基于灰色关联度分析和支持向量机回归的沥青路面使用性能预测
|
摘要
沥青路面使用性能多因素预测是一个复杂的非线性问题,传统预测模型存在很多不足。为弥补传统模型的缺陷,建立一个高精度、长周期、多因素的预测模型,通过灰色关联度分析对各因素进行降维处理,选择与沥青路面使用性能关联度较大的影响因素进行支持向量机回归非线性预测,提出了基于灰色关联度分析和支持向量机回归(GRA-SVR)的沥青路面使用性能预测模型。最后选用广云高速实测车辙指数(RDI)值进行实例验证,并同GM(1,1)和PPI两种模型的预测结果进行了对比分析。结果表明:基于GRA-SVR建立的多因素预测模型具有很好的精度和可操作性,可在长周期过程中使用,为大数据养护决策提供了模型参考和依据。
Asphalt pavement performance prediction is complex and nonlinear when it involves multifactor.In order to overcome the defects existing in traditional prediction models,a long-period and multifactor prediction model with high precision needs to be established,on which the dimension of each factor is reduced by grey relational analysis,and the important relational factors are selected for nonlinear prediction by support vector machine regression.Accordingly the performance prediction model of asphalt pavement based on GRA-SVR was proposed and the measured RDI from Guangyun freeway were collected as an example to validate the proposed model.The results show that GRA-SVR model has better accuracy and maneuverability compared with GM(1,1)and PPI models.It can be used in long-term process and provide model reference for large data maintenance decision-making.
Asphalt pavement performance prediction is complex and nonlinear when it involves multifactor.In order to overcome the defects existing in traditional prediction models,a long-period and multifactor prediction model with high precision needs to be established,on which the dimension of each factor is reduced by grey relational analysis,and the important relational factors are selected for nonlinear prediction by support vector machine regression.Accordingly the performance prediction model of asphalt pavement based on GRA-SVR was proposed and the measured RDI from Guangyun freeway were collected as an example to validate the proposed model.The results show that GRA-SVR model has better accuracy and maneuverability compared with GM(1,1)and PPI models.It can be used in long-term process and provide model reference for large data maintenance decision-making.
引文
[1]李巧茹,郭知洋,王耀军,等.基于PCA-SVM的高速公路沥青路面使用性能评价[J].北京工业大学学报,2018,44(2):283-288.LI Qiaoru,GUO Zhiyang,WANG Yaojun,et al.Evaluation of freeway asphalt pavement performance based on PCA-SVM[J].Journal of Beijing Polytechnic University,2018,44(2):283-288.(in Chinese)
[2]周岚.高速公路沥青路面使用性能评价及预测研究[D].南京:东南大学,2015.ZHOU Lan.Research of performance evaluation and prediction method of asphalt pavements for highway[D].Nanjing:Southeast University,2015.(in Chinese)
[3]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.Review on the performance prediction research of asphalt pavement.[J].Journal of China &Foreign Highway,2017,37(5):31-35.(in Chinese)
[4]Wang K C P,Li Q.Gray clustering-based pavement performance evaluation[J].Journal of Transportation Engineering,2010,136(1):38-44.
[5]申健民,党耀国,周伟杰,等.基于指数函数的灰色动态多属性关联决策模型[J].控制与决策,2016,31(8):1441-1445.SHEN Jianmin,DANG Yaoguo,ZHOU Weijie,et al.Grey dynamic multiple attribute correlation decision-making model based on exponential function[J].Control and Decision,2016,31(8):1441-1445.(in Chinese)
[6]孙立军,刘喜平.路面使用性能的标准衰变方程[J].同济大学学报(自然科学版),1995(5):512-518.SUN Lijun,LIU Xiping.Standard decay equation for pavement performance[J].Journal of Tongji University(Natural Science),1995(5):512-518.(in Chinese)
[7]Yang J,Lu J J,Gunaratne M.Application of neural models for forecasting or pavement crack index and pavement condition rating[R].Washington,DC:National Academy of Sciences,2003.
[8]汪海年,张琛,尤占平,等.基于数理统计方法的MEPDG车辙预估模型校正[J].长安大学学报(自然科学版),2013,33(6):1-7.WANG Hainian,ZHANG Chen,YOU Zhanping,et al.Calibration of rutting prediction model in MEPDG based on mathematical statistics method[J].Journal of Chang’an University(Natural Science Edition),2013,33(6):1-7.(in Chinese)
[9]Dong M.A grey relational analysis between some selected affective factors and English test performance[J].Canadian Social Science,2014,10(6):195-200.
[10]陈可嘉,李烜楠,丘永宜.福建省交通工程材料价格影响因素的灰色关联分析[J].公路交通科技,2018,35(4):137-145.CHEN Kejia,LI Xuannan,QIU Yongyi.Grey correlation analysis on influencing factors of traffic engineering material price in Fujian province[J].Journal of Highway and Transportation Research and Development,2018,35(4):137-145.(in Chinese)
[11]Abdi M J,Giveki D.Automatic detection of erythemato-squamous diseases using PSO-SVM based on association rules[J].Engineering Applications of Artificial Intelligence,2013,26(1):603-608.
[12]Liu Z W,Cao H R,Chen X F,et al.Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings[J].Neurocomputing,2013,99:399-410.
[13]刘黔会,张挣鑫,黄方林,等.基于支持向量机的沥青路面使用性能预测探究[J].公路工程,2018,43(2):201-205.LIU Qianhui,ZHANG Zhengxin,HUANG Fanglin,et al.Studied on performance prediction of asphalt pavement based on support vector machine[J].Highway Engineering,2018,43(2):201-205.(in Chinese)
[14]李嫄源,袁梅,王瑶,等.SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(1):99-107.LI Yuanyuan,YUAN Mei,WANG Yao,et al.Fault diagnosis of motor bearings based on SVM and PSO[J].Journal of Chongqing University,2018,41(1):99-107.(in Chinese)
[15]黄啸.支持向量机核函数的研究[D].苏州:苏州大学,2008.HUANG Xiao.The study on kernels in support vector machine[D].Suzhou:Soochow University,2008.(in Chinese)
[16]董西伟,王玉伟,张广顺,等.基于迁移学习的跨公司软件缺陷预测[J].计算机工程与设计,2016,37(3):684-689.DONG Xiwei,WANG Yuwei,ZHANG Guangshun,et al.Transfer learning based cross-company software defects prediction[J].Computer Engineering and Design,2016,37(3):684-689.(in Chinese)
[17]Aydin I,Karakose M,Akin E.A multi-objective artificial immune algorithm for parameter optimization in support vector machine[J].Applied Soft Computing,2011,11(1):120-129.
[18]de Castro L N,von Zuben F J.Learning and optimization using the clonal selection principle[J].IEEE Transactions on Evolutionary Computation,2002,6(3):239-251.
[19]Deng J L.Introduction to grey theory[J].The Journal of Grey System,1989,1:1-24.
[2]周岚.高速公路沥青路面使用性能评价及预测研究[D].南京:东南大学,2015.ZHOU Lan.Research of performance evaluation and prediction method of asphalt pavements for highway[D].Nanjing:Southeast University,2015.(in Chinese)
[3]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.Review on the performance prediction research of asphalt pavement.[J].Journal of China &Foreign Highway,2017,37(5):31-35.(in Chinese)
[4]Wang K C P,Li Q.Gray clustering-based pavement performance evaluation[J].Journal of Transportation Engineering,2010,136(1):38-44.
[5]申健民,党耀国,周伟杰,等.基于指数函数的灰色动态多属性关联决策模型[J].控制与决策,2016,31(8):1441-1445.SHEN Jianmin,DANG Yaoguo,ZHOU Weijie,et al.Grey dynamic multiple attribute correlation decision-making model based on exponential function[J].Control and Decision,2016,31(8):1441-1445.(in Chinese)
[6]孙立军,刘喜平.路面使用性能的标准衰变方程[J].同济大学学报(自然科学版),1995(5):512-518.SUN Lijun,LIU Xiping.Standard decay equation for pavement performance[J].Journal of Tongji University(Natural Science),1995(5):512-518.(in Chinese)
[7]Yang J,Lu J J,Gunaratne M.Application of neural models for forecasting or pavement crack index and pavement condition rating[R].Washington,DC:National Academy of Sciences,2003.
[8]汪海年,张琛,尤占平,等.基于数理统计方法的MEPDG车辙预估模型校正[J].长安大学学报(自然科学版),2013,33(6):1-7.WANG Hainian,ZHANG Chen,YOU Zhanping,et al.Calibration of rutting prediction model in MEPDG based on mathematical statistics method[J].Journal of Chang’an University(Natural Science Edition),2013,33(6):1-7.(in Chinese)
[9]Dong M.A grey relational analysis between some selected affective factors and English test performance[J].Canadian Social Science,2014,10(6):195-200.
[10]陈可嘉,李烜楠,丘永宜.福建省交通工程材料价格影响因素的灰色关联分析[J].公路交通科技,2018,35(4):137-145.CHEN Kejia,LI Xuannan,QIU Yongyi.Grey correlation analysis on influencing factors of traffic engineering material price in Fujian province[J].Journal of Highway and Transportation Research and Development,2018,35(4):137-145.(in Chinese)
[11]Abdi M J,Giveki D.Automatic detection of erythemato-squamous diseases using PSO-SVM based on association rules[J].Engineering Applications of Artificial Intelligence,2013,26(1):603-608.
[12]Liu Z W,Cao H R,Chen X F,et al.Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings[J].Neurocomputing,2013,99:399-410.
[13]刘黔会,张挣鑫,黄方林,等.基于支持向量机的沥青路面使用性能预测探究[J].公路工程,2018,43(2):201-205.LIU Qianhui,ZHANG Zhengxin,HUANG Fanglin,et al.Studied on performance prediction of asphalt pavement based on support vector machine[J].Highway Engineering,2018,43(2):201-205.(in Chinese)
[14]李嫄源,袁梅,王瑶,等.SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(1):99-107.LI Yuanyuan,YUAN Mei,WANG Yao,et al.Fault diagnosis of motor bearings based on SVM and PSO[J].Journal of Chongqing University,2018,41(1):99-107.(in Chinese)
[15]黄啸.支持向量机核函数的研究[D].苏州:苏州大学,2008.HUANG Xiao.The study on kernels in support vector machine[D].Suzhou:Soochow University,2008.(in Chinese)
[16]董西伟,王玉伟,张广顺,等.基于迁移学习的跨公司软件缺陷预测[J].计算机工程与设计,2016,37(3):684-689.DONG Xiwei,WANG Yuwei,ZHANG Guangshun,et al.Transfer learning based cross-company software defects prediction[J].Computer Engineering and Design,2016,37(3):684-689.(in Chinese)
[17]Aydin I,Karakose M,Akin E.A multi-objective artificial immune algorithm for parameter optimization in support vector machine[J].Applied Soft Computing,2011,11(1):120-129.
[18]de Castro L N,von Zuben F J.Learning and optimization using the clonal selection principle[J].IEEE Transactions on Evolutionary Computation,2002,6(3):239-251.
[19]Deng J L.Introduction to grey theory[J].The Journal of Grey System,1989,1:1-24.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |