Environmental factors and truck traffic loads have significant impacts on asphalt pavement performance.This study implements geospatial hot spot,correlation,and decision tree analyses to investigate the impacts of env...Environmental factors and truck traffic loads have significant impacts on asphalt pavement performance.This study implements geospatial hot spot,correlation,and decision tree analyses to investigate the impacts of environmental factors and truck traffic loads on asphalt pavement performance.A pavement database with 1725 asphalt pavement sections from the Long-Term Pavement Performance(LTPP)program was built and analyzed using geospatial hot spot analysis to characterize the spatial patterns of environmental factors,truck traffic loads,and asphalt pavement distresses in different climatic regions across the United States and Canada.The statistical correlation analysis was conducted to identify significant correlations among hot spots of environmental factors,truck traffic loads,and asphalt pavement distresses.The decision tree model,which is a supervised machine learning method,was used to assess pavement performance in an area that is associated with higher risks of distress based on contributing environmental and traffic conditions.The hot spot analysis showed that the pavement sections located in the dry no-freeze region had higher percentages of hot spots of truck traffic loads and associated loadinduced distresses,such as fatigue cracking,longitudinal wheel path cracking,and rutting.In the dry no-freeze region,higher percentages of pavement sections were also classified as hot spots of transverse cracking.The pavement sections in the wet freeze region are more likely to experience longitudinal non-wheel path cracking and surface roughness.The decision tree models were built to identify the likeliness of hot spots of asphalt pavement distresses using environmental factors and truck traffic loads.These decision tree models provide enhanced decision-making information in pavement design and maintenance.展开更多
Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments,enabling the achievement of better pavement performance with limited finan...Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments,enabling the achievement of better pavement performance with limited financial resources.However,due to the intricate influence of numerous factors on pavement performance deterioration,improving the accuracy of pavement performance prediction poses a challenge for conventional models.Therefore,the aim of this study is to establish a machine learning-based pavement performance prediction model.First,this study considers five factors that affect pavement performance,including pavement initial performance indicators,traffic loads,weather,pavement structure,and maintenance measures,and identifies 15 specific indicators that affect pavement performance based on these five factors.Then,based on the the long-term pavement performance(LTPP)database,the study screens and summarizes these indicators,obtaining 2464 high-quality pavement performance data for pavement conditions index(PCI)prediction and 3238 high-quality pavement performance data for international roughness index(IRI)prediction.Finally,three distinct prediction models are established,namely,the fully connected neural network(FCNN)model,the long short-term memory(LSTM)model,and the combined LSTM-attention model.The study shows that the LSTM-attention model performs significantly better than the FCNN and LSTM models,with an R2 coefficient of determination of 0.81 for PCI and 0.79 for IRI.The innovation of this paper is that the authors have introduced the attention mechanism on the basic of the LSTM model,which makes the fitting accuracy of the prediction model further improved.展开更多
文摘Environmental factors and truck traffic loads have significant impacts on asphalt pavement performance.This study implements geospatial hot spot,correlation,and decision tree analyses to investigate the impacts of environmental factors and truck traffic loads on asphalt pavement performance.A pavement database with 1725 asphalt pavement sections from the Long-Term Pavement Performance(LTPP)program was built and analyzed using geospatial hot spot analysis to characterize the spatial patterns of environmental factors,truck traffic loads,and asphalt pavement distresses in different climatic regions across the United States and Canada.The statistical correlation analysis was conducted to identify significant correlations among hot spots of environmental factors,truck traffic loads,and asphalt pavement distresses.The decision tree model,which is a supervised machine learning method,was used to assess pavement performance in an area that is associated with higher risks of distress based on contributing environmental and traffic conditions.The hot spot analysis showed that the pavement sections located in the dry no-freeze region had higher percentages of hot spots of truck traffic loads and associated loadinduced distresses,such as fatigue cracking,longitudinal wheel path cracking,and rutting.In the dry no-freeze region,higher percentages of pavement sections were also classified as hot spots of transverse cracking.The pavement sections in the wet freeze region are more likely to experience longitudinal non-wheel path cracking and surface roughness.The decision tree models were built to identify the likeliness of hot spots of asphalt pavement distresses using environmental factors and truck traffic loads.These decision tree models provide enhanced decision-making information in pavement design and maintenance.
基金supported by the Science and Technology Plan of Shandong Transportation Department(No.2021B47)the Key Research and Development Program of Ningxia Science and Technology Department(No.2022BEG02008)the Fundamental Research Funds for the Central Universities(No.22120210027).
文摘Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments,enabling the achievement of better pavement performance with limited financial resources.However,due to the intricate influence of numerous factors on pavement performance deterioration,improving the accuracy of pavement performance prediction poses a challenge for conventional models.Therefore,the aim of this study is to establish a machine learning-based pavement performance prediction model.First,this study considers five factors that affect pavement performance,including pavement initial performance indicators,traffic loads,weather,pavement structure,and maintenance measures,and identifies 15 specific indicators that affect pavement performance based on these five factors.Then,based on the the long-term pavement performance(LTPP)database,the study screens and summarizes these indicators,obtaining 2464 high-quality pavement performance data for pavement conditions index(PCI)prediction and 3238 high-quality pavement performance data for international roughness index(IRI)prediction.Finally,three distinct prediction models are established,namely,the fully connected neural network(FCNN)model,the long short-term memory(LSTM)model,and the combined LSTM-attention model.The study shows that the LSTM-attention model performs significantly better than the FCNN and LSTM models,with an R2 coefficient of determination of 0.81 for PCI and 0.79 for IRI.The innovation of this paper is that the authors have introduced the attention mechanism on the basic of the LSTM model,which makes the fitting accuracy of the prediction model further improved.
