摘要To solve the problem of the low accuracy of the traditional qualitative method for highway asphalt pavement performance, a prediction model based on improved firefly algorithm (IFA)-support vector machine (SVM) is established by combining SVM theory and IFA. First, firefly field search is introduced into the prediction model to overcome the random movement of fireflies with the increase in the number of iterations in the optimization process. Second, in the subsequent optimization process, the dynamic adjustment algorithm is used to search the step size to balance the global search ability, which accelerates the optimization selection of the performance parameters of the SVM model. Finally, the example is verified and compared with the standard FA-SVM prediction method to verify the validity of the IFA-SVM model and the feasibility of prediction accuracy. The result shows the following:(1) The maximum relative error is 2.5435% and the minimum is 0.8206% when the standard FA-SVM is used to predict the pavement performance of the Baiyin section of the G6 expressway. The maximum relative error is 1.0858% and the minimum is 0.3654%, and their root mean square error is smaller than that of the standard FA-SVM method. (2) The IFA-SVM model has a faster convergence rate and a higher accuracy than the standard FA-SVM when predicting the performance of asphalt pavement on highways. The prediction result is not only closer to the measured value but also provides effective support for the maintenance decision of asphalt pavement on highways.
Abstract：To solve the problem of the low accuracy of the traditional qualitative method for highway asphalt pavement performance, a prediction model based on improved firefly algorithm (IFA)-support vector machine (SVM) is established by combining SVM theory and IFA. First, firefly field search is introduced into the prediction model to overcome the random movement of fireflies with the increase in the number of iterations in the optimization process. Second, in the subsequent optimization process, the dynamic adjustment algorithm is used to search the step size to balance the global search ability, which accelerates the optimization selection of the performance parameters of the SVM model. Finally, the example is verified and compared with the standard FA-SVM prediction method to verify the validity of the IFA-SVM model and the feasibility of prediction accuracy. The result shows the following:(1) The maximum relative error is 2.5435% and the minimum is 0.8206% when the standard FA-SVM is used to predict the pavement performance of the Baiyin section of the G6 expressway. The maximum relative error is 1.0858% and the minimum is 0.3654%, and their root mean square error is smaller than that of the standard FA-SVM method. (2) The IFA-SVM model has a faster convergence rate and a higher accuracy than the standard FA-SVM when predicting the performance of asphalt pavement on highways. The prediction result is not only closer to the measured value but also provides effective support for the maintenance decision of asphalt pavement on highways.
基金资助:Supported by the National Natural Science Foundation of China (Nos.51668038, 51868042); the Distinguished Young Scholars Fund of Gansu Province (No.1606RJDA318); the Natural Science Foundation of Gansu Province (No.1506RJZA064); Foundation of A Hundred Youth Talents Training Program of Lanzhou Jiaotong University,Youth Science Foundation of Gansu (No.17JR5RA087); Innovation Ability Improvement Project of Colleges and Universities in Gansu Province(No.2019B-055); Youth Science Foundation of Lanzhou Jiaotong University (No.2017016)
通讯作者:
LI Hai-lian
E-mail: 17834040@qq.com
引用本文:
李海莲, 林梦凯, 王起才. Performance Prediction of Highway Asphalt Pavement Based on IFA-SVM[J]. Journal of Highway and Transportation Research and Development, 2020, 14(3): 20-27.
LI Hai-lian, LIN Meng-kai, WANG Qi-cai. Performance Prediction of Highway Asphalt Pavement Based on IFA-SVM. Journal of Highway and Transportation Research and Development, 2020, 14(3): 20-27.
[1] JING Chao, ZHANG Jin-xi. Review of Prediction of Asphalt Pavement Performance[J]. Journal of China & Foreign Highway,2017,37(5):31-35. (in Chinese) [2] KONG Xiang-jie, ZHANG Jin-xi, YUAN Xiao-bin,et al. Research on Factors Affecting Rutting Resistance of Asphalt Pavement[J]. Journal of China & Foreign Highway, 2016, 36(3):43-48. (in Chinese) [3] YU Lin. Study on Decay Characteristics of Asphalt Pavement in Service[J]. Transpoworld,2016(25):16-19. (in Chinese) [4] SUN li-jun, LIU Xi-ping. General Deterioration Equation for Pavement Performance[J]. Journal of Tongji University:Natural Science Edition, 1995(5):512-518. (in Chinese) [5] JIN Nian-sheng, CHEN Fei, MIAO Chao-jie. Study on the Prediction of Asphalt Pavement Performance Based on Grey-Markov Theory[J]. Technology of Highway and Transport, 2018, 34(5):17-20,26. (in Chinese) [6] YANG Guo-feng, WANG Hao-yang,PAN Yu-li. Prediction of Asphalt Pavement Performance Based on Mixed Effect Model[J]. Journal of Highway and Transportation Research and Development, 2018, 35(8):19-27. (in Chinese) [7] LIU Qian-hui, ZHANG Zheng-xin, HUANG Fang-lin, et al. Studied on Performance Prediction of Asphalt Pavement Based on Support Vector Machine[J]. Highway Engineering, 2018, 43(2):201-205. (in Chinese) [8] FISTER I, FISTER I, Jr, YANG X S, et al. A Comprehensive Review of Firefly Algorithms[J]. Swarm and Evolutionary Computation, 2013,13:34-46. [9] ZHANG C H, TIAN Y J, DENG N Y. The New Interpretation of Support Vector Machines on Statistical Learning Theory[J]. Science in China Series A:Mathematics, 2010, 53(1):151-164. [10] FAN Wen-ting, WANG Xiao. PM2.5 Forecasting Based on Improved Firefly Optimization SVM[J]. Computer Systems & Applications,2019, 28(1):134-139. (in Chinese) [11] WANG Xiao-jing, PENG Hu, DENG Chang-shou, et al. Firefly Algorithm Based on Uniform Local Search and Variable Step Size[J]. Journal of Computer Applications,2018, 38(3):715-721. (in Chinese) [12] CHEN Shi-zhou, LI Shan, XIONG Feng, et al. Forecasting of Asphalt Pavement Performance Based on GA-gray Neural Network[J]. Journal of Chongqing Jiaotong University:Natural Science Edition,2019,38(2):44-50. (in Chinese) [13] ZHANG Jin-xi, KONG Xiang-jie, HAN Ding-ding, et al. Prediction Model of Asphalt Pavement PCI of Expressway under Different Maintenance Conditions[J]. Journal of Beijing University of Technology, 2016,42(1):74-80. (in Chinese) [14] BAI Qi-feng, QIAN Zhen-dong,WU Chun-ying. Study on Asphalt Pavement Mechanical Model Based on Calibration of Measurement[J]. Journal of Highway and Transportation Research and Development,2011, 28(5):39-43. (in Chinese) [15] DU Er-peng, MA Song-lin, JING Hai-min. Asphalt Pavement Performance Prediction Model Based on Gray System Theory[J]. Journal of Tongji University:Natural Science Edition, 2010,38(8):1161-1164. (in Chinese) [16] LI Tao, WANG Hui-ming, HU Zong-qi. Application of Asphalt Pavement Performance Evaluation Based on Entropy Weight-normal Cloud Model[J]. Journal of Civil Engineering and Management, 2019,36(4):190-196. (in Chinese) [17] GONG Jian, CHANG Cheng-li, CHENG Shan-shan, et al. An Asphalt Pavement Performance Evaluation Model Based on Deflection[J]. Journal of Highway and Transportation Research and Development, 2016, 33(7):40-46. (in Chinese) [18] WANG Chang-heng, BAI Li-xiang, DENG Shan. Analysis of Asphalt Pavement Performance Based on Entropy Weight Combination Forecast and Rough Fuzzy Set[J]. Journal of Highway and Transportation Research and Development, 2016, 33(4):12-19. (in Chinese)
2020, Vol. 14 
