Road performance digital characterization method and system based on quasi-distributed axle load data

Abstract

The invention discloses a road performance digital characterization method and system based on quasi-distributed axle load data, and relates to the technical field of road engineering, traffic information technology and big data analysis. Multi-dimensional fusion data is formed according to acquired quasi-distributed axle load data and building and maintenance data of road infrastructures and meteorological environment data; selecting performance influence factor data from the data; for each monitoring point, inputting the performance influence factor data into a pre-trained road performance evaluation model to obtain a road performance index estimation value of the current monitoring point at the current moment; an improved spatial interpolation method is adopted, road geographic positions, traffic characteristics and meteorological environment factors are combined, and a road performance index estimated value of each non-monitoring point is obtained through calculation; and according to the estimated value, generating a dynamic thermodynamic diagram for digitally representing the road performance, and marking suggested maintenance prompts. According to the invention, real-time and accurate evaluation of the road performance and digital representation and visual display of the road performance can be realized.

Description

Technical Field

[0001] The present invention relates to the fields of road engineering, traffic information technology and big data analysis technology, and in particular to a method and system for digitally characterizing road performance based on quasi-distributed axle load data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the continuous growth of traffic volume and the prevalence of overloading, road infrastructure is facing tremendous pressure. Evaluating the performance of road infrastructure and repairing roads in a timely manner based on the evaluation results is one of the important measures to ensure the service life of roads, reduce road damage, and reduce the risk of traffic accidents. At present, traditional road performance evaluation methods mainly rely on periodic manual inspections and empirical judgments, which have problems such as low detection frequency, poor real-time performance, low accuracy, and high cost.

[0004] In recent years, with the development of sensor technology and the Internet of Things, it has become possible to deploy a large number of axle load monitoring points on the road. By continuously collecting vehicle axle load data at these monitoring points, a valuable data basis is provided for the timely, efficient and accurate evaluation of road performance. However, the existing road performance evaluation methods still have the following defects when processing the quasi-distributed axle load data obtained above: (1) Insufficient fusion of multi-source data: It is impossible to effectively integrate axle load data with road-related data (such as construction and maintenance data), performance index test data and other multi-source heterogeneous data, making it difficult to timely and comprehensively reflect the actual performance status of the road; (2) Imperfect spatial interpolation methods: Considering that quasi-distributed monitoring points cannot effectively cover the entire road, there is a lack of accurate spatial interpolation methods for road performance between monitoring points, resulting in insufficient accuracy and comprehensiveness in performance evaluation of unmonitored points or unmonitored road sections; (3) Limited digital representation methods: There is a lack of dynamic and intuitive digital representation methods for road performance, making it difficult to effectively display the spatial distribution and temporal changes of road performance. Summary of the invention

[0005] In order to address the deficiencies of the above-mentioned prior art, the present invention provides a method and system for digitally characterizing road performance based on quasi-distributed axle load data, which realizes real-time and accurate evaluation of road performance through effective multi-source data deep fusion strategy, improved spatial interpolation algorithm and dynamic heat map display, and realizes accurate and effective digital characterization and visualization of road performance.

[0006] In a first aspect, the present invention provides a method for digitally characterizing road performance based on quasi-distributed axle load data.

[0007] A road performance digital characterization method based on quasi-distributed axle load data, comprising: Acquire the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment, as well as the meteorological environment data of the area where the road infrastructure is located; the quasi-distributed axle load data includes the axle load size and the number of times of action at each monitoring point; Preprocess the acquired data to obtain multi-dimensional fusion data of each monitoring point, and select performance influencing factor data from them; For each monitoring point, the performance influencing factor data is input into the pre-trained road performance evaluation model to obtain the estimated value of the road performance index of the current monitoring point at the current moment; Based on the estimated value of the road performance index at each monitoring point at the current moment, the improved spatial interpolation method is used to combine the geographical location, traffic characteristics and meteorological environmental factors of the road to calculate the estimated value of the road performance index at each non-monitoring point; Based on the estimated values ​​of road performance indicators at each point on the road, a dynamic heat map that digitally represents road performance is generated, and recommended maintenance tips are marked.

[0008] A further technical solution is to calculate the estimated road performance index of each non-monitoring point based on the estimated road performance index of each monitoring point at the current moment, using an improved spatial interpolation method, combined with the geographical location, traffic characteristics and meteorological environmental factors of the road, including: For each non-monitoring point to be estimated, traffic characteristic data, meteorological environmental factor data and spatial distance between the non-monitoring point and each monitoring point are obtained; wherein the traffic characteristics include traffic volume, and the meteorological environmental factors include temperature and humidity; According to the acquired data, combined with the preset adjustment parameters, the spatial distance weight, traffic characteristic weight, and meteorological environment factor weight of each monitoring point relative to the non-monitoring point are calculated respectively, and then the comprehensive weight is calculated; the adjustment parameters include the distance attenuation index, the traffic adjustment parameter, and the meteorological environment adjustment parameter; Based on the estimated value of the road performance index of each monitoring point at the current moment and the comprehensive weight, the estimated value of the road performance index of the non-monitoring point at the current moment is calculated.

[0009] In a second aspect, the present invention provides a road performance digital characterization system based on quasi-distributed axle load data.

[0010] A road performance digital characterization system based on quasi-distributed axle load data, comprising: A data acquisition module is used to obtain the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment, as well as the meteorological environment data of the area where the road infrastructure is located; the quasi-distributed axle load data includes the axle load size and the number of times of action of each monitoring point; The data preprocessing module is used to preprocess the acquired data to obtain multi-dimensional fusion data of each monitoring point and select performance influencing factor data from it; The monitoring point performance evaluation module is used to input the performance influencing factor data into the pre-trained road performance evaluation model for each monitoring point to obtain the estimated value of the road performance index of the current monitoring point at the current moment; The non-monitoring point performance evaluation module is used to calculate the estimated road performance index value of each non-monitoring point based on the estimated road performance index value of each monitoring point at the current moment, using an improved spatial interpolation method, combined with the geographical location, traffic characteristics and meteorological environmental factors of the road; The digital characterization module is used to generate a dynamic heat map that digitally characterizes road performance based on the estimated values ​​of road performance indicators at each point on the road, and annotate recommended maintenance tips.

[0011] A further technical solution is to calculate the estimated road performance index of each non-monitoring point based on the estimated road performance index of each monitoring point at the current moment, using an improved spatial interpolation method, combined with the geographical location, traffic characteristics and meteorological environmental factors of the road, including: For each non-monitoring point to be estimated, traffic characteristic data, meteorological environmental factor data and spatial distance between the non-monitoring point and each monitoring point are obtained; wherein the traffic characteristics include traffic volume, and the meteorological environmental factors include temperature and humidity; According to the acquired data, combined with the preset adjustment parameters, the spatial distance weight, traffic characteristic weight, and meteorological environment factor weight of each monitoring point relative to the non-monitoring point are calculated respectively, and then the comprehensive weight is calculated; the adjustment parameters include the distance attenuation index, the traffic adjustment parameter, and the meteorological environment adjustment parameter; Based on the estimated value of the road performance index of each monitoring point at the current moment and the comprehensive weight, the estimated value of the road performance index of the non-monitoring point at the current moment is calculated.

[0012] In a third aspect, the present invention further provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing the above-mentioned method for digitally characterizing road performance based on quasi-distributed axle load data when executing the executable instructions stored in the memory.

[0013] In a fourth aspect, the present invention further provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-mentioned method for digital characterization of road performance based on quasi-distributed axle load data.

[0014] In a fifth aspect, the present invention also provides a computer program product, which includes executable instructions stored in a computer-readable storage medium; wherein, when the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned method for digital characterization of road performance based on quasi-distributed axle load data is implemented.

[0015] One or more of the above technical solutions have the following beneficial effects: 1. The present invention provides a method and system for digitally characterizing road performance based on quasi-distributed axle load data. The method and system adopt statistical analysis and machine learning to deeply integrate multi-source heterogeneous data such as axle load data, construction and maintenance data, and performance index detection data, and construct a relationship model between axle load and pavement performance. The improved spatial interpolation algorithm is used to evaluate the performance status and remaining life of road infrastructure in real time, accurately and comprehensively, and digitally characterize and visualize road performance through dynamic heat maps and other means. The above method has the advantages of in-depth data fusion, improved interpolation method, intuitive characterization method, strong real-time and adaptability, etc., and can be widely used in the field of road maintenance and management, providing a scientific basis for road maintenance and management.

[0016] 2. The present invention adopts an improved multi-source data fusion and spatial interpolation method to solve the shortcomings of traditional methods in processing quasi-distributed axle load data. In the improved spatial interpolation method, by introducing traffic characteristics and environmental factors on the basis of spatial position, the relationship between monitoring points and non-monitoring points is analyzed, which effectively improves the accuracy of performance estimation of unmonitored road sections; in addition, the introduction of dynamic heat maps makes the digital representation of road performance more intuitive and practical, which is convenient for further promotion and use.

[0017] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0019] Figure 1 It is a flow chart of the method for digitally characterizing road performance based on quasi-distributed axle load data according to an embodiment of the present invention; Figure 2 A dynamic heat map of road performance with maintenance suggestions and annotations generated in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] It should be noted that the following detailed descriptions are exemplary only, are intended to describe specific embodiments, are intended to provide further explanation of the present invention, and are not intended to limit exemplary embodiments according to the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art to which the present invention belongs. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0021] Embodiment 1 The present embodiment provides a method for digitally characterizing road performance based on quasi-distributed axle load data. First, considering that the evaluation of traditional road performance relies on periodic manual detection and empirical judgment, the detection cost is high and the evaluation cycle is long (usually annual), it is impossible to achieve high-frequency evaluation of road performance (such as evaluation in monthly or weekly cycles), and the evaluation accuracy is also low. For this reason, in the present embodiment, considering the cumulative damage effect of axle load data on the road pavement structure, combined with construction and maintenance data and detection data, statistical analysis and machine learning algorithms are used to build a performance evaluation model that characterizes the relationship between axle load and road performance. According to the multi-dimensional fusion data obtained in real time in the above steps, the performance evaluation model is used to achieve real-time and accurate evaluation of road performance, thereby achieving accurate and effective digital characterization and visualization of road performance.

[0022] Specifically, in this embodiment, a road performance evaluation model is first built based on multi-source fusion data of the road, and the road performance evaluation model is pre-trained using statistical analysis and machine learning algorithms, so that the pre-trained model can be used for high-frequency evaluation later. The pre-training process of the performance evaluation model includes: First, obtain the quasi-distributed axle load data, construction and maintenance data, and performance index detection data of the road infrastructure, as well as the meteorological environment data (including temperature, humidity, etc.) of the area where the road infrastructure is located.

[0023] Specifically, quasi-distributed monitoring points are set for road infrastructure (hereinafter referred to as roads), and an axle load sensor is set at each monitoring point. The sensor is used to monitor and collect corresponding axle load data, wherein the collected quasi-distributed axle load data includes the axle load size and the number of times of action at each monitoring point; at the same time, the construction and maintenance data of the road are obtained, including the pavement structure, pavement material type, construction year and maintenance history, etc.; data such as the pavement damage condition index (PCI), pavement ride quality index (RQI), pavement rutting depth index (RDI) and the like are detected and obtained manually or by using a multi-functional detection vehicle, and a comprehensive assessment of the technical condition of the highway is conducted based on the detection data to obtain a comprehensive score value of the pavement part, that is, the score value of the pavement technical condition index (PQI) specified in the current assessment standard, and the obtained PQI value is the performance indicator detection data finally obtained.

[0024] Furthermore, this embodiment uses PQI to evaluate the road surface technical condition. The PQI is a weighted sum of multiple detection data and can be expressed as: ; In the above formula, They respectively represent the weights of PCI, RQI, and RDI, and the weights can be determined according to existing specifications.

[0025] Secondly, the acquired data is preprocessed, and the preprocessed data is deeply fused according to the spatial position and time dimensions to form the historical multidimensional fusion data of each monitoring point, construct a historical multidimensional fusion data set, and select the performance influencing factor data of each monitoring point from it.

[0026] Specifically, the acquired real-time data is preprocessed to facilitate subsequent data analysis, including: (1) Preprocessing of axle load data: clean the axle load data, i.e. remove outliers, and then count the axle load frequency distribution and cumulative action times (or cumulative axle load times) of each monitoring point. Among them, outlier removal means removing axle load data that exceeds the set range as outliers; (2) Preprocessing of construction and maintenance data: unify the data format of construction and maintenance data and fill in missing information to ensure data consistency and integrity. Taking pavement structure as an example, data format unification means assigning different values ​​to different pavement structures; missing information filling means assigning a value of 0 to missing information to indicate that the value is missing.

[0027] Based on the above preprocessed data, association rules and data fusion technology are used to deeply fuse the axle load data and construction and maintenance data according to the spatial position and time dimensions of each monitoring point, and the multi-dimensional fusion data of each monitoring point time series is obtained. In this way, a comprehensive historical multi-dimensional fusion data set is constructed to provide complete data support for subsequent analysis.

[0028] Furthermore, for each monitoring point, the performance influencing factors that have a more significant impact on the pavement performance are considered, and the cumulative number of axle loads, pavement material type, maintenance history, and meteorological environment data (including temperature and humidity) are selected from the acquired data as performance influencing factor data.

[0029] Afterwards, considering that the relationship between pavement performance and traffic load and meteorological conditions is not a simple linear correlation, the use of linear regression to analyze the relationship between multiple influencing factors and pavement performance will have the problem of poor accuracy. For this reason, this embodiment uses a neural network model to better capture the linear + nonlinear association between data. Specifically, the performance influencing factor data of each monitoring point is used as input, and the performance index detection data (i.e., the PQI score corresponding to the time point of the currently input performance influencing factor) is used as output to construct a neural network model that characterizes the relationship between the cumulative number of axle loads, pavement material type, maintenance history, meteorological environment data and road performance, and the model is used as a road performance evaluation model.

[0030] In this embodiment, a BP neural network model is used to build a road performance evaluation model, which can be expressed as: ; In the above formula, Indicates the road performance index test data, that is, the pavement technical condition index PQI value; [ ... ]express n Performance influencing factors data, is the nonlinear mapping function of the neural network, where is the model weight parameter, is the error term.

[0031] Finally, the neural network model constructed above is trained using the historical multi-dimensional fusion data set. During the training process, multiple rounds of iterative optimization are performed to adjust the weight parameters and activation functions, etc. until the set number of iterations or the minimum loss function value (L1 loss function is used in this embodiment) is reached, and the training is completed. At this time, a more accurate road performance evaluation model can be obtained. Preferably, during the training of the neural network model, the cross-validation method is used to evaluate the prediction performance of the model to further improve the generalization ability of the model.

[0032] This embodiment constructs a neural network model, which can effectively learn the complex relationship between data through the nonlinear activation function (such as ReLU or sigmoid, etc.) and multi-layer structure in the network model, and dynamically optimize the model parameters during the training process to improve the prediction accuracy.

[0033] Based on the pre-trained road performance evaluation model, real-time performance evaluation is performed on each monitoring point on the road, such as Figure 1 As shown, the following steps are included: Step S1, obtaining the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment, as well as the meteorological environment data of the area; the quasi-distributed axle load data includes the axle load size and the number of times of action at each monitoring point, and the construction and maintenance data includes the pavement structure, pavement material type, construction year and maintenance history, etc.

[0034] Step S2, preprocess the acquired data to obtain multidimensional fusion data of each monitoring point, and select performance influencing factor data therefrom, wherein the multidimensional fusion data includes preprocessed axle load data, construction and maintenance data, and meteorological environment data, from which multiple performance influencing factor data affecting performance evaluation are selected.

[0035] Step S3: for each monitoring point, input the performance influencing factor data into the pre-trained road performance evaluation model to obtain the estimated value of the road performance index of the current monitoring point at the current moment.

[0036] Furthermore, in order to solve the problem of estimating road performance between monitoring points, this embodiment proposes an improved spatial interpolation method, which improves the traditional Kriging interpolation method by combining the geographical location, traffic characteristics and environmental factors of the road, so as to achieve accurate performance evaluation of non-monitoring points on the road.

[0037] That is, step S4, based on the estimated value of the road performance index of each monitoring point at the current moment, an improved spatial interpolation method is used, combined with the geographical location, traffic characteristics and meteorological environmental factors of the road, to calculate the estimated value of the road performance index of each non-monitoring point.

[0038] Specifically, first, for each non-monitoring point to be estimated, the traffic characteristic data, meteorological environmental factor data and spatial distance between the non-monitoring point and each monitoring point are obtained; wherein the traffic characteristics include traffic volume, etc., and the meteorological environmental factors include temperature, humidity, etc.

[0039] Secondly, based on the acquired data and the preset adjustment parameters, the spatial distance weight, traffic characteristics weight, and meteorological environmental factor weight of each monitoring point relative to the non-monitoring point are calculated, and then the comprehensive weight is calculated. Among them, for spatial distance, traffic characteristics, and meteorological environmental factors, the preset adjustment parameters include distance attenuation index, traffic adjustment parameters, and meteorological environmental adjustment parameters.

[0040] Furthermore, the calculation formulas for each weight are as follows: (1) The calculation formula of spatial distance weight is: ; in, For monitoring point The distance to the location to be estimated (i.e., not the monitoring point), is the distance decay exponent.

[0041] (2) The calculation formula of traffic characteristic weight is: ; in, For monitoring point The traffic volume, is the traffic volume at the location to be estimated, To adjust the parameters.

[0042] (3) The calculation formula for the weight of meteorological environmental factors is: ; in, For monitoring point The value corresponding to the zth meteorological environmental factor (such as temperature, humidity, etc.), To be estimated position x The value corresponding to the zth meteorological environmental factor, is the adjustment parameter, and Z is the number of meteorological environmental factors.

[0043] According to the above calculated weights of each monitoring point relative to a certain position to be estimated, the comprehensive weight of each monitoring point is calculated. , the calculation formula is: .

[0044] Finally, based on the estimated value of the road performance index of each monitoring point at the current moment and the comprehensive weight, the estimated value of the road performance index of the non-monitoring point at the current moment is calculated. The calculation formula is: ; in, For monitoring point performance indicators, is the estimated value of the performance indicator of the position to be estimated.

[0045] Step S5: Generate a dynamic heat map that digitally represents the road performance based on the estimated value of the real-time road performance index at each point on the road, and annotate the recommended maintenance tips.

[0046] The generation of dynamic heat maps includes: (1) Data mapping: Mapping the estimated performance index values ​​of each road point to the corresponding position of the road grid in the GIS (Geographic Information System) platform; (2) Color gradient setting: The color gradient is set according to the estimated value of the performance indicator, and the color gradually changes from green (indicating good performance) to red (indicating poor performance); (2) Time dimension: Use historical data and real-time updated data to generate a time series of road performance and form a dynamic heat map.

[0047] Furthermore, in the above generated dynamic heat map, corresponding maintenance suggestions or text descriptions are added according to the display conditions, such as Figure 2 As shown, maintenance suggestions or text descriptions are added next to each road section, including "minor repairs", "medium repairs", "major repairs", etc.

[0048] Preferably, the performance evaluation model and the digital characterization results are automatically updated based on the latest axle load data, construction and maintenance data, and inspection data received in real time.

[0049] That is, step S6, based on the real-time received axle load data, construction and maintenance data, meteorological environment data and performance index detection data, continuously updates the historical multi-dimensional fusion data set, uses the updated data set to adaptively optimize the model parameters and interpolation parameters, and updates the dynamic heat map of the digital representation of road performance in real time.

[0050] Among them, (1) the adaptive optimization adjustment of model parameters is: retraining the road performance evaluation model and adjusting the model parameters according to the updated historical multidimensional fusion data set; (2) the interpolation parameters include adjustment parameters, and the adaptive optimization adjustment of the adjustment parameters is: adjusting the optimal value of each adjustment parameter according to the error between the estimated value and the actual value of the road performance indicator at the non-monitoring point.

[0051] Furthermore, during the above-mentioned adaptive optimization and adjustment process, the prediction accuracy of the model and the interpolation method is continuously evaluated, and the optimal model parameters and interpolation parameters are determined to ensure the accuracy and reliability of the final evaluation results.

[0052] Embodiment 2 This embodiment provides a road performance digital characterization system based on quasi-distributed axle load data, the system comprising: A data acquisition module is used to acquire the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment; the quasi-distributed axle load data includes the axle load size and the number of times of action of each monitoring point; The data preprocessing module is used to preprocess the acquired data to obtain multi-dimensional fusion data of each monitoring point and select performance influencing factor data from it; The monitoring point performance evaluation module is used to input the performance influencing factor data into the pre-trained road performance evaluation model for each monitoring point to obtain the estimated value of the road performance index of the current monitoring point at the current moment; The non-monitoring point performance evaluation module is used to calculate the estimated road performance index value of each non-monitoring point based on the estimated road performance index value of each monitoring point at the current moment, using an improved spatial interpolation method, combined with the geographical location, traffic characteristics and environmental factors of the road; The digital characterization module is used to generate a dynamic heat map that digitally characterizes road performance based on the estimated values ​​of road performance indicators at each point on the road, and annotate recommended maintenance tips.

[0053] Embodiment 3 This embodiment provides an electronic device, including: a memory, used to store executable instructions; a processor, used to implement the above method provided by this embodiment when executing the executable instructions stored in the memory.

[0054] Embodiment 4 This embodiment also provides a computer-readable storage medium storing executable instructions. When the executable instructions are executed by a processor, the processor will be caused to execute the above method provided in this embodiment.

[0055] Embodiment 5 This embodiment provides a computer program product, which includes an executable instruction, which is a computer instruction; the executable instruction is stored in a computer-readable storage medium. When a processor of an electronic device reads the executable instruction from the computer-readable storage medium and the processor executes the executable instruction, the electronic device executes the above method provided in this embodiment.

[0056] The steps involved in the above embodiments 2 to 5 correspond to the method embodiment 1. For the specific implementation, please refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0057] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0058] The above description is only a preferred embodiment of the present invention. Although the specific implementation mode of the present invention is described in conjunction with the accompanying drawings, it is not a limitation of the protection scope of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the protection scope of the present invention.

Claims

1. A road performance digital characterization method based on quasi-distributed axle load data, characterized in that: include: Acquire the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment, as well as the meteorological environment data of the area where the road infrastructure is located; the quasi-distributed axle load data includes the axle load size and the number of times of action at each monitoring point; Preprocess the acquired data to obtain multi-dimensional fusion data of each monitoring point, and select performance influencing factor data from them; For each monitoring point, the performance influencing factor data is input into the pre-trained road performance evaluation model to obtain the estimated value of the road performance index of the current monitoring point at the current moment; Based on the estimated value of the road performance index at each monitoring point at the current moment, the improved spatial interpolation method is used to combine the geographical location, traffic characteristics and meteorological environmental factors of the road to calculate the estimated value of the road performance index at each non-monitoring point; Based on the estimated values ​​of road performance indicators at each point on the road, a dynamic heat map that digitally represents road performance is generated, and recommended maintenance tips are marked.

2. A road performance digital characterization method based on quasi-distributed axle load data as claimed in claim 1, characterized in that: Based on the estimated value of the road performance index of each monitoring point at the current moment, the improved spatial interpolation method is used to combine the geographical location, traffic characteristics and meteorological environmental factors of the road to calculate the estimated value of the road performance index of each non-monitoring point, including: For each non-monitoring point to be estimated, traffic characteristic data, meteorological environmental factor data and spatial distance between the non-monitoring point and each monitoring point are obtained; wherein the traffic characteristics include traffic volume, and the meteorological environmental factors include temperature and humidity; According to the acquired data, combined with the preset adjustment parameters, the spatial distance weight, traffic characteristic weight, and meteorological environment factor weight of each monitoring point relative to the non-monitoring point are calculated respectively, and then the comprehensive weight is calculated; the adjustment parameters include the distance attenuation index, the traffic adjustment parameter, and the meteorological environment adjustment parameter; Based on the estimated value of the road performance index of each monitoring point at the current moment and the comprehensive weight, the estimated value of the road performance index of the non-monitoring point at the current moment is calculated.

3. A road performance digital characterization method based on quasi-distributed axle load data as claimed in claim 1, characterized in that: The road performance evaluation model is pre-trained using statistical analysis and machine learning algorithms, and the pre-training process includes: Obtain quasi-distributed axle load data, construction and maintenance data, and performance index test data of road infrastructure, as well as meteorological environment data of the area where the road infrastructure is located; Preprocess the acquired data, deeply fuse the preprocessed data according to spatial location and time dimensions to form historical multidimensional fusion data of each monitoring point, construct a historical multidimensional fusion data set, and select performance influencing factor data of each monitoring point from it; the performance influencing factors include the cumulative number of axle loads, pavement material type, maintenance history, and meteorological environment; Taking the performance influencing factor data of each monitoring point as input and the performance index detection data as output, a neural network model is constructed to characterize the relationship between the cumulative number of axle loads, pavement material type, maintenance history, meteorological environment data and road performance as a road performance evaluation model; The road performance evaluation model is trained using a historical multidimensional fusion data set, and the cross-validation method is used to evaluate the predictive performance of the model. After multiple rounds of iterative optimization training, the training is completed until the set number of iterations is reached or the loss function value is minimized, and the pre-trained road performance evaluation model is obtained.

4. A road performance digital characterization method based on quasi-distributed axle load data as claimed in claim 3, characterized in that: The construction and maintenance data include pavement structure, pavement material type, construction year and maintenance history; the performance index detection data include pavement technical condition index value, which is calculated based on pavement damage condition index, pavement driving quality index and pavement rutting depth index data; The pre-processing comprises: Remove outliers from axle load data and count the axle load frequency distribution and cumulative action times at each monitoring point; Unify the data format of construction and maintenance data and fill in missing values.

5. The method for digitally characterizing road performance based on quasi-distributed axle load data according to claim 3, characterized in that: The road performance evaluation model is expressed as: ； In the above formula, It indicates the road performance index test data, that is, the road surface technical condition index value; [ ... ]express n Performance influencing factors data, is the nonlinear mapping function of the neural network, is the model weight parameter, is the error term.

6. A road performance digital characterization method based on quasi-distributed axle load data as claimed in claim 1, characterized in that: Based on the real-time received axle load data, construction and maintenance data, meteorological environment data and performance index detection data, the historical multi-dimensional fusion data set is continuously updated, and the model parameters and interpolation parameters are adaptively optimized using the updated data set, and the dynamic thermal map of the digital representation of road performance is updated in real time; The adaptive optimization and adjustment of the model parameters include: retraining the road performance evaluation model and adjusting the model parameters according to the updated historical multi-dimensional fusion data set; The interpolation parameters include adjustment parameters, and the adaptive optimization adjustment of the adjustment parameters is: adjusting the optimal value of each adjustment parameter according to the error between the estimated value and the actual value of the road performance index of the non-monitoring point.

7. A road performance digital characterization system based on quasi-distributed axle load data, characterized in that: include: A data acquisition module is used to obtain the quasi-distributed axle load data and construction and maintenance data of the road infrastructure at the current moment, as well as the meteorological environment data of the area where the road infrastructure is located; the quasi-distributed axle load data includes the axle load size and the number of times of action of each monitoring point; The data preprocessing module is used to preprocess the acquired data to obtain multi-dimensional fusion data of each monitoring point and select performance influencing factor data from it; The monitoring point performance evaluation module is used to input the performance influencing factor data into the pre-trained road performance evaluation model for each monitoring point to obtain the estimated value of the road performance index of the current monitoring point at the current moment; The non-monitoring point performance evaluation module is used to calculate the estimated road performance index value of each non-monitoring point based on the estimated road performance index value of each monitoring point at the current moment, using an improved spatial interpolation method, combined with the geographical location, traffic characteristics and meteorological environmental factors of the road; The digital characterization module is used to generate a dynamic heat map that digitally characterizes road performance based on the estimated values ​​of road performance indicators at each point on the road, and annotate recommended maintenance tips.

8. An electronic device, characterized in that: include: A memory for storing executable instructions; The processor is used to implement a road performance digital characterization method based on quasi-distributed axle load data as described in any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause the processor to execute the executable instructions to implement a road performance digital characterization method based on quasi-distributed axle load data as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes executable instructions stored in a computer-readable storage medium; When the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the method for digitally characterizing road performance based on quasi-distributed axle load data as described in any one of claims 1 to 6 is implemented.

Images