铁道科学与工程学报2018，Vol.15Issue(7)：1671-1677,7.DOI:10.19713/j.cnki.43-1423/u.2018.07.006
基于支持向量机的轨道不平顺预测研究
Prediction for track Irregularity based on support vector machine
摘要
Abstract
The prediction model of the track irregularity was established by using the support vector machine. The model was verified by the actual inspection data of the 100 rail segments under the Beijing-Kowloon line. The predicted results were compared with recurrent composite BP network. The results show that the average relative error of the TQI predicted value obtained by the model is 0.85%. The predicted accuracy is improved compared with recurrent composite BP network. The experimental results show that the support vector machine (SVM) can be used to predict the track irregularity, which can effectively reflect the development trend of track quality index, and it has some reference value for the prediction of track irregularity.关键词
支持向量机/轨道不平顺/轨道质量指数/模型预测Key words
support vector machine/track irregularity/track quality index/model prediction分类
交通工程引用本文复制引用
于瑶,刘仍奎,王福田..基于支持向量机的轨道不平顺预测研究[J].铁道科学与工程学报,2018,15(7):1671-1677,7.基金项目
国家自然科学基金资助项目(51578057) （51578057）
轨道交通控制与安全国家重点实验室(北京交通大学)自主研究课题资助项目(RCS2016ZT007) （北京交通大学）
