论文部分内容阅读
针对变速齿轮箱中的故障检测问题,提出了一种结合Morlet小波变换和多层感知器(MLP)神经网络的齿轮故障检测方法。首先,利用角域技术将时域中齿轮故障的非平稳振动信号转化为角域中的平稳信号。然后,利用进行Morlet小波变换并从小波系数中提取统计特征。同时根据最大能量与香农熵比来确定连续小波变换(CWT)的最优尺度,以此来缩减特征量,并将小波系数的能量和香农熵作为两个新特征添加到特征向量。最后,利用MLP神经网络对输入特征进行分类,从而检测故障。实验结果表明,该方法故障检测准确率高,且计算速度快。
Aiming at the problem of fault detection in gearbox, a gear fault detection method based on Morlet wavelet transform and multilayer perceptron (MLP) neural network is proposed. First, the angular domain technique is used to transform the non-stationary vibration signal of gear failure in the time domain into the stationary signal in the angular domain. Then, Morlet wavelet transform is used to extract statistical features from the wavelet coefficients. At the same time, the optimal scale of continuous wavelet transform (CWT) is determined according to the entropy ratio between maximum energy and Shannon, so as to reduce the feature quantity and add the energy of wavelet coefficients and Shannon entropy as two new features to the feature vector. Finally, the input features are classified using MLP neural network to detect faults. Experimental results show that the method has high accuracy and fast calculation speed.