|Table of Contents|

Pavement condition prediction based on theory-data collabrative analysis(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2025年1期
Page:
38-49
Research Field:
道路工程
Publishing date:

Info

Title:
Pavement condition prediction based on theory-data collabrative analysis
Author(s):
LIU Wen-bo1;  YANG Xu1; 2;  WANG Hai-nian1;  XU Kun1;  FAN Tai-bo1
(1. School of Highway, Chang'an University, Xi'an 710064, Shaanxi, China; 2. School of Future Transportation, Chang'an University, Xi'an 710064, Shaanxi, China)
Keywords:
road engineering;  pavement performance prediction;  dual-driven;  theory-data;  fusion model;  TCN-GRU
PACS:
U418.6
DOI:
10.19721/j.cnki.1671-8879.2025.01.004
Abstract:
The deformation of the road and the structural strength are important contents of pavement performance evaluation. The precise prediction of the above two is of significant importance for road scientific maintenance decision-making. However, the development of the current research in prediction accuracy still needs to be improved. A theory-data dual-driven pavement performance prediction method is proposed to improve the pavement performance prediction effect. Firstly, the key influencing factors of pavement performance development are determined based on the influence mechanism theory. Then, based on the analysis results and the Beijing ring road full-scale test site data, the model input and output variables are determined. Finally, a temporal convolutional network-gated recurrent unit(TCN-GRU)fusion prediction model is proposed to predict the development of rutting and bearing capacity. This model is compared with the basic single model and the temporal convolutional network-long short term memory(TCN-LSTM)fusion model. The research results show that for rut depth prediction, the TCN-GRU achieves the best prediction performance, with MSE, RMSE, MAE, and R2 values of 22.635, 4.758, 3.319, and 0.940, respectively. Compared to the single models(TCN, GRU), R2 is improved by 0.53% and 0.86%, respectively. For deflection value development prediction, the TCN-GRU also achieves the best prediction performance, with MSE, RMSE, MAE, and R2 values of 8.009, 2.830, 1.819, and 0.850, respectively. R2 is improved by 5.85% and 2.04% compared to the single models(TCN, GRU). The proposed TCN-GRU demonstrates the best prediction performance for road rutting and bearing capacity development. It fully combines the long-term dependency modeling capability of TCN and the efficient state update advantage of GRU, improving the prediction accuracy and efficiency of sequence data. It can accurately predict the development of rutting and bearing capacity for specific roads based on historical data, providing data support for scientific maintenance decision-making by highway maintenance management departments.8 tabs, 9 figs, 30 refs.

References:

[1] 尹国军.沥青路面使用性能评价及预测研究[J].四川建材,2024,50(1):174-175,178.
YIN Guo-jun.Research on evaluation and prediction of asphalt pavement performance[J].Sichuan Building Materials,2024,50(1):174-175,178.
[2]黄 东,尹雨阳,谢学斌,等.路基沉降预测的灰色自记忆模型[J].工业建筑,2023,53(2):569-572.
HUANG Dong,YIN Yu-yang,XIE Xue-bin,et al.Grey self-memory model for roadbed settlement prediction[J].Industrial Construction,2023,53(2):569-572.
[3]邓聚龙.灰色系统理论与计量未来学[J].未来与发展,1983(3):20-23.
DENG Ju-long.Grey system theory and quantitative futurology[J].Future and Development,1983(3):20-23.
[4]严世涛,唐忠国,邹一强.基于灰色理论的沥青路面使用性能衰变预测研究[J].西部交通科技,2020(2):17-21.
YAN Shi-tao,TANG Zhong-guo,ZOU Yi-qiang.Research on prediction of asphalt pavement performance decay based on grey theory[J].Western China Communication Science and Technology,2020(2):17-21.
[5]杨雨晴,胡庆国.永州市高速公路沥青路面使用性能预测研究[J].公路与汽运,2021(6):168-171,178.
YANG Yu-qing,HU Qing-guo.Research on performance prediction of asphalt pavement on Yongzhou Expressway[J].Highways and Automotive Applications,2021(6):168-171,178.
[6]于保华,高玉梅,杨婉怡,等.北京市京承高速沥青路面性能衰变规律分析[J].山东交通科技,2021(5):1-2,9.
YU Bao-hua,GAO Yu-mei,YANG Wan-yi,et al.Analysis on performance decay law of asphalt pavement in Beijing-Chengde Expressway[J].Shandong Transportation Science and Technology,2021(5):1-2,9.
[7]何志敏,孙晓磊,杨婉怡,等.北京市六环高速公路沥青路面性能预测模型及精度分析[J].市政技术,2020,38(6):34-36.
HE Zhi-min,SUN Xiao-lei,YANG Wan-yi,et al.Performance prediction model and accuracy analysis of asphalt pavement of Beijing Sixth Ring Expressway[J].Municipal Engineering Technology,2020,38(6):34-36.
[8]ABDULLAH N M,JA MAL K M,KARIM B M R U,et al.Cracking models for HMA overlay treatment of composite pavements in Louisiana[J].International Journal of Pavement Engineering,2020,22(14):1-12.
[9]丁世飞,孙玉婷,梁志贞,等.弱监督场景下的支持向量机算法综述[J].计算机学报,2024,47(5):987-1009.
DING Shi-fei,SUN Yu-ting,LIANG Zhi-zhen,et al.A review of support vector machine algorithms in weakly supervised scenarios[J].Journal of Computer Science and Technology,2024,47(5):987-1009.
[10]段哲政.一级公路沥青路面性能评价——以国道108省道汾屯线、东夏线为例[J].四川建材,2024,50(3):177-179.
DUAN Zhe-zheng.Performance evaluation of first-class highway asphalt pavement:Taking Fentun Line and Dongxia Line of National Highway 108 and Provincial Highway as examples[J].Sichuan Building Materials,2024,50(3):177-179.
[11]张丽娟,黄 晟,梅 诚,等.基于K最邻近算法的沥青路面使用性能预测[J].公路工程,2020,45(3):73-78,85.
ZHANG Li-juan,HUANG Sheng,MEI Cheng,et al.Asphalt pavement performance prediction based on K nearest neighbor algorithm[J].Highway Engineering,2020,45(3):73-78,85.
[12]张金喜,郭旺达,宋 波,等.基于随机森林的沥青路面性能预测[J].北京工业大学学报,2021,47(11):1256-1263.
ZHANG Jin-xi,GUO Wang-da,SONG Bo,et al.Asphalt pavement performance prediction based on random forest[J].Journal of Beijing University of Technology,2021,47(11):1256-1263.
[13]王笑风,毛海臻,杨 博,等.基于深度学习LSTM网络的沥青路面性能预测研究[J].公路交通科技(应用技术版),2020,16(8):4-7.
WANG Xiao-feng,MAO Hai-zhen,YANG Bo,et al.Research on asphalt pavement performance prediction based on deep learning LSTM network[J].Journal of Highway and Transportation Research and Development(Applied Technology Edition),2020,16(8):4-7.
[14]ABDELAZIZ N,ABD EL-HAKIM R T,EL-BADAWY S M,et al.International roughness index prediction model for flexible pavements[J].International Journal of Pavement Engineering,2020,21(1):88-99.
[15]JIYU X,MITSUYOSHI A,M I F D,et al.Reliability-based life-cycle cost design of asphalt pavement using artificial neural networks[J].Structure and Infrastructure Engineering,2021,17(6):872-886.
[16]WANG Z,GUO N,WANG S,et al.Prediction of highway asphalt pavement performance based on Markov chain and artificial neural network approach[J].The Journal of Supercomputing,2020,77(2):1-23.
[17]肖 磊,颜俊键,聂 文,等.基于组合预测模型的沥青路面养护方案规划[J].广东公路交通,2022,48(1):1-6,19.
XIAO Lei,YAN Jun-jian,NIE Wen,et al.Asphalt pavement maintenance program planning based on combined prediction model[J].Guangdong Highway Communications,2022,48(1):1-6,19.
[18]CAI L,WU F,LEI D.Pavement condition index prediction using fractional order GM(1,1)model[J].IEEJ Transactions on Electrical and Electronic Engineering,2021,16(8):1099-1103.
[19]ZHU Y,CHEN J,WANG K,et al.Research on performance prediction of highway asphalt pavement based on Grey-Markov model[J].Transportation Research Record,2022,2676(4):194-209.
[20]WANG X C,ZHAO J,LI Q Q,et al.A hybrid model for prediction in asphalt pavement performance based on support vector machine and grey relation analysis[J].Journal of Advanced Transportation,2020,2020(1):1-14.
[21]LI Z,ZHANG J,LIU T,et al.Using PSO-SVR algorithm to predict asphalt pavement performance[J].Journal of Performance of Constructed Facilities,2021,35(6):04021094.
[22]KARBALLAEEZADEH N,MOHAMMADZADEH D S,MOAZEMI D,et al.Smart structural health monitoring of flexible pavements using machine learning methods[J].Coatings,2020,10(11):1100.
[23]马子媛,李海莲,蔺望东.基于PCA-IPSO-RBF神经网络的沥青路面破损状况预测[J].大连理工大学学报,2022,62(2):197-205.
MA Zi-yuan,LI Hai-lian,LIN Wang-dong.Prediction of asphalt pavement damage condition based on PCA-IPSO-RBF neural network[J].Journal of Dalian University of Technology,2022,62(2):197-205.
[24]尚千里,田 波,李思李,等.沥青路面车辙LSTM-BPNN特征融合预测模型研究[J].中外公路,2021,41(4):70-75.
SHANG Qian-li,TIAN Bo,LI Si-li,et al.Research on LSTM-BPNN feature fusion prediction model for asphalt pavement rutting[J].Journal of China and Foreign Highway,2021,41(4):70-75.
[25]凌冲宇.基于多源数据的某高速公路沥青路面预养护决策研究[D].长沙:中南大学,2023.
LING Chong-yu.Research on pre-maintenance decision of asphalt pavement of a highway based on multi-source data[D].Changsha:Central South University,2023.
[26]裴莉莉.基于多源感知数据的沥青路面服役性能演变预测方法研究[D].西安:长安大学,2023.
PEI Li-li.Research on prediction method of asphalt pavement service performance evolution based on multi-source sensing data[D].Xi'an:Chang'an University,2023.
[27]孙 昕.高速公路路面性能预测模型可靠性及养护优化策略[D].贵阳:贵州大学,2024.
SUN Xin.Reliability of highway pavement performance prediction model and maintenance optimization strategy[D].Guiyang:Guizhou University,2024.
[28]KOOKJIN L,JAIDEEP R,COSMIN S.The predictive skill of convolutional neural networks models for disease forecasting[J].PloS One,2021,16(7):254-319.
[29]XIAOKE H,XIAOMIN Z,HONGFEI L,et al.Enhanced predictive modeling of hot rolling work roll wear using TCN-LSTM-Attention[J].The International Journal of Advanced Manufacturing Technology,2024,131(3/4):1335-1346.
[30]郭 玲,徐青山,郑 乐.基于TCN-GRU模型的短期负荷预测方法[J].电力工程技术,2021,40(3):66-71.
GUO Ling,XU Qing-shan,ZHENG Le.Short-term load forecasting method based on TCN-GRU model[J].Electric Power Engineering Technology,2021,40(3):66-71.

Memo

Memo:
-
Last Update: 2025-02-25