actual load of the merged vehicle is expressed in tons (t). The weighting coefficients for each sensor data are used when the weighing sensor accuracy is <0.5%. The initial value is 0.6; when the IMU precision is <0.1g, The initial value is 0.15; when the no-load reference load error is >5%, The initial value was set to 0.05; all initial values ​​were within the optimization range. Subsequent adjustments were made using vehicle driving history data combined with an adaptive genetic algorithm for iterative calibration, ultimately satisfying the desired result. + + =1 Real-time load data collected by the vehicle-mounted weighing sensor, in tons (t). The load data is derived from inertial measurement unit data, in tons (t), and its derivation formula is as follows: , The longitudinal inertial force detected by the IMU, in N. The longitudinal acceleration of the vehicle is expressed in m / s². The acceleration due to gravity is taken as 9.8 m / s². The unloaded baseline load of the vehicle is determined by the vehicle's factory parameters and is measured in tons (t).

[0055] The algorithm for quantitatively assessing the risk level of overloaded vehicles is based on fused load data, vehicle driving status, and road environment parameters. It quantifies the safety risk level of overloaded vehicles, providing a basis for subsequent response strategies. The specific formula is as follows:

[0056] ;

[0057] in, The overall risk level for overweight individuals ranges from 0 to 10. Low risk; Medium risk; High risk; Extremely high risk; , , The weights of each risk factor satisfy the following conditions: ; The overload risk factor ranges from 0 to 10, and the calculation formula is as follows: , The approved load capacity of a vehicle is measured in tons (t). The vehicle driving status risk factor has a value range of 0 to 10, and the calculation formula is as follows:

[0058] , The actual speed of the vehicle. The current speed limit for this section of road is in km / h. The longitudinal acceleration for vehicle safety is set at 2.5 m / s². The road environmental risk factor has a value range of 0 to 10, and the calculation formula is as follows: , For the quantity of environmental factors, For the first The weighting coefficients of various environmental factors As a state variable of environmental factors, when this environmental factor exists... ,otherwise .

[0059] The vehicle-road cooperative overweight verification algorithm integrates on-board terminal detection data and roadside perception data to perform secondary verification of the overweight status, reducing the false detection rate of a single data source and ensuring the accuracy of overweight determination. The specific formula is as follows:

[0060] ;

[0061] in, For the overweight verification results, This indicates that the weight is confirmed to be overweight. This indicates that you are not overweight. The absolute value is the overweight percentage, that is... , hour, This represents the actual percentage of overweight individuals. At that time, it represents the proportion of those who were not overweight or whose test data deviated. This is a sign function; it returns 1 for a positive input, -1 for a negative input, and 0 for a zero input. The weights for roadside data range from 0.3 to 0.5. The actual load capacity of the merged vehicle. The rated load capacity of the vehicle is expressed in tons (t). Vehicle load data collected by roadside weighing equipment, in tons (t).

[0062] The optimal handling route planning algorithm for overweight vehicles plans the optimal handling route for confirmed overweight vehicles, taking into account real-time road conditions, the location of the overweight vehicle inspection station, and road restrictions. This ensures that the vehicle travels to the designated overweight vehicle inspection station efficiently and safely. The specific formula is as follows:

[0063] ;

[0064] in, This is the optimal handling path; For the set of all feasible disposal paths; For path The estimated travel time, in minutes, is calculated using the following formula: , The path element is a infinitesimal element, with units of km. For path infinitesimal elements Real-time driving speed at the location, in km / h; For path The total length, in km; For path The safety risk coefficient, ranging from 0 to 1, is calculated using the following formula:

[0065] ,

[0066] For path The number of curves on the road For path The length, in km. For path The elevation difference, in kilometers. For path Average traffic flow The saturation traffic volume for the road segment is expressed in vehicles per hour. , These are the weighting coefficients, and , .

[0067] The multi-source disposal resource scheduling optimization algorithm optimizes the scheduling of disposal resources such as law enforcement personnel and detection equipment based on the location and risk level of overweight vehicles and the enforcement resource status of each overweight vehicle control station, thereby improving disposal efficiency. The specific formula is as follows:

[0068] ;

[0069] in, Resources to be optimally scheduled; A collection of available disposal resources; To dispose of resources Arrival of overweight vehicles Estimated time at location, in minutes; To dispose of resources The scheduling cost, in yuan, includes labor costs and equipment depreciation costs. To dispose of resources Overweight vehicles The straight-line distance, in km; The overall risk level of overweight vehicles; , , These are the weighting coefficients, and =0.4, =0.3, =0.3, the higher the risk level, The weight can be dynamically increased.

[0070] The algorithm for tracing and matching overweight violations combines historical vehicle driving data, load data, roadside sensing records, and violation information stored in the cloud to achieve accurate tracing and matching of overweight violations, providing evidence for law enforcement. The specific formula is as follows:

[0071] ;

[0072] in, To track the matching degree, the value ranges from 0 to 1. A match is considered successful when the value is ≥0.7; The number of historical data samples to be matched; For the first The fused load data of historical samples, in tons; This is the overweight determination function; when the input is >0... ,otherwise ; The time matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The collection time of each historical sample, The time of the suspected illegal activity The time matching threshold is set to 30 minutes. The position matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The planar coordinates of the vehicle positions in a historical sample. The coordinates of the suspected illegal activity are shown in km. The location matching threshold is set to 1km. The rated load capacity of a vehicle is specified in tons (t).

[0073] The present invention will be further described in detail below with reference to specific embodiments:

[0074] [Example 1] A heavy truck is traveling on a highway. The onboard weighing sensor collects a load data of 42t, the IMU collects a longitudinal inertial force of 10000N, a longitudinal acceleration of 0.2m / s², a vehicle baseline load of 15t, and a rated load of 30t. The fused load is calculated using an onboard dynamic load fusion detection algorithm:

[0075] First calculate calculate g is the gravitational acceleration of 9.8 m / s², and dividing by 1000 converts kg to t.

[0076] With weighting coefficients set α=0.7, β=0.2, and γ=0.1, the following is calculated based on the vehicle-mounted dynamic load fusion detection algorithm:

[0077] .

[0078] The risk level is assessed using a quantitative algorithm for assessing overweight risk: the vehicle's actual speed is 80 km / h, the current road speed limit is 100 km / h, the longitudinal acceleration is 0.2 m / s², which is less than the safe acceleration of 2.5 m / s², and the road conditions are clear, straight, with no construction, and no school zones. , , Comprehensive risks It was determined to be low risk;

[0079] The roadside weighing equipment collected a load data of 32.1t, which was verified by the vehicle-road cooperative overload verification algorithm. ,but It was determined that the weight was not excessive, and no action was required.

[0080] [Example 2] A heavy truck was traveling on a provincial highway with a combined onboard load of 45t, a rated load of 30t, an actual speed of 60km / h, a speed limit of 60km / h, a longitudinal acceleration of 0.8m / s², and a rainy, curved road environment. The suspected overweight violation occurred at 14:30 at kilometer marker K120+500 on the provincial highway.

[0081] Calculated using an algorithm for quantitative assessment of overweight risk levels ;

[0082] ,

[0083] The preset total weight of environmental factors is 10, with rainy days having a weight of 10. Curve weight If no other environmental factors are present, the value is 0. Comprehensive risks It was determined to be high-risk;

[0084] The vehicle-road cooperative overweight verification algorithm verifies that S=0.35>0, thus confirming overweight.

[0085] The optimal route planning algorithm for handling overweight vehicles plans the optimal route to the nearest overweight vehicle control station, with an estimated travel time of 25 minutes. The multi-source resource scheduling optimization algorithm schedules the enforcement team of the overweight vehicle control station, with an estimated arrival time of 20 minutes, a scheduling cost of 800 yuan, and a distance of 5km. Subsequently, the overweight violation tracing and matching algorithm traces and matches the data. Five samples in the historical data between 14:25 and 14:35 and within the range of K120+300m-K120+700m are all overweight data. The matching degree M is calculated to be 0.85 ≥ 0.7, indicating a successful match and confirmation of the violation.

[0086] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, the phrase "comprising an element defined as..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0087] The above technical solutions only embody the preferred technical solutions of the present invention. Any modifications that may be made by those skilled in the art to certain parts thereof embody the principles of the present invention and fall within the protection scope of the present invention.

Claims

1. A vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire chain of vehicle-mounted overloaded vehicles, characterized in that, It includes the vehicle terminal layer, roadside perception layer, cloud platform layer, and processing and execution layer; The vehicle-mounted terminal layer is equipped with a weighing sensor, a GPS positioning module, an IMU (Inertial Measurement Unit), and a vehicle-mounted communication module, which are used to collect real-time vehicle load data, location information, and driving status data. The roadside perception layer is equipped with radar, cameras, roadside weighing equipment and roadside communication units to collect auxiliary load data, road traffic environment data and vehicle trajectory data. The cloud platform layer integrates a data storage module, an algorithm operation module, and a decision scheduling module; The execution layer includes a roadside enforcement terminal, a vehicle braking assist module, and a road maintenance early warning module. The execution layer receives instructions from the cloud platform layer through the V2X communication protocol and executes enforcement actions, vehicle driving interventions, and road maintenance early warnings in real time. The algorithm operation module has built-in vehicle dynamic load fusion detection algorithm, overload risk level quantitative assessment algorithm, vehicle-road cooperative overload verification algorithm, overload vehicle optimal disposal path planning algorithm, multi-source disposal resource scheduling optimization algorithm, and overload violation tracing and matching algorithm.

2. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 2, characterized in that, The vehicle-mounted dynamic load fusion detection algorithm is based on the fusion of data from multiple vehicle sensors to achieve accurate detection of vehicle load during dynamic driving. The formula is as follows: ； in, The actual load of the merged vehicle is expressed in tons (t). The weighting coefficients for each sensor data are used when the weighing sensor accuracy is <0.5%. The initial value is 0.6; when the IMU precision is <0.1g, The initial value is 0.15; when the no-load reference load error is >5%, The initial value was set to 0.05; all initial values ​​were within the optimization range. Subsequent adjustments were made using vehicle driving history data combined with an adaptive genetic algorithm for iterative calibration, ultimately satisfying the desired result. + + =1 Real-time load data collected by the vehicle-mounted weighing sensor, in tons (t). The load data is derived from inertial measurement unit data, in tons (t), and its derivation formula is as follows: , The longitudinal inertial force detected by the IMU, in N. The longitudinal acceleration of the vehicle is expressed in m / s², and g is the acceleration due to gravity, taken as 9.8 m / s². The unloaded baseline load of the vehicle is determined by the vehicle's factory parameters and is measured in tons (t).

3. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 2, characterized in that, The algorithm for quantitatively assessing the risk level of overloaded vehicles is based on fused load data, vehicle driving status, and road environment parameters. It quantifies the safety risk level of overloaded vehicles using the following formula: ； in, The overall risk level for overweight is 0 to 10, with 0 indicating no risk and 10 indicating extremely high risk. , , The weights of each risk factor satisfy the following conditions: ; The overload risk factor ranges from 0 to 10, and the calculation formula is as follows: , The approved load capacity of a vehicle is measured in tons (t). The vehicle driving status risk factor has a value range of 0 to 10, and the calculation formula is as follows: , The actual speed of the vehicle. The current speed limit for this section of road is in km / h. The longitudinal acceleration for vehicle safety is set at 2.5 m / s². The road environmental risk factor has a value range of 0 to 10, and the calculation formula is as follows: , For the quantity of environmental factors, For the first The weighting coefficients of various environmental factors are preset, with weighting coefficients for 6 categories of environmental factors. The total is 10, which is the weighting coefficient of the single factor. Based on risk level: Snowy weather Foggy days ,rain Construction area School section ,at night When multiple environmental factors are present, For each The sum, with a maximum value of 10, For environmental factors, state variables, when this environmental factor exists ,otherwise .

4. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 2, characterized in that, The vehicle-road cooperative overweight verification algorithm integrates on-board terminal detection data and roadside perception data to perform secondary verification of the overweight state. The formula is as follows: ； in, For the overweight verification results, This indicates that the weight is confirmed to be overweight. This indicates that you are not overweight. The absolute value is the overweight percentage, that is... , hour, This represents the actual percentage of overweight individuals. At that time, it represents the proportion of those who were not overweight or whose test data deviated. This is a sign function; it returns 1 for a positive input, -1 for a negative input, and 0 for a zero input. The weights for roadside data range from 0.3 to 0.

5. The actual load capacity of the merged vehicle. The rated load capacity of the vehicle is expressed in tons (t). Vehicle load data collected by roadside weighing equipment, in tons (t).

5. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 2, characterized in that, The optimal handling path planning algorithm for overweight vehicles plans a handling path for confirmed overweight vehicles, taking into account real-time road conditions, the location of overweight vehicle control stations, and road restrictions. The formula is as follows: ； in, This is the optimal handling path; For the set of all feasible disposal paths; For path The estimated travel time, in minutes, is calculated using the following formula: , For path The total length, in km. The path element is a infinitesimal element, with units of km. For path infinitesimal elements Real-time driving speed at the location, in km / h; For path The total length, in km; For path The safety risk coefficient, ranging from 0 to 1, is calculated using the following formula: ， For path The number of curves on the road For path The length, in km. For path The elevation difference, in kilometers. For path Average traffic flow The saturation traffic volume for the road segment is expressed in vehicles per hour. , These are the weighting coefficients, and , .

6. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 2, characterized in that, The multi-source disposal resource scheduling optimization algorithm optimizes disposal resources and improves disposal efficiency based on the location, risk level, and enforcement resource status of each overload control station. The formula is as follows: ； in, Resources to be optimally scheduled; A collection of available disposal resources; To dispose of resources Arrival of overweight vehicles Estimated time at location, in minutes; To dispose of resources The scheduling cost, in yuan, includes labor costs and equipment depreciation costs. To dispose of resources Overweight vehicles The straight-line distance, in km; The overall risk level of overweight vehicles; , , These are the weighting coefficients, and =0.4, =0.3, =0.3, With a base weight of 0.3, when the risk level... When the weighting coefficients are adjusted, the following is true: 。 7. A vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire chain of vehicle-mounted overloaded vehicles, as described in claim 2, is characterized in that... The algorithm for tracing and matching overweight violations combines historical vehicle driving data, load data, roadside sensing records, and violation information stored in the cloud to achieve accurate tracing and matching of overweight violations. The formula is as follows: ； in, To track the matching degree, the value ranges from 0 to 1. The match is considered successful at that time. The number of historical data samples to be matched; For the first The fused load data of historical samples, in tons; This is the overweight determination function; when the input is >0... ,otherwise ; The time matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The collection time of each historical sample, The time of the suspected illegal activity The time matching threshold is set to 30 minutes. The position matching coefficient ranges from 0 to 1, and is calculated using the following formula: , For the first The vehicle location plane coordinates of each historical sample are Gauss-Kruger projection coordinates, in km. The location coordinates of the suspected illegal activity are Gauss-Kruger projection coordinates, with units of km, and Euclidean distance is used for distance calculation. The location matching threshold is set to 1km. The rated load capacity of a vehicle is specified in tons (t).

8. The vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire vehicle-mounted overload chain according to claim 1, characterized in that, The vehicle terminal layer, roadside perception layer, cloud platform layer, and processing execution layer achieve real-time data transmission through V2X, the vehicle-to-everything (V2X) communication protocol.

9. A vehicle-road-cloud collaborative intelligent monitoring and handling system for the entire chain of vehicle-mounted overloaded vehicles, as described in claim 1, is characterized in that... The workflow of the vehicle-road-cloud collaborative intelligent monitoring and handling system for overloaded vehicles includes the following steps: S1. Data Acquisition: The vehicle terminal layer and the roadside perception layer respectively collect corresponding data and upload them to the cloud platform layer; S2. Overload Detection: The cloud platform layer calculates the fused load through the vehicle dynamic load fusion detection algorithm to preliminarily determine whether it is overloaded; S3. Secondary verification: The cloud platform layer integrates roadside load data through the vehicle-road cooperative overload verification algorithm to confirm the overload status; S4. Risk Assessment: The cloud platform layer assesses the overall risk level of overweight through a quantitative assessment algorithm for overweight risk levels. S5. Path planning and resource scheduling: The cloud platform layer plans the disposal path through the optimal disposal path planning algorithm for overweight vehicles and schedules disposal resources through the multi-source disposal resource scheduling optimization algorithm. S6. Enforcement and Traceability: The enforcement layer executes enforcement operations, while the cloud platform layer uses an algorithm to trace and match serious violations, thus forming a regulatory closed loop.

Images