基于深度小波去噪自动编码器的轴承智能故障诊断方法

针对原始振动数据无监督特征学习问题,提出一种深度小波去噪自动编码器与鲁棒极限学习机相结合的滚动轴承的智能故障诊断方法.利用小波函数作为非线性激活函数设计小波去噪自动编码器,从而有效地捕获信号特征;利用多个小波去噪自动编码器构造一个深度小波去噪自动编码器来增强无监督特征学习能力;采用鲁棒极限学习机作为分类器,对不同的轴承...

AN INTELLIGENT FAULT DIAGNOSIS METHOD FOR BEARING BASED ON DEEP WAVELET DENOISING AUTOMATIC ENCODER

Aiming at unsupervised feature learning of original vibration data,an intelligent fault diagnosis method for rolling bearings is proposed,which combines deep wavelet denoising automatic encoder with robust limit learning machine.The wavelet function was used as a non-linear activation function to design an automatic wavelet de-noising coder to capture the signal features effectively;a deep wavelet denoising automatic coder was constructed by using multiple wavelet denoising automatic coders to enhance unsupervised feature learning ability;robust limit learning machine was used as classifier to classify and identify different bearing faults.The experimental results show that the proposed method is superior to the traditional method and the standard deep learning method under the condition of unsupervised feature learning of the original vibration data.