Road fatigue damage prediction method, system, equipment, medium and program product

Abstract

The invention discloses a road fatigue damage prediction method, system and device, a medium and a program product, and relates to the technical field of road surface damage prediction.The method comprises the steps that according to obtained road surface traffic load data, each axle load of each vehicle is converted into the equivalent axle number of standard axle loads, the equivalent axle numbers of all vehicles at the current moment are summarized, and the equivalent axle numbers of all vehicles at the current moment are obtained; obtaining a multi-axle load accumulated value at the current moment, and obtaining an accumulated damage degree according to the multi-axle load accumulated value; according to the multi-axle load accumulated value at the current moment, the proportion of various vehicle types, the average vehicle speed at the current moment and the accumulated damage degree at the previous moment, the evolution trend of the accumulated damage degree is predicted, set damage degree predicted values at multiple moments in the future are obtained, and an early warning signal is pushed when the damage degree predicted values exceed a set threshold value. High-frequency and multi-axle load data are accumulated according to time periods, the road damage degree is quantified more truly, and the potential damage risk of the road surface is reduced through rolling prediction of the damage degree.

Description

Technical Field

[0001] The present invention relates to the technical field of road damage prediction, and in particular to a road fatigue damage prediction method, system, equipment, medium and program product. Background Art

[0002] Traditional road design and maintenance assessments typically use a single axle load or gross vehicle weight to estimate the extent of pavement damage. However, in today's high-traffic, high-volume environment, large numbers of heavy-loaded trucks and multi-axle vehicles frequently travel on trunk roads, expressways, and urban freeways. The fatigue damage these vehicles inflict on pavement far exceeds the limits of a single axle load or gross vehicle weight.

[0003] Existing methods calculate pavement fatigue damage based on the vehicle's gross weight or a representative single-axle weight (e.g., the load on a fixed axle). However, in multi-axle vehicles, the impact frequency and amplitude of each axle on the road surface vary, and variations in the vehicle's wheelbase and number of axles affect how wheel loads act on the road surface and the cumulative effect. Furthermore, heavily loaded vehicles with a high axle count often produce multiple, cumulative fatigue effects on the road surface within a short period of time. This results in a significant loss of information regarding the specific details of multi-axle load characteristics (e.g., 5-axle, 6-axle, or even 8-axle) when calculating cumulative fatigue, if only a single axle or gross weight is used as the basis. This can lead to errors in the assessment results and may even significantly underestimate the risk of road damage. Summary of the Invention

[0004] To address the above-mentioned issues, the present invention proposes a road fatigue damage prediction method, system, equipment, medium, and program product, which accumulate high-frequency, multi-axle load data by time period to obtain a more realistic quantification of road damage. By making a rolling prediction of damage levels, the potential risk of road damage is reduced.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for predicting road fatigue damage, comprising: Based on the acquired road traffic load data, each axle load of each vehicle is converted into an equivalent axle load of the standard axle load. The equivalent axle loads of all vehicles at the current moment are summarized to obtain the cumulative value of the multi-axle load at the current moment, and the cumulative damage degree is obtained based on the cumulative value of the multi-axle load; Based on the current cumulative multi-axle load value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree at the previous moment, the evolution trend of the cumulative damage degree is predicted to obtain the damage degree prediction values ​​for multiple set future moments, and a warning signal is pushed when the damage degree prediction value exceeds the set threshold.

[0006] As an optional implementation, the process of converting the equivalent axle load to the standard axle load includes: Where, is the equivalent axle load of a single axle, is the conversion index, is the axis group coefficient, is the wheel coefficient, is the uniaxial load of the i-th type of shaft, For standard axle load.

[0007] As an optional implementation, the process of obtaining the cumulative damage degree according to the multi-axle load cumulative value includes: Where, for The accumulated value of multi-axle load at the moment; for The cumulative damage at that time, for The cumulative damage at that time, It is a constant that adjusts the relationship between road materials and loads. It is the durable axle load capacity of the road under standard load.

[0008] As an optional implementation method, the process of predicting the evolution trend of the cumulative damage degree includes: according to the current multi-axle load cumulative value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree at the previous moment, the long short-term memory network is used to map the hidden state and obtain the damage degree prediction value at the next moment. ;in, ; ; ; in, is the hidden state at time t-1; is the cell state at time t-1; is the hidden state at time t; is the cell state at time t; Output of the forget gate; is the Sigmoid activation function; 、 、 and are the weight matrices of the forget gate, input gate, cell update, and output gate, respectively; 、 、 and are the bias vectors for the forget gate, input gate, cell update, and output gate, respectively; is the candidate cell state at the current moment; is the output of the input gate; Output of the output gate; is the hyperbolic tangent activation function, is the weight matrix of the output layer; is the bias vector of the output layer.

[0009] As an optional implementation, according to the difference between the predicted damage degree at the next moment and the actual accumulated damage degree, the mean square error loss function is used to update the network parameters of the long short-term memory network based on the gradient descent algorithm.

[0010] As an optional implementation method, a damage degree prediction curve is constructed based on the damage degree prediction values ​​at multiple future moments. In the damage degree prediction curve, if there is a future moment If the set threshold is exceeded, an early warning signal will be sent to Damage degree prediction value at time Carry out road maintenance measures before it occurs.

[0011] In a second aspect, the present invention provides a road fatigue damage prediction system, comprising: The damage degree calculation module is configured to convert each axle load of each vehicle into an equivalent axle load of a standard axle load based on the acquired road traffic load data, summarize the equivalent axle loads of all vehicles at the current moment, obtain a cumulative multi-axle load value at the current moment, and obtain a cumulative damage degree based on the cumulative multi-axle load value; The damage degree prediction module is configured to predict the evolution trend of the cumulative damage degree based on the current multi-axle load accumulation value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree at the previous moment, obtain the damage degree prediction value for multiple set future moments, and push a warning signal when the damage degree prediction value exceeds the set threshold.

[0012] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0014] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention proposes a road fatigue damage prediction method, system, device, medium, and program product. First, each axle load of each vehicle is converted into an equivalent axle load of a standard axle load. The equivalent axle loads of all vehicles are then aggregated to obtain the current cumulative multi-axle load value. This cumulative damage degree is then calculated based on the multi-axle load cumulative value. High-frequency, multi-axle load data is then accumulated by time period to achieve a more accurate quantification of the road damage degree. The evolution trend of the cumulative damage degree is then predicted based on key traffic load characteristics at the current moment, resulting in predicted damage degrees for multiple predetermined future moments. A warning signal is then issued when the predicted damage degree exceeds a set threshold. This enables rolling damage degree prediction, improves prediction accuracy and robustness, and reduces the risk of potential road damage.

[0016] Traditional methods only use the gross vehicle weight or a few axle load indicators to estimate road fatigue, and tend to ignore the cumulative effect caused by multi-axis coupling. So in order to solve the problem of how to accurately map vehicle multi-axle load data to the cumulative fatigue of the road, the present invention introduces the equivalent axle load conversion formula and the Miner fatigue criterion to accumulate high-frequency, multi-axle load data according to time periods, thereby obtaining a more realistic quantification of road damage. Different from traditional methods that mainly rely on estimated values ​​or recommended parameters, the present invention is based on the measured data of each vehicle and each axle, and dynamically accumulates and converts equivalent data by vehicle type, axle, and time period, which retains the real information of traffic load to the greatest extent and effectively reduces the system error caused by simplification or empirical estimation. Therefore, the results after conversion of the method of the present invention are closer to the actual traffic load pattern, and the evaluation accuracy is significantly improved.

[0017] Traditional methods lack a precise and accurate prediction link, and are unable to systematically present the road fatigue accumulation process from the perspective of single-vehicle multi-axle data. When faced with a surge in heavy-loaded vehicles, the lag of traditional methods can easily cause excessive damage to the road. Therefore, the present invention conducts in-depth mining based on multi-axle load data. Unlike the traditional simplified evaluation based on gross weight or single axle, it can carefully depict the compound fatigue damage of multi-axle vehicles to the road surface. It then introduces time series prediction technology based on long-short-term memory networks, making the road damage prediction more sensitive and accurate according to the time-varying characteristics of traffic flow fluctuations and high-load vehicle characteristics. Finally, based on the damage prediction curve, timely intervention and repair are carried out before fatigue reaches its limit. In combination with incremental training and new data feedback, a new self-learning road maintenance management system is formed. In practical applications, it helps to carry out targeted maintenance in key sections or lanes, significantly extending the local or overall service life of the road surface, and saving subsequent maintenance costs.

[0018] Given the significant fluctuations in traffic flow over daily, weekly, and seasonal cycles, as well as in the proportion of vehicle types, how can we achieve time-series prediction of road fatigue damage and effectively predict short- and medium-term road damage trends? To address this issue, this paper utilizes a long-short-term memory network to capture the nonlinear evolution of damage, enabling rolling prediction. The model also incorporates key features such as multi-axle load accumulation, vehicle type ratio, and vehicle speed, thereby improving prediction accuracy and robustness.

[0019] The goal is to develop a closed-loop maintenance decision-making mechanism based on damage prediction results, including early warning of maintenance opportunities, solution selection, and dynamic verification of implementation effectiveness. By setting a threshold on the damage prediction curve, this invention issues a warning signal if the accumulated fatigue level exceeds the allowable limit during a certain period in the future. This allows optimized maintenance measures to be deployed in advance, before heavy traffic causes serious damage, minimizing potential damage and economic losses.

[0020] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of an implementation environment for the solution provided in Example 1 of the present invention; Figure 2 Flowchart of the road fatigue damage prediction method provided in Example 1 of the present invention; Figure 3 This is a framework diagram of the road fatigue damage prediction system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "comprise" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0027] Multi-axle load data can be refined down to the actual weight borne by each vehicle axle. By combining information such as axle spacing and vehicle type, it provides a more accurate basis for identifying the fatigue damage contributions of different vehicles to the road surface. By converting and accumulating all axle loads according to a specific nonlinear relationship, the true impact of multi-axle vehicles can be fully captured. This allows road lifespan assessments and maintenance strategy development to more closely reflect actual traffic conditions, reducing underestimations or overestimations caused by simplified models.

[0028] Therefore, the present invention proposes a road fatigue damage prediction method. By combining multi-axle load data with a pavement cumulative damage model, and then using the long short-term memory network (LSTM) in deep learning to perform time series prediction, it ultimately forms dynamic management and early warning of the cumulative damage degree of the road, providing a more scientific and accurate basis for road maintenance decision-making.

[0029] Example 1 Figure 1 This is a diagram of the implementation environment involved in a road fatigue damage prediction method provided by an embodiment of the present invention. Figure 1 As shown, the implementation environment includes a vehicle 101, an image acquisition device 102, a weighing system 103 and a server 104; wherein the vehicle 101 is equipped with an on-board GPS device.

[0030] The image acquisition device 102 can be deployed along the road. For example, it can be deployed at a checkpoint on the highway. Taking one of the checkpoints as an example, the image acquisition device 102 can capture photos of all vehicles passing through the checkpoint at any given moment and transmit the captured photos of all vehicles passing through the checkpoint at any given moment to the server 104. The server 104 can then identify the license plate data and vehicle model data of all vehicles in the photos based on the received photos of all vehicles passing through the checkpoint at any given moment.

[0031] The weighing system 103 is mainly deployed at the road entrance to weigh the vehicles entering and collect the license plate data, and then store the license plate data and weight of the vehicles in correspondence.

[0032] The server 104 is used to obtain the vehicle GPS data sent by the vehicle-mounted GPS device of the vehicle 101. The vehicle GPS data includes the vehicle license plate data and the position coordinates of the vehicle on the road at each moment and the time corresponding to the position coordinates passed.

[0033] Server 104 converts each axle load of each vehicle into an equivalent axle load of the standard axle load based on the acquired road traffic load data, such as vehicle type, axle weight, total weight, passing time, etc., summarizes the equivalent axle loads of all vehicles at the current moment, obtains the cumulative value of the multi-axle load at the current moment, and obtains the cumulative damage degree based on the cumulative value of the multi-axle load; then, based on the cumulative value of the multi-axle load at the current moment, the proportion of various vehicle types, the average vehicle speed at the current moment and the cumulative damage degree at the previous moment, predicts the evolution trend of the cumulative damage degree, obtains the damage degree prediction values ​​for the set future multiple moments, and pushes a warning signal when the damage degree prediction value exceeds the set threshold.

[0034] The server 104 may be a separate server, a server cluster, or a cloud platform, which is not limited in the embodiment of the present invention.

[0035] Next, the road fatigue damage prediction method provided by an embodiment of the present invention is introduced.

[0036] Figure 2 This is a road fatigue damage prediction method provided by an embodiment of the present invention. This method can be applied to a target server, where the target server can be Figure 1 The server shown. Figure 2 As shown, the method includes the following steps: S201: Based on the acquired road traffic load data, each axle load of each vehicle is converted into an equivalent axle load of the standard axle load, the equivalent axle loads of all vehicles at the current moment are summarized to obtain a cumulative multi-axle load value at the current moment, and a cumulative damage degree is obtained based on the cumulative multi-axle load value; S202: Based on the current cumulative multi-axle load value, the proportion of various types of vehicles, the current average speed, and the cumulative damage degree at the previous moment, the evolution trend of the cumulative damage degree is predicted to obtain the damage degree prediction values ​​for the set future multiple moments, and a warning signal is pushed when the damage degree prediction value exceeds the set threshold.

[0037] In this embodiment, the road traffic load data is first collected based on the on-site dynamic weighing system, including: the total number of vehicles in each lane in each direction, vehicle type, vehicle speed, number of axles, axle type composition, axle weight, axle spacing, total weight, passing time (date, hour, minute, second), etc.; among them, the axle type can be determined based on the wheel group and axle group, and the vehicle type can be determined based on the axle type.

[0038] Then, calculate the equivalent axle times of various axle types of various vehicles, that is, convert each axle load of each vehicle into the equivalent axle times of standard axle load; ; Where, is the equivalent axle load of a single axle; For conversion index, if it is for asphalt mixture layer fatigue and asphalt mixture layer permanent deformation, n=4, if it is for roadbed permanent deformation, n=5, if it is for inorganic binder stabilized layer fatigue, n=13; is the axle group coefficient. When the distance between the front and rear axles is greater than 3m, they are calculated as single axles. When the distance between the axles is less than or equal to 3m, the value is determined according to Table 1. is the wheel set coefficient, which is 1 for a double wheel set and 4.5 for a single wheel set; is the single shaft load of the i-th shaft type. For double and triple shafts, it is the load evenly distributed to each single shaft. For standard axle load.

[0039] Table 1 Axis group coefficient values; .

[0040] Furthermore, the current moment The equivalent axle loads of all vehicles in the vehicle are summarized to obtain the multi-axle load cumulative value at the current time t Compared with the traditional method of measuring by gross vehicle weight or single axle, the method of this embodiment can accurately reflect the coupling effect of multi-axle load on road fatigue.

[0041] In order to quantify the contribution of multi-axle load data to the cumulative damage of the pavement, this embodiment adopts a pavement cumulative damage model based on the Miner criterion. Each time step (such as hour or day) is used as the calculation unit, and the cumulative value of multi-axle load is used as the calculation unit. Get the cumulative damage : ; Where, for The cumulative damage at that time, Represents the durable axle load capacity of the road under standard load; It is a constant that adjusts the relationship between road materials and loads. In actual engineering, The value usually needs to be determined comprehensively based on the specific road structure type, material properties, regional standards and historical test data, and is generally selected between 0.8 and 1.2. However, it can be selected based on actual engineering design or test conditions and is not mandatory here.

[0042] In this embodiment, the cumulative damage degree is recursively calculated at each time step to describe the superposition effect of multi-axle load data on road fatigue at different time periods. When the value is close to or equal to 1, it means that the road structure is approaching or has reached its fatigue limit and requires immediate assessment and maintenance or renovation. If it continues to operate at a high level, it is very likely to suffer from large-scale cracking, rutting or broken plates in a short period of time.

[0043] In this embodiment, the cumulative damage degree is obtained Then, the long short-term memory network is used to The evolution trend of traffic load is dynamically predicted, and the key traffic load characteristics, namely the cumulative value of multi-axle load at the current moment, the proportion of various types of vehicles, the average speed at the current moment and the cumulative damage degree at the previous moment, are used as the input of the LSTM network, so that the network can "see" the change pattern of multi-axle load data during training and prediction.

[0044] Specifically: Each time step, The input feature vector of the LSTM network at the moment Defined as: ; in, The proportion of each type of vehicle model; is the average speed at the current moment, which is obtained based on the speed of each vehicle and the total number of vehicles at the current moment; The cumulative damage at the previous moment.

[0045] Among them, As the model input, it is to incorporate historical state information into the current prediction and realize the dynamic recursion of time series data, which is in line with the common practice of time series modeling such as LSTM network. As a model input, it reflects the direct impact of the current load on damage. Combining these two ensures that the model leverages historical damage states while reflecting current load changes, improving the consistency and accuracy of predictions. Furthermore, factors such as temperature and rainfall can also be incorporated.

[0046] The input feature vector is input into the LSTM network, and after passing through the forget gate, input gate, output gate and other structures, the historical sequence and the current input are mapped to a new hidden state. and cell status , and finally output the damage degree prediction value for the next moment .

[0047] The core process is expressed as: ; ; ; in, is the hidden state at time t-1; is the cell state at time t-1; Output of the forget gate; is the Sigmoid activation function; 、 、 and are the weight matrices of the forget gate, input gate, cell update, and output gate, respectively; 、 、 and are the bias vectors for the forget gate, input gate, cell update, and output gate, respectively; is the candidate cell state at the current moment; is the output of the input gate; Output of the output gate; is the hyperbolic tangent activation function.

[0048] Finally, the predicted value is obtained through a linear mapping ;in, is the weight matrix of the output layer; is the bias vector of the output layer.

[0049] During the model training phase, Compared with the actual cumulative damage at time t+1 Calculate the difference (e.g. using mean square error loss function) and continuously update it using gradient descent algorithm 、 、 Equal network parameters, so that the prediction and the true value gradually approach each other.

[0050] Therefore, the LSTM network can capture the nonlinear changes in traffic volume while learning the role of multi-axle load data in road damage accumulation into its own parameters, making the prediction more sensitive to periods of high traffic volume and heavy-load vehicles, thereby outputting fatigue trends that are more in line with reality.

[0051] Through the multi-step rolling forecast method, we can look forward to several periods (hours, days or weeks) at any time, and thus obtain the damage prediction curve. If the set threshold is exceeded, the relevant road management department will be notified. Make good maintenance and construction plans in advance.

[0052] In this embodiment, after completing the damage degree prediction for multiple moments in the future, the early warning and maintenance management links are further established. If the road's speed continuously exceeds a set maximum threshold (such as 0.7 or 0.8), the road is considered to be at high risk of fatigue damage. At this point, an early warning message is sent to the management system, advising relevant departments to schedule inspections, resurfacing, local pothole repairs, or other necessary preventive maintenance before that time. If there is a probability of severe overloads (for example, frequent overloaded trucks in a specific area), dynamic scheduling measures are embedded in the maintenance management system, such as speed and load limits, or lane diversion strategies, to mitigate the occurrence of severe damage. After implementing these measures, data from the new time period can be monitored in real time and fed back to the LSTM network for incremental training, achieving closed-loop management of road conditions.

[0053] Example 2 Please refer to Figure 3 , is a block diagram of a road fatigue damage prediction system according to an embodiment of the present invention. The system is configured to execute the steps of the aforementioned road fatigue damage prediction method. The road fatigue damage prediction system includes a damage degree calculation module 301 and a damage degree prediction module 302.

[0054] The damage degree calculation module 301 is configured to convert each axle load of each vehicle into an equivalent axle load of a standard axle load based on the acquired road traffic load data, summarize the equivalent axle loads of all vehicles at the current moment, obtain a cumulative multi-axle load value at the current moment, and obtain a cumulative damage degree based on the cumulative multi-axle load value; The damage degree prediction module 302 is configured to predict the evolution trend of the cumulative damage degree based on the current multi-axle load accumulation value, the proportion of various types of vehicles, the current average vehicle speed and the cumulative damage degree at the previous moment, obtain the damage degree prediction value for multiple set future moments, and push a warning signal when the damage degree prediction value exceeds the set threshold.

[0055] It should be noted that the systems provided in the above embodiments are only illustrated by the division of the above functional modules when implementing their functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the systems and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0056] In an exemplary embodiment, an electronic device is further provided, including a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions complete the method described in embodiment 1 when executed by the processor.

[0057] The processor may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor may be implemented in at least one of the following hardware forms: digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor may also include an AI processor, which is responsible for processing computing operations related to machine learning.

[0058] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices or flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store computer instructions, which are configured to be executed by one or more processors to implement the above method.

[0059] In an exemplary embodiment, a computer-readable storage medium is further provided, wherein the storage medium stores computer instructions, which, when executed by a processor, implement the method described in Example 1. Optionally, the computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), solid state drives (SSD), or optical disks. The random access memory may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM).

[0060] In an exemplary embodiment, a computer program product is further provided, the computer program product including a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the method described in Example 1.

[0061] It should be noted that the collection and processing of relevant data in this invention, when applied in practice, should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of authorization of laws and regulations and the personal information subject.

[0062] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A road fatigue damage prediction method, characterized in that: include: Based on the acquired road traffic load data, each axle load of each vehicle is converted into an equivalent axle load of the standard axle load. The equivalent axle loads of all vehicles at the current moment are summarized to obtain the cumulative value of the multi-axle load at the current moment, and the cumulative damage degree is obtained based on the cumulative value of the multi-axle load; Based on the current cumulative multi-axle load value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree at the previous moment, the evolution trend of the cumulative damage degree is predicted to obtain the damage degree prediction values ​​for multiple set future moments, and a warning signal is pushed when the damage degree prediction value exceeds the set threshold.

2. A road fatigue damage prediction method according to claim 1, characterized in that: The process of converting the equivalent axle load to the standard axle load includes: Where, is the equivalent axle load of a single axle, is the conversion index, is the axis group coefficient, is the wheel coefficient, is the uniaxial load of the i-th type of shaft, For standard axle load.

3. A road fatigue damage prediction method according to claim 1, characterized in that: The process of obtaining the cumulative damage degree based on the cumulative value of multi-axle load includes: Where, for The accumulated value of multi-axle load at the moment; for The cumulative damage at that time, for The cumulative damage at that time, It is a constant that adjusts the relationship between road materials and loads. It is the durable axle load capacity of the road under standard load.

4. A road fatigue damage prediction method according to claim 1, characterized in that: The process of predicting the evolution trend of the cumulative damage degree includes: according to the current multi-axle load cumulative value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree of the previous moment, the long short-term memory network is used to map the hidden state and obtain the damage degree prediction value at the next moment. ;in, ； ； ； in, is the hidden state at time t-1; is the cell state at time t-1; is the hidden state at time t; is the cell state at time t; Output of the forget gate; is the Sigmoid activation function; 、 、 and are the weight matrices of the forget gate, input gate, cell update, and output gate, respectively; 、 、 and are the bias vectors for the forget gate, input gate, cell update, and output gate, respectively; is the candidate cell state at the current moment; is the output of the input gate; Output of the output gate; is the hyperbolic tangent activation function, is the weight matrix of the output layer; is the bias vector of the output layer.

5. A road fatigue damage prediction method according to claim 4, characterized in that: According to the difference between the predicted damage value at the next moment and the actual accumulated damage value, the mean square error loss function is used to update the network parameters of the long short-term memory network based on the gradient descent algorithm.

6. A road fatigue damage prediction method according to claim 1, characterized in that: The damage prediction curve is constructed based on the damage prediction values ​​at multiple future moments. In the damage prediction curve, if there is a future moment If the set threshold is exceeded, an early warning signal will be sent to Damage degree prediction value at time Carry out road maintenance measures before it occurs.

7. A road fatigue damage prediction system, characterized in that: include: The damage degree calculation module is configured to convert each axle load of each vehicle into an equivalent axle load of a standard axle load based on the acquired road traffic load data, summarize the equivalent axle loads of all vehicles at the current moment, obtain a cumulative multi-axle load value at the current moment, and obtain a cumulative damage degree based on the cumulative multi-axle load value; The damage degree prediction module is configured to predict the evolution trend of the cumulative damage degree based on the current multi-axle load accumulation value, the proportion of various types of vehicles, the current average speed and the cumulative damage degree at the previous moment, obtain the damage degree prediction value for multiple set future moments, and push a warning signal when the damage degree prediction value exceeds the set threshold.

8. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images