基于SVM的转向架故障诊断技术研究
冯泽阳，邬平波
（西南交通大学 牵引动力国家重点实验室，四川 成都 610031）
摘要：分析了我国当前转向架故障诊断的技术特点，通过小波包变换提取列车转向架故障工况的能量特征向量，同时结合列车振动信号的时频特征，提出一种基于多维特征SVM模型的列车转向架故障诊断方法。并通过滚动振动试验台实测的转向架故障运行工况数据，对比了SVM算法和BP神经网络的诊断性能，验证了该方法的可行性。研究表明：通过分析列车的振动信号，以时域特征和能量特征结合的特征向量，在支持向量机方法下能有效区分列车不同故障工况，与传统的BP神经网络相比，SVM模型的故障诊断正确率更高，可作为故障诊断的依据之一。
关键词：故障诊断；高速列车转向架；小波包；支持向量机
中图分类号：U271.91 文献标志码： A doi：10.3969/j.issn.1006-0316.2020.08.007
文章编号：1006－0316 (2020) 08－0037－07
Research on Bogie Fault Diagnosis Technology Based on Support Vector Machine
FENG Zeyang，WU Pingbo
( State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu 610031, China )
Abstract：In this paper, wavelet packet transform is used to extract the energy eigenvector of train bogie fault condition. At the same time, according to the time-frequency characteristics of train vibration signal, a fault diagnosis method of rrain bogie based on multi-dimensional SVM model is proposed. The performance of SVM model and BP neural network are compared through the data of bogie fault operation obtained from rolling vibration test-bed, and the method is verified. The research shows that this method can effectively distinguish different fault conditions of trains. Compared with the traditional BP neural network, the SVM model has higher accuracy in fault diagnosis, which can be used as one of the basis of fault diagnosis.
Key words：fault diagnosis；high-speed train bogie；wavelet packet；support vector machine
———————————————
收稿日期：2020－03－02
作者简介：冯泽阳（1994－），男，广东广州人，硕士研究生，主要研究方向为车辆强度，E-mail：fffzzz_yyy@qq.com；邬平波（1968－），男，浙江奉化人，博士，西南交通大学牵引动力国家重点实验室研究员，主要研究方向为车辆系统动力学及车辆强度。
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS