A method for evaluating historical characteristics of traffic loads during long-term road service

Abstract

This invention discloses a method for evaluating the historical characteristics of traffic loads on roads during their long-term service. The method collects existing pavement conditions and annual historical traffic, pavement, and weather data for long-serving sections with no maintenance history. The method then determines the half-value of the Standard Axle Load (ESAL) and the overload rate corresponding to each ESAL over the service life of the road section, and calculates their ratio (LOI). The LOIs are grouped and the degradation of the Pavement Condition Index (PCI) with ESAL at different LOIs is compared. A PCI prediction model is constructed to compare the change in model prediction accuracy when LOI is used as an independent variable, and to rank the LOI's importance within the independent variable set. This method uses the historical characteristics of traffic loads on long-serving sections to propose an LOI metric for quantitative evaluation, providing valuable guidance for traffic load control, pavement performance prediction, and maintenance decision-making.

Description

Technical Field

[0001] The present invention belongs to the technical field of road maintenance, and in particular relates to a method for evaluating historical characteristics of traffic loads during the long-term service of a road. Background Art

[0002] Traffic load is a key factor influencing pavement degradation. Accurately assessing its impact on pavement performance is crucial for making informed maintenance decisions. Commonly used traffic load metrics include the number of standard axle load applications (ESAL) and the average annual daily traffic volume (AADT). These metrics are typically treated as cumulative or average values ​​when evaluating traffic conditions on long-serving roads. However, this approach ignores the specific loading history of traffic loads and fails to fully reflect the complexity of actual road stress conditions. Previous studies have demonstrated through laboratory tests that different loading sequences produce distinct failure modes for asphalt mixtures, affecting their service life and damage severity. Furthermore, field observations have shown that even under identical ESALs, pavement structural materials, and climatic conditions, performance degradation rates can vary significantly across road sections, leading to varying maintenance requirements. This suggests that traditional traffic load variables cannot fully capture subtle variations in traffic load histories in pavement performance predictions, potentially leading to inaccurate maintenance decisions. Therefore, accurately assessing the historical characteristics of traffic loads is particularly important for long-serving roads. This not only supports accurate predictions of pavement performance but also helps optimize maintenance plans, ensuring a high level of service throughout the road's lifecycle. To address this issue, this method proposes an evaluation method for the historical characteristics of traffic loads over the long term of a road's service life. Based on years of measured axle load spectra and pavement performance test data, this method develops quantitative indices for measuring the historical characteristics of traffic loads. These indices better reflect the complexity of traffic loads and can be used to analyze the decay patterns of pavement damage conditions, thereby constructing a predictive model for damage conditions. This method clearly demonstrates the significant contribution of traffic load history to the development and prediction of pavement damage conditions, providing a more scientific basis for road performance prediction and maintenance decisions. This approach not only helps extend the service life of roads and reduce maintenance costs, but also improves the overall service quality of roads, possessing important practical application value and guiding significance. Summary of the Invention

[0003] This invention aims to address the shortcomings of existing methods for evaluating the historical characteristics of traffic loads on long-serving roads by innovatively designing a quantitative index to accurately measure the historical characteristics of traffic loads. This not only allows for in-depth analysis of the decay patterns of pavement damage but also enables the construction of a predictive model for damage conditions, thereby clarifying the crucial role of historical traffic load characteristics in determining and predicting pavement damage. This provides a more scientific and reliable basis for accurate road performance prediction and maintenance decision-making, helping to improve maintenance efficiency and service levels throughout the road lifecycle.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A method for evaluating historical characteristics of traffic loads during long-term road service, characterized by comprising the following steps:

[0006] Step 1: Collect data on the basic characteristics, pavement structure materials, traffic load conditions, pavement damage conditions, and weather conditions of roads that have been in service for ten years or more without maintenance;

[0007] Step 2: Determine the overload rate generated during the service life of the road section corresponding to half of the given standard axle load (ESAL) value and the ESAL, and calculate their ratio, which is defined as the loading order index (LOI);

[0008] Step 3: Group the LOI indicators and use box plots to compare the decline of the pavement condition index (PCI) with ESAL under different LOIs;

[0009] Step 4: Use random forest and artificial neural network algorithms to build PCI prediction models, compare the changes in model prediction accuracy when LOI is used as an independent variable, and compare the importance ranking of LOI in the independent variable set.

[0010] Furthermore, the data items that need to be collected in step one include: basic characteristics of the road section: road age, lane, road surface or bridge deck; pavement structural materials: modified asphalt layer thickness, asphalt surface layer thickness, asphalt surface layer gradation type, base layer thickness, base layer material; annual traffic load conditions: ESAL, axle load spectrum; annual pavement damage conditions: PCI; weather conditions: proportion of high temperature days, proportion of low temperature days, proportion of rainy days, annual average daily temperature, annual average daily precipitation.

[0011] Furthermore, the calculation method of the loading order index LOI in step 2 is as follows:

[0012] 1) For a road section with a service time of more than 10 years T, determine its corresponding ESAL and find the service time corresponding to ESAL / 2: T half=f(ESAL / 2),f:ESAL→t, where f represents a mapping from ESAL to service time t;

[0013] 2) Using the axle load spectrum information, calculate the T and T of the road section from opening to service half The corresponding overload rates for each year are:

[0014] Where OR(t) represents the overload rate from the opening of the road to year t, A represents the axle type set, including single axle, double axle and triple axle, a represents a specific axle type, Indicates time t ′ When the shaft type a is overloaded, Indicates time t ′ When , the total number of shafts of shaft type a;

[0015] 3) Calculate the loading order index corresponding to the service time T of the road section: LOI(T)=OR(T half ) / OR(T).

[0016] Furthermore, the graphic display method in step three is as follows:

[0017] 1) For each road segment with a service time of more than ten years, the LOI value was calculated and divided into three groups according to its value: <1.0, 1.0-1.2, and ≥1.2;

[0018] 2) For each LOI group, the PCI set corresponding to each 1 million ESAL increment from the road section’s opening to a specific service time is calculated;

[0019] 3) Draw box plots and stacked plots in groups to determine the decline of PCI with ESAL under different LOIs.

[0020] Furthermore, the methods for constructing the PCI prediction model, comparing the prediction accuracy, and evaluating the importance of LOI in step 4 are as follows:

[0021] 1) Analyze the factors affecting pavement damage and determine the independent variable set for the PCI prediction model. These variables include road age, lane location, whether it is a pavement or bridge deck, modified asphalt layer thickness, asphalt surface layer thickness, asphalt surface layer gradation type, base layer thickness, base layer material, ESAL, overload rate, LOI, proportion of high temperature days, proportion of low temperature days, proportion of rainy days, annual average daily temperature, and annual average daily precipitation. Based on these variables, a dataset was constructed for establishing the PCI prediction model, with 80% of the data used as the training set and 20% as the test set.

[0022] 2) One-hot encoding and Z-score methods were used to standardize the nominal and numerical variables in the independent variables, respectively. Neural network models and random forest models were constructed without and with LOI, respectively. The hyperparameters of the models were tuned using random search. The hyperparameters of the neural network model included the number of hidden layers, the number of hidden layer neurons, the optimizer, the learning rate, the number of training rounds, and the batch size. The hyperparameters of the random forest model included the number of trees, the number of sampled features, the maximum depth of the tree, the minimum number of samples required to split an internal node, the minimum number of samples required to split a leaf node, and whether the sample set was sampled with replacement.

[0023] 3) The R2 coefficient of determination was used to evaluate the prediction accuracy of the model on the test set, and the prediction accuracy of the two machine learning models before and after LOI was considered was compared;

[0024] 4) Evaluate the importance of each independent variable for PCI prediction, focusing on the importance ranking of LOI, and determine the importance of traffic load history characteristics on pavement performance degradation.

[0025] The method fully considers the historical characteristics of traffic loads on long-term service roads, especially the impact of loading sequence on pavement performance degradation, and innovatively proposes quantitative indicators to overcome the limitations of existing traffic load indicators that only focus on cumulative values ​​or average values ​​and cannot effectively measure loading history. This quantification method is simple and easy to use, with good repeatability. Through graphical display and machine learning modeling verification, the key role of loading history characteristics in the development and prediction of pavement damage conditions is clarified, significantly improving prediction accuracy. This invention provides a more scientific and accurate basis for road performance prediction and maintenance decision-making, and has important practical application value and broad guiding significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flow chart for evaluating the historical characteristics of traffic loads during the long-term service life of a road;

[0027] Figure 2 It is the distribution map of LOI index;

[0028] Figure 3 The decline of PCI with ESAL at different LOI levels;

[0029] Figure 4 Rank the importance of independent variables in the PCI prediction model. DETAILED DESCRIPTION

[0030] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0031] A method for evaluating the historical characteristics of traffic loads during the long-term service of a road, such as Figure 1As shown, the following steps are included:

[0032] S1. Collect data on the basic characteristics, pavement structure materials, and traffic load conditions, pavement damage conditions, and weather conditions of roads that have been in service for ten years or more without maintenance. Divide the highway into multiple sub-sections based on the type of pavement (such as pavement or bridge deck), number of lanes, driving direction, and structural and traffic characteristics. For sections longer than 1.5 kilometers, further subdivide them at intervals of 1 kilometer. Match the time nodes of all pavement performance tests over the years to each section of approximately 1 kilometer in length, associate them with the corresponding traffic flow and weather condition variables, and calculate the service time.

[0033] S2. Determine the overload rate generated during the service time of the road section corresponding to half of the given standard axle load (ESAL) value and the ESAL, and calculate their ratio, which is defined as the loading order index (LOI). Figure 2 The figure shows the distribution of the LOI index. It can be found that a considerable proportion of road sections had a high overload rate in the early stage, resulting in an LOI greater than 1, that is, the initial overload rate was high, but it was later effectively controlled and the overload rate decreased.

[0034] S3. Group the LOI indicators. For each road section with a service time of more than ten years, divide the LOI into three groups: <1.0, 1.0-1.2, and ≥1.2. For each LOI group, calculate the PCI sum corresponding to each 1 million ESAL increment from the road section's opening to a specific service time, and draw a box plot for each group, such as Figure 3 As shown in the figure, the decay of PCI with ESAL under different LOI is analyzed. It can be seen from the figure that the larger the LOI value, the higher the decay rate of PCI, which shows that different loading sequences will affect the damage condition of asphalt pavement.

[0035] S4. Analyze the factors affecting the pavement damage condition and determine the independent variable set of the PCI prediction model, including road age, lane, road surface or bridge deck, modified asphalt layer thickness, asphalt surface layer thickness, asphalt surface layer gradation type, base layer thickness, base layer material, ESAL, overload rate, LOI, proportion of high temperature days, proportion of low temperature days, proportion of rainy days, annual average daily temperature and annual average daily precipitation. Based on this, construct a data set for establishing the PCI prediction model. 80% of the data is used as the training set and 20% of the data is used as the test set. Use the one-hot encoding and Z-score method to standardize the nominal variables and numerical variables in the independent variables respectively. Without considering L and considering L Under the condition of OI, a neural network model and a random forest model were constructed respectively, and the random search method was used to tune the hyperparameters in the model. The hyperparameters of the neural network model include the number of hidden layers, the number of hidden layer neurons, the optimizer, the learning rate, the number of training rounds, and the batch size. The hyperparameters of the random forest model include the number of trees, the number of sampled features, the maximum depth of the tree, the minimum number of samples required to split internal nodes, the minimum number of samples required for leaf nodes, and whether the sample set is sampled with replacement. The coefficient of determination R2 was used to evaluate the prediction accuracy of the model on the test set. The prediction accuracy of the two machine learning models before and after LOI was compared, as shown in Table 1.

[0036] Table 1 Model evaluation results

[0037]

[0038] As can be seen, the performance of both the neural network and random forest models improved slightly after adding LOI, indicating that LOI contributes to the prediction of pavement damage, and that the performance of the random forest model is slightly better than that of the neural network model. Therefore, the random forest model was used to evaluate the importance of each independent variable in PCI prediction. As shown in the figure, it can be seen that among the three traffic load-related indicators, LOI contributes the most to predicting pavement damage, even exceeding common indicators such as ESAL and overload rate, demonstrating the importance of considering traffic load history characteristics in pavement performance prediction.

Claims

1. A method for evaluating historical characteristics of traffic loads during long-term road service, characterized in that: The following steps are involved: Step 1: Collect basic characteristics and pavement structural materials of road sections that have been in service for ten years or more without maintenance, as well as data on traffic load conditions, pavement damage conditions, and weather conditions year by year during the service period; Step 2: Determine the overload rate generated during the service time of the road section corresponding to half of the given standard axle load application times ESAL and ESAL, and calculate their ratio, which is defined as the loading sequence index LOI; The calculation method of the loading order index LOI is as follows: 1) For a certain road section with a service time of more than 10 years , determine its corresponding , search Corresponding service time: ,in Indicates a Time to serve Mapping; 2) Using axle load spectrum information, calculate the road section from opening to service and The corresponding overload rates for each year are: ,in Indicates from opening to The annual overload rate, Represents a set of axis types, including single axis, double axis and triple axis, Indicates a specific axis type, Indicates time When the shaft type Overloaded axles, Indicates time When the shaft type Total axis times; 3) Calculate the service time of the road section Corresponding loading order indicators: ; Step 3: Group the LOI indicators and use box plots to compare the decline of the pavement damage index PCI with ESAL under different LOIs; Step 4: Use random forest and artificial neural network algorithms to build PCI prediction models, compare the changes in model prediction accuracy when LOI is used as an independent variable, and compare the importance ranking of LOI in the independent variable set.

2. A method for evaluating historical characteristics of traffic loads during long-term service of a road as claimed in claim 1, characterized in that: The data items that need to be collected in step 1 include: basic characteristics of the road section: road age, lane, road surface or bridge deck; pavement structural materials: modified asphalt layer thickness, asphalt surface layer thickness, asphalt surface layer gradation type, base layer thickness, base layer material; annual traffic load conditions: ESAL, axle load spectrum; annual pavement damage conditions: PCI; weather conditions: proportion of high temperature days, proportion of low temperature days, proportion of rainy days, annual average daily temperature, and annual average daily precipitation.

3. A method for evaluating historical characteristics of traffic loads during long-term service of a road as claimed in claim 1, characterized in that: The graphical display method in step 3 is as follows: 1) For each road section with a service time of more than ten years, the LOI value was calculated and divided into three groups according to its value: <1.0, 1.0-1.2, and ≥1.2; 2) For each LOI group, the PCI set corresponding to each 1 million ESAL increment from the road section’s opening to a specific service time is calculated; 3) Draw boxplots and stacked plots in groups to determine the decline of PCI with ESAL under different LOIs.

4. A method for evaluating historical characteristics of traffic loads during long-term service of a road as claimed in claim 1, characterized in that: The methods for constructing the PCI prediction model, comparing the prediction accuracy, and evaluating the importance of LOI in step 4 are as follows: 1) Analyze the factors affecting pavement damage and determine the independent variable set for the PCI prediction model. These variables include road age, lane location, whether it is a pavement or bridge deck, modified asphalt layer thickness, asphalt surface layer thickness, asphalt surface layer gradation type, base layer thickness, base layer material, ESAL, overload rate, LOI, proportion of high temperature days, proportion of low temperature days, proportion of rainy days, annual average daily temperature, and annual average daily precipitation. Based on these variables, a dataset was constructed for establishing the PCI prediction model, with 80% of the data used as the training set and 20% as the test set. 2) Use one-hot encoding and Z-score methods to standardize the nominal and numerical variables in the independent variables, respectively. Construct neural network models and random forest models without and with LOI, respectively, and use random search to tune the hyperparameters in the models. The hyperparameters of the neural network model include the number of hidden layers, the number of hidden layer neurons, the optimizer, the learning rate, the number of training rounds, and the batch size. The hyperparameters of the random forest model include the number of trees, the number of sampled features, the maximum tree depth, the minimum number of samples required to split an internal node, the minimum number of samples required to split a leaf node, and whether to perform sampling with replacement on the sample set. 3) The R² coefficient of determination was used to evaluate the prediction accuracy of the model on the test set, and the prediction accuracy of the two machine learning models before and after considering LOI was compared; 4) Evaluate the importance of each independent variable for PCI prediction, focusing on the importance ranking of LOI and determining the importance of traffic load history characteristics on pavement performance degradation.

Images