基于支持向量机的机械故障诊断方法研究

针对因缺少大量故障数据样本而制约机械故障智能诊断发展的问题，提出了一种基于支持向量机的机械故障诊断新方法，介绍了该方法的原理和算法，并利用模拟故障数据建立了多故障分类器。这种诊断方法只需要少量的时域故障数据样本来训练故障分类器，不必进行信号预处理以提取特征量，便可实现多故障的识别和诊断。测试结果表明，当数据样本中含有26％的噪声时，故障分类器仍然能正确分类多种故障。这种诊断方法具有算法简单、可对故障在张分类和故障分类能力强的优点。

Research on Diagnosis Method of Machinery Fault Based on Support Vector Machine

A new method of machinery fault diagnosis based on support vector machine is proposed in order to solve the problem in development of machinery fault intelligent diagnosis due to needing many fault data samples. Principle and algorithm of the mehtod are introduced, and a multi-fault classifier is constructed by simulating fault data. The new method, by which multiple faults can be diagnosed, only requires a small quantity of fault data samples in time domain for training the fault classifier, and does not require signal preprocessing for extracting signal features. Testing results show that the multi-fault classifier can still correctly classify multiple faults even when data samples include 26% noise signal. The new method has simple algorithm, online fault classification, and excellent capability of fault classification.