基于NIC-DWT-WOASVM的齿轮箱混合故障诊断

Compound fault diagnosis for gearbox based on NIC-DWT-WOASVM

由于齿轮箱中振动信号的复杂性和非平稳性,致使齿轮箱混合故障诊断工作具有一定难度。针对这一问题提出基于NIC-DWT-WOASVM的齿轮箱混合故障诊断方法。首先通过窄带干扰消除(Narrow Band Interference Canceller,NIC)滤除原始信号中齿轮啮合和转轴等窄带干扰信号,接着对信号进行离散小波变换(Discrete Wavelet Transform,DWT),重构小波系数得到小波分量,提取分量的方差作为特征参数构成特征矩阵样本。针对传统优化支持向量机收敛速度慢及容易局部最优等问题,提出鲸鱼算法优化的支持向量机(Whale Optimization Algorithm Support Vector Machine,WOASVM),运用训练样本对WOASVM进行训练得到优化分类模型,将测试样本输入到优化模型中得到诊断结果。为验证方法的有效性,开展了变工况下齿轮箱混合故障实验,通过实验分析及与其他方法的比较,证明方法对于齿轮箱混合故障诊断是有效的。

The compound fault diagnosis of gearbox is difficult because of the complexity and non-stationarity of the vibration signal in the gearbox.A compound fault diagnosis method of gearbox based on NIC-DWT-WOASVM was proposed in this paper.Firstly,the narrowband interference signals were filtered by Narrow Band Interference Canceller(NIC).Then the Discrete Wavelet Transform(DWT)was used to reconstruct the wavelet coefficients to get the wavelet component and the variance of the wavelet components was extracted as the characteristic parameter to form the characteristic matrix sample.Aiming at the problems of slow convergence and easy local optimization of traditional optimized support vector machines,this paper proposed a whale algorithm optimized support vector machine(WOASVM),which used training samples to trained WOASVM to get the optimal classification model,and input the test samples into the optimization model to get the diagnosis results.In order to verify the effectiveness of the proposed method,a compound fault experiment of gearbox under variable conditions was carried out.The experimental results show that the proposed method is effective for compound fault diagnosis of gearbox.