A method, device and medium for road network axle load identification based on crowd sensing

Abstract

The application relates to a crowd-sensing-based road network axle load identification method, device and medium. Based on crowd sensing, sensor is used to collect dynamic response data, and the dynamic response data is sent to a controller for road network axle load identification. The controller repeatedly performs the following steps until all unknown road surface structure parameter road sections and unknown axle load vehicles are calibrated: first dynamic response data caused by a known axle load vehicle to an unknown road surface structure parameter road section is acquired; road surface structure parameters of the unknown road surface structure parameter road section are calibrated based on the first dynamic response data, and a mapping relationship between vehicle axle load and dynamic response is acquired; second dynamic response data caused by an unknown axle load vehicle to a road section with calibrated road surface structure parameters is acquired, and the axle load of the unknown axle load vehicle is calibrated based on the second dynamic response data and the mapping relationship. The device and the medium are used to realize the above method. Compared with the prior art, the application improves the calculation efficiency and the stability and reliability of axle load identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of road engineering, in particular to a road network axle load identification method, device and medium based on crowd sensing. BACKGROUND

[0002] Accurate identification and monitoring of vehicle axle load is crucial for the maintenance and management of road engineering. Traditional axle load monitoring methods rely on manual measurement or fixed weighing equipment, which has problems such as high cost, low efficiency, limited data coverage, etc. In existing technologies, the monitoring of road surface axle load usually adopts static weighing or methods based on pressure sensors. These methods have limitations in practical application. Static weighing equipment cannot provide continuous monitoring data, while methods based on pressure sensors may result in inaccurate data due to sensor accuracy and durability issues. In addition, these methods often require installation of equipment at specific locations, which cannot achieve comprehensive monitoring of the entire road network.

[0003] In the field of axle load identification, there are already a large number of freight vehicles with known axle loads in the existing road network. Therefore, by quickly deploying road surface structure dynamic response sensing nodes in the road network, parameter estimation and calibration can be achieved through vehicle-road interaction, which can realize road network level axle load identification. However, the accuracy and reliability of similar methods in axle load identification still need to be improved. In particular, in complex and variable road network environments, how to accurately identify vehicle axle load and update road surface structure parameters in real time is a problem that needs to be solved in the current technical field. SUMMARY

[0004] The purpose of the present application is to overcome the defects of the prior art and provide a road network axle load identification method, device and medium based on crowd sensing.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] With the development of Internet of Things technology, crowd sensing as a new data collection method provides new possibilities for road axle load monitoring. The core of crowd sensing is to utilize a large number of dispersed sensor networks and achieve perception and analysis of core elements through spontaneous organization and interaction between sensors. In the field of axle load identification, there are already a large number of freight vehicles with known axle loads in the existing road network. Therefore, by quickly deploying road surface structure dynamic response sensing nodes in the road network, parameter estimation and calibration can be achieved through vehicle-road interaction, which can realize road network level axle load identification.

[0007] Based on this, the application provides a road network axle load identification method based on crowd sensing, which is based on crowd sensing, uses sensors to collect dynamic response data, and sends the dynamic response data to a controller for road network axle load identification, and the controller repeatedly performs the following steps until all unknown road surface structure parameter road sections and unknown axle load vehicles are calibrated:

[0008] Obtain first dynamic response data caused by a known axle load vehicle on an unknown road surface structure parameter road section;

[0009] Calibrate the road surface structure parameters of the unknown road surface structure parameter road section based on the first dynamic response data, and obtain a mapping relationship between the vehicle axle load and the dynamic response;

[0010] Obtain second dynamic response data caused by an unknown axle load vehicle on a calibrated known road surface structure parameter road section, and calibrate the axle load of the unknown axle load vehicle based on the second dynamic response data and the mapping relationship.

[0011] As a preferred technical solution, the method for obtaining the first dynamic response data is:

[0012] Obtain the position information of the sensor and the dynamic response data, and obtain the trajectory information of the known axle load vehicle within the preset sensing range of the sensor based on the position information;

[0013] Obtain the time period when the vehicle passes through the sensor based on the trajectory information, and extract first intermediate data in the dynamic response data that meets the time period;

[0014] Continuously calculate and adjust the first intermediate data until the number of wave crests of the first intermediate data is equal to the number of axles of the known axle load vehicle, and obtain second intermediate data;

[0015] Cut off the data in the preset range in the second intermediate data, and the data is the first dynamic response data.

[0016] As a preferred technical solution, the method for calculating and adjusting is to calculate the first intermediate data by using a short-time energy calculation method, and continuously adjust the calculation time window of the short-time energy.

[0017] As a preferred technical solution, the preset range refers to the starting point of the first wave crest to the end point of the last wave crest.

[0018] As a preferred technical solution, the method for calibrating the road surface structure parameters of the unknown road surface structure parameter road section is:

[0019] Construct a response data set based on the first dynamic response data, and construct an axle load feature set corresponding to the response data set based on the axle load data of the known axle load vehicle;

[0020] extract a spectrum distribution based on the response data set, and generate a real spectrum distribution feature data set based on the spectrum distribution;

[0021] obtain design data of a road section with unknown pavement structure parameters, construct an initial model of a multi-layer pavement structure based on the design data, and determine an initial value of a vector of to-be-determined structure parameters;

[0022] based on the axle load feature set, the real spectrum distribution feature data set, and the vector of to-be-determined structure parameters, repeatedly perform the following steps:

[0023] based on the vector of to-be-determined structure parameters, obtain upper and lower bounds of the pavement structure parameters, and randomly generate a batch of vectors of to-be-determined structure parameters based on the upper and lower bounds;

[0024] construct a finite element model of the multi-layer pavement structure based on the batch of vectors of to-be-determined structure parameters, input the axle load feature set into the finite element model, and calculate the dynamic response parameters;

[0025] extract to-be-determined spectrum distribution features based on the dynamic response parameters;

[0026] calculate errors between the to-be-determined spectrum distribution features and the real spectrum distribution features, and if the errors corresponding to the batch of vectors of to-be-determined structure parameters all satisfy a preset error threshold, select a vector of to-be-determined structure parameters corresponding to a minimum error as the pavement structure parameters;

[0027] if any of the errors corresponding to the batch of vectors of to-be-determined structure parameters does not satisfy the preset error threshold, select vectors of to-be-determined structure parameters corresponding to a second minimum error and a third minimum error as upper and lower bounds of a next batch of vectors of to-be-determined structure parameters.

[0028] As a preferred technical solution, the method for obtaining the mapping relationship between the vehicle axle load and the dynamic response is:

[0029] calculate third dynamic response data based on the calibrated pavement structure parameters and the corresponding finite element model;

[0030] extract a first vibration energy of a specified frequency band of the third dynamic response data, and solve a relationship between the vibration energy and the vehicle axle load by using a regression fitting method based on the first vibration energy.

[0031] As a preferred technical solution, the method for calibrating the axle load of the unknown axle load vehicle is:

[0032] obtain a mapping relationship between vehicle axle loads and vibration energies in road sections with a plurality of calibrated pavement structure parameters;

[0033] acquire second dynamic response data of the unknown axle load vehicle on each road section with a calibrated road structure parameter, and extract second vibration energy at a corresponding frequency band of the first vibration energy frequency band in each second dynamic response data;

[0034] estimate the axle load of the unknown axle load vehicle based on the second vibration energy and a corresponding mapping relationship, to obtain an axle load estimation value of the unknown axle load vehicle on multiple road sections with calibrated road structure parameters;

[0035] fit multiple axle load estimation values to obtain an expected value, which is the final axle load data.

[0036] As a preferred technical solution, the controller further performs the following steps:

[0037] select multiple calibrated road structure parameters and vehicle axle load parameters, respectively fit them using Gaussian distribution, and calculate the variance according to the fitting result, if the variance meets a preset threshold, it is considered that the calibration is reliable;

[0038] if the variance does not meet the preset threshold, it is considered that the calibration is unreliable and the road structure parameter and vehicle axle load calibration need to be performed again.

[0039] According to a second aspect of the present application, an electronic device for road network axle load identification is provided, comprising a memory and a processor, the memory stores a computer program, and the processor executes the program to realize the above method.

[0040] According to a third aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to realize the above method.

[0041] Compared with the prior art, the present application has the following advantages:

[0042] 1) The present application uses crowd-sensing method to realize rapid calibration of road structure parameters, fully utilizes the interaction between vehicles and roads in the road network, realizes rapid estimation of large-scale road network axle load, and completes comprehensive detection of the entire road network without installing equipment in specific places, which not only improves the estimation efficiency of road network axle load, but also solves the problems of high cost and time-consuming of traditional methods;

[0043] 2) The present application proposes a semi-supervised learning type vehicle-road cyclic calibration method, which reduces the error in the process of single estimation of road structure parameter calibration and vehicle axle load through continuous iteration calculation, improves the estimation accuracy, and fully utilizes the interaction between vehicles and roads to realize autonomous calibration of vehicle axle load and road structure parameters, and improves the stability and reliability of road network axle load identification. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 A crowd-sensing diagram of the present application;

[0045] Figure 2 A vehicle-road autonomous calibration diagram of the present application;

[0046] Figure 3 A method flowchart of the present application. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0048] Unless otherwise defined, technical terms or scientific terms used in the present application should be understood as the common meanings thereof by those skilled in the art. The terms “a”, “an”, “one”, “this” and like terms used in the present application do not denote a quantity limitation, but can represent a single or multiple. The terms “include”, “contain”, “have” and any variations thereof used in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device including a series of steps or modules (units) is not limited to the listed steps or units, but can further include steps or units not listed or can further include other steps or units inherent to the process, method, product or device. The terms “connect”, “connect to”, “couple” and like terms used in the present application are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The term “multiple” in the present application refers to two or more. The term “and / or” describes the association relationship of the associated objects, which means that there can be three relationships, for example, “A and / or B” can represent the three cases of A alone, A and B together, and B alone. The character “ / ” generally represents an “or” relationship between the associated objects. The terms “first”, “second”, “third” and the like in the present application are only to distinguish similar objects, and do not represent a specific order of the objects.

[0049] Embodiment 1

[0050] The embodiment provides a road network axle load identification method based on crowd-sensing. The method is based on crowd-sensing, uses multiple embedded sensors buried in a target road network to collect dynamic response data, and sends the data to a controller in a semi-supervised learning manner of vehicle-road interaction, to realize vehicle axle load and road network structure parameter calibration of the whole road network. Specifically, the embodiment realizes the vehicle axle load and road network structure parameter calibration of the whole road network by Figure 1The structure shown enables crowd sensing. The detailed steps of this method include:

[0051] Within the highway network, 100 road sections were selected and corresponding sensors were installed. The sensors were vibration sensors with a sampling frequency of 100Hz embedded in the road structure layer to obtain the dynamic response of vehicles under axle load excitation in real time.

[0052] Define the vehicle set V with known axle loads based on the actual road network conditions. load Road set R with known pavement structure parameters modulus Vehicle set U with unknown axle load parameters v-load Road set U with unknown pavement structure parameters r-modulus The vehicle set U with unknown axle load parameters v-load Road set U with unknown pavement structure parameters r-modulus It can be dynamically expanded based on actual road network data.

[0053] Define the set of roads R for vehicles traveling on unknown roads. sample ={R1,R2,......,R n The set of vehicles V, including unknown vehicles, passing through known roads. sample ={V1,V2,......,V i}, where R n V indicates that the nth unknown road has been traversed by known vehicles. i This indicates that the i-th vehicle with an unknown axle load passes through a road with known pavement structure parameters, when the set R... sample The number of samples exceeds the preset value T1 = 15 and the set V sample When the number of samples exceeds the preset value T2 = 10, proceed as follows: Figure 2 The loop calibration architecture shown executes as follows: Figure 3 The flowchart shown illustrates the method until all Us are reached. r-modulus All samples were calibrated and transferred to R modulus The detailed steps are as follows:

[0054] S1. Obtain the first dynamic response data of a vehicle with known axle load to a road section with unknown road structure parameters.

[0055] S11. Based on the BeiDou / GPS information of the embedded sensor's location, set the maximum acquisition range to 10m, filter out the vehicle trajectory information passing through the sensor, and extract the dynamic response data.

[0056] S12. Based on the trajectory information, the time period when the vehicle passes the sensor is extracted, the data that matches the time period is extracted from the dynamic response data, and the dynamic response data of the vehicle acting on the corresponding sensor is further filtered out as the first intermediate data according to the distribution of the signal peak.

[0057] S13, performing a short-time energy calculation on the first intermediate data and adjusting a short-time energy calculation time window until a number of wave peaks of the first intermediate data equals a number of axles of the known axle load vehicle, to obtain second intermediate data.

[0058] S14, intercepting data between a start point of a first signal wave peak and an end point of a last signal wave peak in the second intermediate data, and the data is the first dynamic response data.

[0059] S2, calibrating a road surface structure parameter of the unknown road surface structure parameter section based on the first dynamic response data, and obtaining a mapping relationship between the vehicle axle load and the dynamic response.

[0060] S21, calibrating the road surface structure parameter of the unknown road surface structure parameter section.

[0061] When the number of vehicles passing through a road with an unknown road surface structure parameter reaches 15, the road surface structure parameter is calibrated, and the road with the calibrated road surface structure parameter is put into a set R sample and a corresponding road surface structure parameter sample set R sample is constructed. cal The detailed steps are as follows:

[0062] S211, constructing a response data set R based on the first dynamic response data, and constructing an axle load feature set L corresponding to the response data set based on the axle load data of the known axle load vehicle.

[0063] S212, extracting a frequency spectrum distribution of each response data in the response data set R based on the response data set R, and generating a real frequency spectrum distribution feature data set R f based on the frequency spectrum distribution.

[0064] S213, obtaining design data of the unknown road surface structure parameter section, constructing an initial model of a multi-layer road surface structure based on the design data, and determining an initial value P0 of an undetermined structure parameter vector, P0=[E 01 ,E 02 ,……,E 0m ], wherein E 01 ,E 02 ,……,E 0m represent initial values of parameters of the first to mth structure layers, and are all elastic moduli.

[0065] S214, repeatedly executing the following steps based on the axle load feature set, the real frequency spectrum distribution feature data set, and the undetermined structure parameter vector:

[0066] A1, obtaining upper and lower bounds of the road surface structure parameter based on the undetermined structure parameter vector, and randomly generating a batch of undetermined structure parameter vectors [P1, P2, P3, …, P x ] based on the upper and lower bounds.

[0067] A2, construct a finite element model of the multi-layer pavement structure based on the batch of undetermined structure parameter vectors, take the axle load feature set L as the input of the finite element model, and calculate the dynamic response parameters.

[0068] A3, extract the undetermined spectral distribution features based on the dynamic response parameters.

[0069] A4, calculate the error of the undetermined spectral distribution features and the real spectral distribution features, if any of the errors corresponding to the batch of undetermined structure parameter vectors does not satisfy the preset error threshold, select the undetermined structure parameter vectors corresponding to the second smallest and third smallest error values as the upper and lower bounds of the next batch of undetermined structure parameter vectors to generate the next batch of undetermined structure parameter vectors for feedback optimization, the process of feedback optimization can adopt one or more of particle swarm optimization algorithm and genetic algorithm; if the errors corresponding to the batch of undetermined structure parameter vectors all satisfy the preset error threshold, select the undetermined structure parameter vector corresponding to the smallest error as the pavement structure parameter, and put the calibrated pavement structure parameter into R cal .

[0070] S22, obtain the mapping relationship between the vehicle axle load and the dynamic response.

[0071] S221, calculate the third dynamic response data based on the calibrated pavement structure parameter using the corresponding finite element model.

[0072] S222, extract the vibration energy of the third dynamic response data in the frequency range of 0.5-20Hz, and solve the relationship between the vibration energy and the vehicle axle load based on the vibration energy using methods such as linear fitting and polynomial fitting.

[0073] S3, obtain the second dynamic response data caused by the unknown axle load vehicle to the road section with calibrated pavement structure parameters, and calibrate the axle load of the unknown axle load vehicle based on the second dynamic response data and the mapping relationship.

[0074] When a certain unknown axle load vehicle passes through more than 10 road sections with calibrated pavement structure parameters, the vehicle axle load is calibrated, and after the calibration, the vehicle is put into the set V sample and a vehicle axle load set V sample corresponding to V cal is constructed, the detailed steps are as follows:

[0075] S31, obtain the mapping relationship between the vehicle axle load and the vibration energy in the road sections with multiple calibrated pavement structure parameters.

[0076] S32, obtain the second dynamic response data of the unknown axle load vehicle in each road section with calibrated pavement structure parameters, and extract the vibration energy in the frequency range of 0.5-20Hz in each second dynamic response data.

[0077] S33, estimating the axle load of the unknown axle load vehicle based on the vibration energy and the corresponding mapping relationship to obtain an axle load estimation value of the unknown axle load vehicle in the road section with the plurality of calibrated road structure parameters.

[0078] S34, performing normal distribution fitting on the plurality of axle load estimation values, taking the expected value obtained by fitting as the final axle load data, and putting it into set V cal .

[0079] S4, selecting a plurality of calibrated road structure parameters and vehicle axle load parameters from sets R cal and V cal , fitting them with Gaussian distribution respectively and calculating the variance according to the fitting results, if the variance meets the preset threshold, it is considered that the calibration is reliable, and the road and vehicle corresponding to the calibrated road structure parameters and vehicle axle load parameters can be transferred from unknown sets U v-load and U r-modulus to V load and R modulus ; if the variance does not meet the preset threshold, it is considered that the calibration is unreliable, and the road and vehicle corresponding to the calibrated road structure parameters and vehicle axle load parameters need to be re-calibrated for road structure and vehicle axle load.

[0080] Embodiment 2

[0081] The above is the introduction of the method embodiment, and the following will further illustrate the scheme of the application through the device embodiment. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process described can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0082] The embodiment provides an electronic device for road network axle load identification, which comprises a central processing unit (CPU) which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded into a random access memory (RAM) from a storage unit. In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0083] A plurality of components in the device are connected to the I / O interface, including: an input unit such as a keyboard, a mouse, etc.; an output unit such as various types of displays, speakers, etc.; a storage unit such as a magnetic disk, an optical disk, etc.; and a communication unit such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunications networks.

[0084] The processing units perform the various methods and processes described above, such as methods S1-S4 and A1-A4. For example, in some embodiments, methods S1-S4 and A1-A4 can be implemented as a computer software program tangibly embodied in a machine readable medium, such as a storage unit. In some embodiments, portions or all of the computer program can be loaded and / or installed onto the device via the ROM and / or the communication unit. When the computer program is loaded onto the RAM and executed by the CPU, one or more of the steps of methods S1-S4 and A1-A4 described above can be performed. Alternatively, in other embodiments, the CPU can be configured to perform methods S1-S4 and A1-A4 by way of other suitable means, such as by way of firmware.

[0085] The functionality described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0086] Program code for carrying out methods of the present application can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be retrieved from a machine-readable medium or device, a storage medium, a memory medium, a tangible medium, or a non-transitory medium. The program code can be executed by a machine, such as a computer, which can be hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. A machine-readable medium or device can be any medium or device that can tangibly contain or store program code for execution by the machine to produce a machine implemented process. The machine readable media can include, but is not limited to, one or more types of tangible, non-transitory storage media or devices that are tangible. A machine readable medium can include, by way of example, a storage device, a memory device, or a combination thereof.

[0087] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store program code for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more types of tangible, non-transitory storage media or devices that are tangible. Examples of the machine-readable storage medium will include, but are not limited to, one or more types of tangible, non-transitory storage media or devices that are tangible. Examples of the machine-readable storage medium will include, but are not limited to, one or more types of tangible, non-transitory storage media or devices that are tangible. Examples of the machine-readable storage medium will include, but are not limited to, one or more types of tangible, non-transitory storage media or devices that are tangible.

[0088] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements shall be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for identifying road network axle load based on crowd sensing, characterized in that, The method is based on crowd sensing, utilizes sensors to collect dynamic response data, and sends the dynamic response data to a controller for road network axle load identification, and the controller repeatedly performs the following steps until all unknown road surface structure parameter road sections and unknown axle load vehicles are calibrated: Obtain first dynamic response data caused by a known axle load vehicle on an unknown road surface structure parameter road section; Calibrate road surface structure parameters of the unknown road surface structure parameter road section based on the first dynamic response data, and obtain a mapping relationship between vehicle axle load and dynamic response; Obtain second dynamic response data caused by an unknown axle load vehicle on a road section with calibrated road surface structure parameters, and calibrate the axle load of the unknown axle load vehicle based on the second dynamic response data and the mapping relationship. The method for calibrating road surface structure parameters of the unknown road surface structure parameter road section is as follows: Based on the first dynamic response data, a response data set is constructed, and an axle load feature set corresponding to the response data set is constructed based on axle load data of the known axle load vehicle; Based on the response data set, a frequency spectrum distribution is extracted, and a real frequency spectrum distribution feature data set is generated based on the frequency spectrum distribution; Obtain design data of the unknown road surface structure parameter road section, construct an initial model of a multi-layer road surface structure based on the design data, and determine an initial value of an undetermined structure parameter vector; Based on the axle load feature set, the real frequency spectrum distribution feature data set, and the undetermined structure parameter vector, the following steps are repeatedly performed: Based on the undetermined structure parameter vector, upper and lower bounds of the road surface structure parameters are obtained, and a batch of undetermined structure parameter vectors are randomly generated based on the upper and lower bounds; Based on the batch of undetermined structure parameter vectors, finite element models of the multi-layer road surface structure are constructed, the axle load feature set is taken as an input of the finite element models, and dynamic response parameters are calculated; Based on the dynamic response parameters, undetermined frequency spectrum distribution features are extracted; Errors between the undetermined frequency spectrum distribution features and real frequency spectrum distribution features are calculated, if the errors corresponding to the batch of undetermined structure parameter vectors all satisfy a preset error threshold, an undetermined structure parameter vector corresponding to a minimum error is selected as a road surface structure parameter; If any of the errors corresponding to the batch of undetermined structure parameter vectors does not satisfy the preset error threshold, undetermined structure parameter vectors corresponding to a second smallest error and a third smallest error are selected as upper and lower bounds of a next batch of undetermined structure parameter vectors.

2. The method according to claim 1, wherein, The method for obtaining the first dynamic response data is as follows: Position information and dynamic response data of the sensor are obtained, and trajectory information of the known axle load vehicle within a preset sensing range of the sensor is obtained based on the position information; A time period when the vehicle passes the sensor is obtained based on the trajectory information, and first intermediate data in the dynamic response data that meets the time period is extracted; The first intermediate data is continuously calculated and adjusted until a number of wave crests of the first intermediate data is equal to a number of axles of the known axle load vehicle, and second intermediate data is obtained; Data within a preset range of the second intermediate data is intercepted, and the data is the first dynamic response data.

3. The method according to claim 2, wherein, The method for calculation and adjustment is that the first intermediate data is calculated by using a short-time energy calculation method, and a calculation time window of the short-time energy is continuously adjusted.

4. The method according to claim 2, wherein, The preset range refers to the start point of the first wave peak to the end point of the last wave peak.

5. The method according to claim 1, wherein, The method for obtaining the mapping relationship between the vehicle axle load and the dynamic response is: Based on the calibrated road surface structure parameters, the third dynamic response data is calculated by using the corresponding finite element model; The first vibration energy of the specified frequency band of the third dynamic response data is extracted, and the relationship between the vibration energy and the vehicle axle load is solved by using a regression fitting method based on the first vibration energy.

6. The method according to claim 1, wherein, The method for calibrating the axle load of the unknown axle load vehicle is: Obtain the mapping relationship between the vehicle axle load and the vibration energy in the road section with multiple calibrated road surface structure parameters; Obtain the second dynamic response data of the unknown axle load vehicle in the road section with each calibrated road surface structure parameter, and extract the second vibration energy at the corresponding frequency band of the first vibration energy frequency band in each second dynamic response data; Based on the second vibration energy, the axle load of the unknown axle load vehicle is estimated by using the corresponding mapping relationship, and the axle load estimation value of the unknown axle load vehicle in the road section with multiple calibrated road surface structure parameters is obtained; Fit multiple axle load estimation values to obtain an expected value, and the expected value is the final axle load data.

7. The method according to claim 1, wherein, The controller further performs the following steps: Select multiple calibrated road surface structure parameters and vehicle axle load parameters, respectively fit them by using Gaussian distribution, and calculate the variance according to the fitting results. If the variance meets the preset threshold, it is considered that the calibration is reliable. If the variance does not meet the preset threshold, it is considered that the calibration is unreliable and the road surface structure parameter and vehicle axle load calibration need to be performed again.

8. An electronic device for axle load discrimination of a road network, comprising a memory and a processor, wherein a computer program is stored on the memory, characterized in that, The processor executes the program to realize the method in any one of claims 1-7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the method in any one of claims 1-7. The program is executed by the processor to realize the method in any one of claims 1-7.

Images