基于AMPSO-SVM的沥青路面使用性能评价  

Asphalt pavement performance evaluation based on AMPSO-SVM

作　　者：李海莲[1,2] 杨斯媛 司金忠 张茗 LI Hailian;YANG Siyuan;SI Jinzhong;ZHANG Ming(School of Civil Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Key Laboratory of Road&Bridge and Underground Engineering of Gansu Province,Lanzhou Jiaotong University,Lanzhou 730070,China)

机构地区：[1]兰州交通大学土木工程学院,甘肃兰州730070 [2]兰州交通大学甘肃省道路桥梁与地下工程重点实验室,甘肃兰州730070

出　　处：《大连理工大学学报》2023年第1期69-76,共8页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(51868042);甘肃省自然科学基金资助项目(20JR10RA229,22JR5RA334);甘肃省青年科学基金资助项目(17JR5RA087);甘肃省高等学校创新基金资助项目(2021A-048);兰州交通大学青年科学基金资助项目(2017016);兰州交通大学“百名青年优秀人才培养计划”基金资助项目(2018103)。

摘　　要：传统的沥青路面使用性能评价模型主要针对路面服务情况进行评价,无法对路面的养护决策提供有力支持.为克服这一问题,提出了基于AMPSO-SVM的沥青路面使用性能评价模型.根据路面养护性质确定训练集标签,在支持向量机(support vector machine, SVM)对数据集的训练中引入自适应变异粒子群算法(adaptive mutation particle swarm optimization, AMPSO),增加了变异操作,克服了参数寻优过程中容易陷入局部极值点的问题.最后,与规范的评价结果进行对比分析,证明了AMPSO-SVM评价模型的可行性,评价结果也可为路面的养护决策提供一定的支持.The traditional asphalt pavement performance evaluation model only evaluates the pavement service,which can not provide strong support for the pavement maintenance decision.Aiming at this problem,an asphalt pavement performance evaluation model based on AMPSO-SVM is proposed.The label of training set is determined according to the nature of pavement maintenance.Adaptive mutation particle swarm optimization(AMPSO)is introduced into the training of data set by support vector machine(SVM),which increases the mutation operation and overcomes the problem that it is easy to fall into local extreme points in the process of parameter optimization.Finally,the feasibility of AMPSO-SVM evaluation model is proved by comparing with the standard evaluation results.The AMPSO-SVM evaluation model can also provide a certain support for the decision of pavement maintenance.

关 键 词：道路工程 路面使用性能评价 沥青路面 支持向量机 自适应变异粒子群算法 

分 类 号：U416.2[交通运输工程—道路与铁道工程]