基于群智算法优化的ME车辙预测模型

刘佳佳; 李卓轩; 张伟光; 曹进德

doi:10.21656/1000-0887.460045

基于群智算法优化的ME车辙预测模型

doi: 10.21656/1000-0887.460045

刘佳佳¹,
李卓轩^1,2,
张伟光³,
曹进德^1,2, ,

1. 东南大学数学学院，南京 211189;
2. 中华人民共和国交通运输部综合交通运输理论交通运输行业重点实验室(南京现代综合交通实验室), 南京 211135;
3. 东南大学交通学院，南京 210096

基金项目:

国家重点研发计划（2020YFA0714300）；南京现代综合交通实验室开放课题（MTF2023004）

详细信息

作者简介:
刘佳佳（2001—），女，硕士生（E-mail: 3046838001@qq.com）；李卓轩（1997—），男，博士生（E-mail: 230229338@seu.edu.cn）；张伟光（1986—），男，副教授（E-mail: wgzhang@seu.edu.cn）；曹进德（1963—），男，教授（通信作者. E-mail: jdcao@seu.edu.cn）.

通讯作者:
曹进德（1963—），男，教授（通信作者. E-mail: jdcao@seu.edu.cn）.

中图分类号: U416.217|TP18
计量
- 文章访问数: 16
- HTML全文浏览量: 2
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2025-03-10
- 修回日期: 2025-04-22
- 网络出版日期: 2026-06-04
- 刊出日期: 2026-05-01

Optimization of the ME Rutting Depth Prediction Model Using Swarm Intelligence Algorithms

1. School of Mathematics, Southeast University, Nanjing 211189, P.R. China;
2. Key Laboratory of Transport Industry of Comprehensive Transportation Theory(Nanjing Modern Multimodal Transportation Laboratory), Ministry of Transport of the People’s Republic of China, Nanjing 211135, P.R. China;
3. School of Transportation, Southeast University, Nanjing 210096, P.R. China

摘要

摘要: 车辙，作为沥青路面的一种常见病害，不仅影响着道路的行驶质量和安全性，还在许多国家沥青路面结构设计中占据着举足轻重的地位.为了更准确地预测和评估车辙的演变趋势，对现有车辙预测模型进行改进和优化显得尤为重要.因此，基于RIOHTrack足尺路面加速加载试验环道长期观测数据，对《公路沥青路面设计规范》(JTG D50—2017)中的力学经验车辙性能预测模型进行了全面的调整和优化，引入三个校准参数，分别对常数项系数、温度和累计载荷次数进行校准，以提升模型的预测准确性和泛化能力.接着，提出了一种多策略自适应粒子群算法，引入邻域突变策略，并融合指数自适应惯性权重和正弦自适应学习因子，有效平衡了局部搜索和全局搜索的能力，使得粒子可以更高效地找到最优解.使用该算法求解三个校准参数的值，进一步提升模型的精准度.最后，以RIOHTrack中19种沥青路面的车辙数据为例，使用本文提出的MAPSORME模型进行车辙预测.实验发现，相对于《公路沥青路面设计规范》(JTG D50—2017)中的力学经验车辙预测模型，其拟合性能显著提升，模型预测均方误差MSE大幅降低.
- 沥青路面 /
- 车辙 /
- 参数校准 /
- 多策略自适应粒子群算法
Abstract: Rutting, a common disease of asphalt pavement, not only compromises the road quality and safety, but also plays a critical role in the structural design of asphalt pavement in many countries. To achieve more accurate prediction and evaluation of rutting evolution trends, it is particularly important to improve and optimize the existing rutting depth prediction model. Therefore, based on the long-term observation data of the RIOHTrack full-scale pavement acceleration loading test loop, the mechanical-empirical rutting depth prediction model in the Highway Asphalt Pavement Design Specifications (JTG D50—2017) was comprehensively adjusted and optimized. Three calibration parameters were introduced to calibrate the constant coefficients, temperatures, and cumulative load times, respectively, to improve the prediction accuracy and generalization ability of the model. Subsequently, a multi-strategy adaptive particle swarm optimization (MAPSO) algorithm incorporating a neighborhood mutation strategy and fusing exponential adaptive inertia weights with sinusoidal adaptive learning factors, was proposed. Then this algorithm was used to estimate the values of three calibration parameters to further improve the accuracy of the model. Finally, with the rutting data of 19 types of asphalt pavements in the RIOHTrack as an example, the MAPSO-RME model proposed in this article was applied for rutting depth prediction. The experimental results demonstrate that, compared with the mechanical-empirical rutting depth prediction model in the Highway Asphalt Pavement Design Specifications (JTG D50—2017), the MAPSO-RME model achieves remarkable improvement in fitting performance with a significant reduction in mean squared error (MSE) of prediction.
- asphalt pavement /
- rutting /
- parameter calibration /
- multi-strategy adaptive particle swarm optimization

HTML全文

参考文献(29)

[2]CHEN X, DONG Q, ZHU H, et al. Development of distress condition index of asphalt pavements using LTPP data through structural equation modeling[J]. Transportation Research (Part C): Emerging Technologies,2016,68: 58-69.

GUNGOR O E, AL-QADI I L. All for one: centralized optimization of truck platoons to improve roadway infrastructure sustainability[J]. Transportation Research (Part C): Emerging Technologies,2020,114: 84-98.

[3]ZHENG J, L S, LIU C. Technical system, key scientific problems and technical frontier of long-life pavement[J]. Chinese Science Bulletin,2020,65(30): 3219-3229.

[4]CAREY W N, IRICK P E. The pavement serviceability-performance concept[J]. Highway Research Board Bulletin. 1960.

[5]WU T, CAO J, MA T, et al. Development of rutting forecasting models for distinct asphalt pavement structures in RIOH testing track using different approaches[J]. Construction and Building Materials,2023,368: 130483.

[6]WOREL B, VAN DEUSEN D. Benefits of MnROAD phase-Ⅱ research: MN/RC 2015-19[R]. St Paul, MN: Minnesota Department of Transportation, 2015.

[7]TIMM D H, PRIEST A L. Dynamic pavement response data collection and processing at the NCAT test track[R]. 2004.

[8]Federal Highway Administration. AASHO road test[EB/OL].(2022-03-08)[2025-04-22]. https://www.fhwa.dot.gov/infrastructure/50aasho.cfm.

[9]ZHANG X, OTTO F, OESER M. Pavement moduli back-calculation using artificial neural network and genetic algorithms[J].Construction and Building Materials,2021,287: 123026.

[10]NZ Transport Agency. Canterbury accelerated pavement testing indoor facility[EB/OL]. [2025-04-22]. https://www.nzta.govt.nz/resources/captif/.

[11]WANG X D, ZHOU G L, LIU H Y, et al. Key points of RIOHTRACK testing road design and construction[J]. Journal of Highway and Transportation Research and Development (English Edition), 2020,14(4): 1-16.

[12]RADHAKRISHNAN V, DUDIPALA RR, MAITY A, et al. Evaluation of rutting potential of asphalts using resilient modulus test parameters[J]. Road Materials and Pavement Design,2019,20(1): 20-35.

[13]ZHANG J R, CAO J D, HUANG W, et al. Rutting prediction and analysis of influence factors based on multivariate transfer entropy and graph neural networks[J]. Neural Networks,2023,157: 26-38.

[14]LI Z, SHI X, CAO J, et al. CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction[J]. Science China Technological Sciences,2022,65(7): 1470-1481.

[15]KIM W J, LE V P, LEE H J, et al. Calibration and validation of a rutting model based on shear stress to strength ratio for asphalt pavements[J].Construction and Building Materials,2017,149: 327-337.

[16]LIU G, CHEN L L, QIAN Z D, et al. Rutting influencing factors and prediction model for asphalt pavements based on the factor analysis method[J]. Journal of Southeast University(English Edition), 2021, (4): 421-428.

[17]CHOI Y T, KIM Y R. Implementation and verification of a mechanistic permanent deformation model (shift model) to predict rut depths of asphalt pavement[J]. Road Materials and Pavement Design,2014,15(sup1): 195-218.

[18]LING J, REN L, TIAN Y, et al. Analysis of airfield composite pavement rutting using full-scale accelerated pavement testing and finite element method[J]. Construction and Building Materials,2021,303: 124528.

[19]ARCHILLA A R. Use of superpave gyratory compaction data for rutting prediction[J]. Journal of Transportation Engineering,2006,132(9): 734-741.

[20]SUH Y C, CHO N H. Development of a rutting performance model for asphalt concrete pavement based on test road and accelerated pavement test data[J]. KSCE Journal of Civil Engineering,2014,18(1): 165-171.

[21]刘俊卿, 刘红, 李倩. 变温条件下考虑车辆-路面相互作用的车辙分析[J]. 应用数学和力学, 2017,38(2): 170-180.(LIU Junqing, LIU Hong, LI Qian. Pavement rutting analysis based on vehicle-road interaction under thermal effects[J]. Applied Mathematics and Mechanics,2017,38(2): 170-180. (in Chinese))

[22]AASHTO. Mechanistic-empirical pavement design guide: a manual of practice, interim edition[S]. Washington, DC, USA: American Association of State Highway and Transportation Officials, 2008.

[23]中华人民共和国交通运输部. 公路沥青路面设计规范[M]. 北京: 人民交通出版社, 2017.(Ministry of Transport of the People’s Republic of China. Specifications for Design of Highway Asphalt Pavements[M]. Beijing: China Communications Press, 2017.(in Chinese))

[24]SHELL. Pavement Design Manual[M]. London, UK: Shell International Petroleum Company, Ltd., 1978.

[25]WU Y, ZHOU X, WANG X, et al. Evaluation and correction method of asphalt pavement rutting performance prediction model based on RIOHTrack long-term observation data[J]. Applied Sciences,2022,12(13): 6805.

[26]WANG Y Y, ZHANG B Q, CHEN Y C. Robust airfoil optimization based on improved particle swarm optimization method[J]. Applied Mathematics and Mechanics (English Edition), 2011,32(10): 1245-1254.

[27]KENNEDY J,EBERHART R. Particle swarm optimization[C]//Proceedings of ICNN’95-International Conference on Neural Networks. Perth, WA, Australia,1995: 1942-1947.

[28]李敏, 李卓轩, 时欣利, 等. 基于可解释性集成学习的RIOHTrack车辙预测模型及驱动因素研究[J]. 应用数学和力学, 2025,46(1): 92-104.(LI Min, LI Zhuoxuan, SHI Xinli, et al. Research on driving factors of the RIOHTrack rutting prediction model based on interpretable ensemble learning[J]. Applied Mathematics and Mechanics,2025,46(1): 92-104. (in Chinese))

[29]冯伟. 基于足尺环道试验的沥青路面车辙预估模型及变形机理研究[D]. 长沙: 长沙理工大学, 2021.(FENG Wei. Study on rutting prediction model and deformation mechanism of asphalt pavement based on full-scale test loop[D]. Changsha: Changsha University of Science & Technology, 2021. (in Chinese))

施引文献

资源附件(0)

访问统计