Pavement performance and economic efficiency are researched on the perpetual test pavement of Yijiang-Suzhou Express Highway in Jiangsu province, China. Test sections were continuously monitored. The conditions and de...Pavement performance and economic efficiency are researched on the perpetual test pavement of Yijiang-Suzhou Express Highway in Jiangsu province, China. Test sections were continuously monitored. The conditions and developing laws of deflection, rutting and cracking are compared among the perpetual pavement with the rich binder layer （RBL）, the perpetual pavement without the RBL, and the conventional semi-rigid asphalt pavement in the past eight years after opening for traffic. Economical evaluation is conducted via life cycle cost analysis （LCCA）. Based on the performance comparison and LCCA analysis, sections with the RBL have good crack resistance, but they are not very satisfactory in the aspect of permanent deformation; the conventional semi-rigid asphalt pavement is the least economic one due to requiring more frequent maintenance. Research results show that the perpetual pavement without RBL is a more appropriate structure for the test site.展开更多
In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based...In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based on principal component analysis(PCA)and one-dimensional convolution neural network(1D-CNN)is proposed in this paper.Firstly,multiple state parameters corresponding to massive cycles of aeroengine are collected and brought into PCA for dimensionality reduction,and principal components are extracted for further time series prediction.Secondly,the 1D-CNN model is constructed to directly study the mapping between principal components and RUL.Multiple convolution and pooling operations are applied for deep feature extraction,and the end-to-end RUL prediction of aeroengine can be realized.Experimental results show that the most effective principal component from the multiple state parameters can be obtained by PCA,and the long time series of multiple state parameters can be directly mapped to RUL by 1D-CNN,so as to improve the efficiency and accuracy of RUL prediction.Compared with other traditional models,the proposed method also has lower prediction error and better robustness.展开更多
基金The Science and Technology Project of Jiangsu Provincial Communications Department(No.7621000078)
文摘Pavement performance and economic efficiency are researched on the perpetual test pavement of Yijiang-Suzhou Express Highway in Jiangsu province, China. Test sections were continuously monitored. The conditions and developing laws of deflection, rutting and cracking are compared among the perpetual pavement with the rich binder layer （RBL）, the perpetual pavement without the RBL, and the conventional semi-rigid asphalt pavement in the past eight years after opening for traffic. Economical evaluation is conducted via life cycle cost analysis （LCCA）. Based on the performance comparison and LCCA analysis, sections with the RBL have good crack resistance, but they are not very satisfactory in the aspect of permanent deformation; the conventional semi-rigid asphalt pavement is the least economic one due to requiring more frequent maintenance. Research results show that the perpetual pavement without RBL is a more appropriate structure for the test site.
基金supported by Jiangsu Social Science Foundation(No.20GLD008)Science,Technology Projects of Jiangsu Provincial Department of Communications(No.2020Y14)Joint Fund for Civil Aviation Research(No.U1933202)。
文摘In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based on principal component analysis(PCA)and one-dimensional convolution neural network(1D-CNN)is proposed in this paper.Firstly,multiple state parameters corresponding to massive cycles of aeroengine are collected and brought into PCA for dimensionality reduction,and principal components are extracted for further time series prediction.Secondly,the 1D-CNN model is constructed to directly study the mapping between principal components and RUL.Multiple convolution and pooling operations are applied for deep feature extraction,and the end-to-end RUL prediction of aeroengine can be realized.Experimental results show that the most effective principal component from the multiple state parameters can be obtained by PCA,and the long time series of multiple state parameters can be directly mapped to RUL by 1D-CNN,so as to improve the efficiency and accuracy of RUL prediction.Compared with other traditional models,the proposed method also has lower prediction error and better robustness.
