Research in Analysis of Asphalt Pavement Performance Evaluation Based on PSO-SVM

Abstract:

An emerging machine learning technique, the support vector machine (SVM), based on statistical learning theory is very good at analyzing small samples and non-linear regression problem. The particle swarm optimize (PSO) can avoid the man-made blindness and enhance the efficiency and capability in forecasting. In this paper, SVM is applied to establish a model for asphalt pavement performance evaluation, optimized by PSO algorithm. In road engineering, PCI, SSI, SRI and IRI were selected as the asphalt pavement performance evaluation indexes, but it is difficult to get pavement condition index. This paper describes the relationships among the four indicators, and SSI, SRI and IRI were used for establishing the prediction model to forecast PCI based on PSO-SVM. The results show that the method is simple and effective for evaluation of asphalt pavement performance.

• Periodical: Applied Mechanics and Materials (Volumes 97-98)
• Pages: 203-207
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.97-98.203
• Online since: September 2011
• Authors: Ke Zhen Yan, Zou Zhang
• Keywords: Pavement, Pavement Performance Evaluation, PCI, Support Vector Machine (SVM)

References

[1] JI Tian-jian, HUANG Xiao-ming, CHEN Rong-sheng: Application of Artificial Neural Network in Analyses of Pavement Performance[J]. Journal of Highway and Transportation Research and Development, Vol.19(2002), p.19~21.

[2] XU Qiang: Preventive Maintenance Evaluation System Research of Highway Asphalt Pavement [J] . Journal of China & Foreign Highway, Vol.19(2009), p.64~68.

[3] ZHANG Yongqing, JIA Shuangying: Evaluation Method for Asphalt Pavement Performance of Freeway [J]. Journal of Chang'an University: Natural Science Edition, Vol.25(2005), p.15~18.

[4] ZI Jianmin, JIANG Tao: Gray Method of the Comprehensive Evaluation for Road Surface Condition [J] . Journal of Huazhong University of Science and Technology: Natural Science Edition, Vol.30(2002), p.62~64.

[5] YAN Kezhen, WU Jianliang: A Method of Asphalt Pavement Performance Evaluation Based on POS-LSSVM [J] . Journal of Highway and Transportation Research and Development,Vol.26(2009), p.32~34.

[6] TANG Xian-lun, ZHUANG Ling, QU Guo-qing, CA I Jun: Support Vector Machine Based on Chaos Swarm Optimization for Fault Diagnosis of Rotating Machine[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), Vol.21(2009), p.127~133.

[7] LI Li, NIU Ben: The particle swarm optimization algorithm [M] (Metallurgical Industry Press, China 2010).

[8] DONG Yinfeng, LI Yingmin, LAI Ming, XIAO Mingkui：Nonlinear structural response prediction based on support vector machines[J]. Journal of Sound and Vibration, Vol.311(2008), p.886~897.

DOI: 10.1016/j.jsv.2007.09.054