Pavement Performance Prediction Based on Integrated Particle Swarm Optimization-Gray Back Propagation Neural Network Model

Authors

LI Xuelian, School of Transportation, Changsha University of Science & Technology, Changsha, Hunan 410114, ChinaFollow
HUANG Yan, School of Transportation, Changsha University of Science & Technology, Changsha, Hunan 410114, China
LI Xiong, School of Transportation, Changsha University of Science & Technology, Changsha, Hunan 410114, China

Abstract

The existing performance prediction model of asphalt pavements is limited by low accuracy and a lack of historical measured data. To address this issue and maximally optimize the pavement maintenance decision, a pavement performance prediction model integrating particle swarm optimization (PSO), gray model (GM), and back propagation neural network (BPNN) was proposed based on network management. Meanwhile, the model was compared with the GM (1, 1) model, support vector regression (SVR) model, BPNN model, and PSO-BPNN model. Then, the prediction accuracy of the models was evaluated by the mean absolute error (EMAE), the root mean square error (ERMSE), and the mean absolute percentage error (EMAPE). The fitting results of the PSO-gray BPNN model were assessed by the R-squared (R2). The results indicate that by optimizing the BPNN model with the PSO algorithm and the GM model, the accuracy of the PSO-gray BPNN model is significantly improved. Based on the performance data of 14 expressways in Hubei Province, a high correlation between the predicted values of the model and the measured data is found. For the IPCI index, the value of EMAE, ERMSE, and EMAPE is reduced to 1.721 8, 2.296 8, and 1.897 1, respectively. The value of R2 could be up to 0.919. Compared to the other four models, the PSO-gray BPNN model has the smallest values of prediction error for IPCI, IRQI, IRDI, and ISRI, fully showing the superiority of the model. With higher prediction accuracy, the proposed PSO-gray BPNN model has prediction results more consistent with the actual situation, providing an accurate and reliable technical support for the prediction of pavement performance at the network level.

Publication Date

10-27-2025

DOI

10.14048/j.issn.1671-2579.2025.05.005

First Page

46

Last Page

52

Submission Date

November 2025

Recommended Citation

Xuelian, LI; Yan, HUANG; and Xiong, LI (2025) "Pavement Performance Prediction Based on Integrated Particle Swarm Optimization-Gray Back Propagation Neural Network Model," Journal of China & Foreign Highway: Vol. 45: Iss. 5, Article 5.
DOI: 10.14048/j.issn.1671-2579.2025.05.005
Available at: https://zwgl1980.csust.edu.cn/journal/vol45/iss5/5

Reference

[1]刘海斌.基于 EMD-SVM-LSTM 组合的桥梁变形响应预测模型研究 [J].公路,2025,70(3):204-210.LIU Haibin.Research on prediction model of bridge deformation response based on EMD-SVM-LSTM combination [J].Highway,2025,70(3):204-210.
[2]敬超,张金喜.沥青路面性能预测研究综述 [J].中外公路,2017,37(5):31-35.JING Chao,ZHANG Jinxi.Summary of asphalt pavement performance prediction research [J].Journal of China & Foreign Highway,2017,37(5):31-35.
[3]苏卫国,吴启槟,王景霄.基于 GM(1,1)+BP神经网络组合模型的路用性能预测研究 [J].昆明理工大学学报 (自然科学版),2022,47(1):147-155.SU Weiguo,WU Qibin,WANG Jingxiao.Road performance prediction based on GM (1,1)+BP neural network combined model [J].Journal of Kunming University of Science and Technology (Natural Sciences),2022,47(1):147-155.
[4]ULLIDTZ P.Mathematical model of pavement performance under moving wheel load [C]// Thousand Oaks,California：Transportation Research Record,2006.
[5]周鹏飞,温胜强,康海贵.基于马尔可夫链与神经网络组合的路面使用性能预测 [J].重庆交通大学学报 (自然科学版),2012,31(5):997-1001.ZHOU Pengfei,WEN Shengqiang,KANG Haigui.Pavement performance combining forecasting based on BP neural network and Markov model [J].Journal of Chongqing Jiaotong University (Natural Science),2012,31(5):997-1001.
[6]武建民,刘大彬,李福聪,等.基于时间序列分析法的沥青路面使用性能预测 [J].长安大学学报 (自然科学版),2015,35(3):1-7.WU Jianmin,LIU Dabin,LI Fucong,et al.Performance prediction of asphalt pavement maintenance based on time series analysis [J].Journal of Chang ’an University (Natural Science Edition),2015,35(3):1-7.
[7]郭蕾,蔡育宏,张俊,等.基于频率响应与图像特征提取的动车组变压器绕组状态诊断方法研究 [J].铁道学报,2024,46(4):47-56.GUO Lei,CAI Yuhong,ZHANG Jun,et al.Research on diagnosis method for state of transformer winding of trainset based on frequency response and image feature extraction [J].Journal of the China Railway Society,2024,46(4):47-56.
[8]曹雪娟,李小宇,吴博文,等.基于 PCA-GA-LSSVMR 的高速公路沥青路面行驶质量预测 [J].重庆交通大学学报(自然科学版),2023,42(5):35-43.CAO Xuejuan,LI Xiaoyu,WU Bowen,et al.Driving quality prediction of highway asphalt pavement based on PCA-GA-LSSVMR [J].Journal of Chongqing Jiaotong University (Natural Science),2023,42(5):35-43.
[9]KARBAL LAEEZADEH N,MOHAMMADZADEH S D,SHAMSHIRBAND S,et al.Prediction of remaining service life of pavement using an optimized support vector machine (case study of Semnan –Firuzkuh road)[J].Engineering Applications of Computational Fluid Mechanics,2019,13(1):188-198.
[10]贺得荣.基于组合预测模型对公路沥青路面使用性能预测的研究 [J].公路工程,2015,40(6):264-270.HE Derong.Study on asphalt pavement performance prediction research based on the combination forecast model [J].Highway Engineering,2015,40(6):264-270.
[11]乔建刚,范颖蓉,王彦萍,等.基于 PSO-LSTM 模型的沥青路面 PCI值预测研究 [J].公路,2025,70(4):52-59.QIAO Jiangang,FAN Yingrong,WANG Yanping,et al.Research on road PCI value prediction based on PSO-LSTM model [J].Highway,2025,70(4):52-59.
[12]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):7534970.
[13]俞竞伟,傅睿,李雄威,等.基于混合神经网络 (GANN)的沥青路面使用性能预测模型 [J].桂林理工大学学报,2016,36(3):521-525.YU Jingwei,FU Rui,LI Xiongwei,et al.Asphalt pavement performance prediction model based on hybrid artificial neural network [J].Journal of Guilin University of Technology,2016,36(3):521-525.
[14]刘媛媛,司君岭,郑好,等.基于不确定性量化理论的寒区道路服役性能预测及评价研究 [J].中外公路,2025,45(1):60-66.LIU Yuanyuan,SI Junling,ZHENG Hao,et al.Prediction and evaluation of road service performance in cold regions based on uncertainty quantification theory [J].Journal of China & Foreign Highway,2025,45(1):60-66.
[15]黄晓明.路基路面工程 [M].7版.北京:人民交通出版社股份有限公司,2023.HUANG Xiaoming.Road subgrade and pavement engineering [M].7th ed.Beijing:China Communications Press Co.,Ltd.,2023.
[16]崔峰,王汉封,舒卓乐.基于 PSO-BP 神经网络的隧道内气动压力幅值预测 [J].中南大学学报 (自然科学版),2023,54(9):3752 -3761.CUI Feng,WANG Hanfeng,SHU Zhuole.Prediction of aerodynamic pressure amplitude in tunnel based on PSO-BP neural network [J].Journal of Central South University (Science and Tech nology),2023,54(9):3752 -3761.
[17]姚勇,闫宇,孙博文,等.基于 DE-BP神经网络的混凝土箱梁热学参数反分析 [J].中外公路,2025,45(3):112-120.YAO Yong,YAN Yu,SUN Bowen,et al.Inverse analysis of thermal parameters of concrete box girder based on DE-BP neural network [J].Journal of China & Foreign Highway,2025,45(3):112-120.
[18]交通运输部公路科学研究院.公路技术状况评定标准:JTG 5210—2018 [S].北京:人民交通出版社股份有限公司,2018.Research Institute of Highway Ministry of Transport.Highway performance assessment standards:JTG 5210—2018 [S].Beijing:China Communications Press Co.,Ltd.,2018.
[19]张安顺.基于 LSTM+Transformer 的冻融循环作用下路基土永久变形预估模型 [J].中外公路,2025,45(1):67-72.ZHANG Anshun.Permanent deformation prediction model of subgrade soil under freeze-thaw cycles based on LSTM and transformer [J].Journal of China & Foreign Highway,2025,45(1):67-72.
[20]蒋玮,许庆正,单金焕,等.基于熵值赋权灰色马尔可夫法的沥青路面使用性能预测 [J].中国科技论文,2022,17(6):595-601.JIANG Wei,XU Qingzheng,SHAN Jinhuan,et al.Prediction of asphalt pavement performance based on entropy weighted grey Markov method [J].China Sciencepaper,2022,17(6):595-601.
[21]熊远南.基于改进灰色 ‒多元回归组合预测模型的燃煤电 厂 智 慧 水 务 研 究 [J].化 工 进 展,2020,39(增 刊 2):393-400.XIONG Yuannan.Smart water affair of coal-fired power plant based on improved combination prediction model of grey system and regression analysis [J].Chemical Industry and Engineering Progress,2020,39(sup 2):393-400.
[22]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 Lili.Study on prediction method of asphalt pavement service performance evevolution based on multi-source[D].Xi’an:Chang’an University,2023.
[23]闫鹏程,尚松行,张超银,等.改进 BP神经网络算法对煤矿水源的分类研究 [J].光谱学与光谱分析,2021,41(7):2288 -2293.YAN Pengcheng,SHANG Songhang ZHANG Chaoyin,et al.Classification of coal mine water sources by improved BP neural network algorithm [J].Spectroscopy and Spectral Analysis,2021,41(7):2288 -2293.