计算机应用研究2017，Vol.34Issue(4)：1097-1100,4.DOI:10.3969/j.issn.1001-3695.2017.04.032
基于MEEMD香农熵-LSSVM的高速列车蛇行失稳诊断方法
Hunting instability of high-speed train diagnose method based on modified ensemble empirical mode decomposition Shannon entropy and LSSVM
摘要
Abstract
Aiming at addressing the issue of hunting instability for the train at a high speed,this paper presented a new methodology which combined modified ensemble empirical mode decomposition (MEEMD),Shannon entropy features and least squares supported vector machine (LSSVM) to diagnose hunting motion state of high-speed train.This method used MEEMD to decompose the vibration signal under 330 ～350 km/h and got IMF.It used Hilbert transformation (HT) to analyze the spectrum of hunting motion signal,and finally used LSSVM to train and recognize Shannon entropy features of IMFs.The results show that distribution of bogie frequency is highly centralized,and the methodology of MEEMD Shannon features-LSSVM can accurately recognize the unsteady state of hunting motion,up to 96.67％.Furthermore,the accuracy and calculation time are superior to ensemble empirical mode decomposition-support vector machine(EEMD-SVM).关键词
蛇行运动/改进的集合经验模态分解(MEEMD)/Hilbert-Huang变换(HHT)/香农熵/最小二乘法支持向量机(LSSVM)Key words
hunting motion/modified ensemble empirical mode decomposition (MEEMD)/Hilbert-Huang transformation(HHT)/Shannon entropy/least squares support vector machine (LSSVM)分类
信息技术与安全科学引用本文复制引用
叶运广,宁静,种传杰,崔万里,刘棋..基于MEEMD香农熵-LSSVM的高速列车蛇行失稳诊断方法[J].计算机应用研究,2017,34(4):1097-1100,4.基金项目
国家自然科学基金资助项目(51475387) （51475387）
中央高校基本业务费专项基金资助项目(2682014CX033) （2682014CX033）
四川省科技创新苗子工程资助项目(2015102) （2015102）
