基于小波分析-最小二乘支持向量机的转子碰摩故障诊断

The Rub-Impact Fault Diagnosis Based on Wavelet Analysis-Least Square Support Vector Machine

针对不同材料碰摩声发射信号分类识别的问题,利用小波分析良好的时频特性和最小二乘支持向量机解决小样本、非线性、高维模式识别问题的优势,提出一种小波分析与最小二乘支持向量机结合的分类方法.声发射信号进行小波多尺度分解,将分解获得的各尺度能量百分比作为最小二乘支持向量机的输入,用于声发射信号分类识别.实验结果表明:该方法可以明显识别出转子碰摩故障信号以及分类不同材料的碰摩信号.

Aiming at the problem of classification and recognition of rub-impact acoustic emission signals of different materials,taking advantage of wavelet analysis with good time-frequency characteristics and least squares support vector machine to solve small sample,nonlinear and high-dimensional pattern recognition problems,a classification method combining wavelet analysis with least squares support vector machine is proposed. Firstly,the acoustic emission signal is decomposed into wavelet multi-scale decomposition,and the energy percentage of each scale obtained by decomposition is used as input of least squares support vector machine for the classification and identification of acoustic emission signals. Experimental results showthat the method can recognize the rub-impact fault signal of rotor and classify the rub-impact sigral of different materials.