摘要：近年来随着我国高速铁路动车组的大规模投入使用，动车组行车安全成为铁路运行过程中最重要的环节。滚动轴承作为动车组走行部的重要部件，运转状态的好坏直接影响动车组行车安全。故研究滚动轴承故障智能诊断对保障列车安全可靠运营有着重大现实意义。本文在研究滚动轴承故障产生机理和分析方法的基础上，确定了动车组滚动轴承基于振动信号的故障诊断方法。即通过对振动信号进行包络谱分析提取特征向量，利用SVM算法进行智能故障识别。对此设计了故障智能诊断系统，并利用滚动轴承四种状态下实验数据对系统的有效性进行验证。经过验证结果与实际情况的对比，结果表明该系统能够对待诊断数据状态进行准确的识别，验证了利用SVM算法对动车组滚动轴承故障智能诊断的准确性和可行性。
关键词：动车组；滚动轴承；提取特征；SVM；智能诊断
Study on SVM intelligent diagnosis of multiple unit train
Abstract：In recent years, with the large-scale use of China's high-speed railway emu, the safety of emu has become the most important link in railway operation. Rolling bearing, as an important part of moving part of emu, influences the safety of emu directly. Therefore, it is of great practical significance to study intelligent diagnosis of rolling bearing fault to ensure safe and reliable operation of train. In this paper, the fault diagnosis method based on vibration signal of rolling bearing in emu is determined on the basis of studying the fault generation mechanism and analysis method of rolling bearing. In other words, the characteristic vector is extracted by the envelope spectrum analysis of the vibration signal, and the intelligent fault identification is carried out by using the SVM algorithm. The intelligent fault diagnosis system is designed and the validity of the system is verified by using the experimental data of rolling bearing in four states. Proven results contrast with actual situation, and the results show that the system can treat state accurately identify diagnostic data, the SVM algorithm validation of the emu accuracy and feasibility of the rolling bearing fault intelligent diagnosis.
Key Words：Multiple Units；Rolling bearing；Extracted features；SVM；Intelligent diagnosis
目录
1绪论 1
1.1课题目的和意义 1
1.3文献综述 3
1.4论文内容和结构安排 4
2滚动轴承故障机理和信号分析方法 5
2.1滚动轴承的基本结构 5
2.2振动机理和失效形式 5
2.2.1振动机理 5
2.2.2失效形式 7
2.3滚动轴承产生故障的特征频率 8
2.4滚动轴承的信号分析方法 9
2.4.1时域分析 9
2.4.2频域分析 11
2.5本章小结 11
3支持向量机原理以及算法 12
3.1统计学理论相关知识 12
3.2支持向量机的理论 13
3.2.1一对多方法 15
3.2.2一对一方法 16
3.3本章小结 16 动车组滚动轴承SVM智能诊断研究:http://www.chuibin.com/zidonghua/lunwen_205116.html