Fault diagnosis of gearbox based on adaptive wavelet de-noising and convolution neural network

Abstract

In this paper, in order to solve the problem that it is difficult to carry out accurate fault diagnosis for gearbox under noise environment, complete ensemble imperial mode decomposition with adaptive noise analysis (CEEMDAN) is used to solve the sample entropy of the original signal and each intrinsic mode function (IMF) component, adaptive wavelet is adopted to decompose and reconstruct IMF with large sample entropy for noise reduction, and first layer wide convolution kernel deep convolution neural network (WDCNN) and long short term memory (LSTM) are used to extract the basic digital features of the reconstructed signal and the correlation features between the features. Therefore, a new fault diagnosis method for gearbox under noise environment is proposed. Taking the public data set of Jiangsu Qiangpeng Diagnostic Engineering Co., Ltd as the research object, the experiments were carried out with the method proposed in this paper. The experimental results show that the proposed method has high accuracy and strong anti-noise ability. Under the environment of no noise and low noise, the fault diagnosis accuracy of the gearbox is 100%; even if the signal to noise ratio is −4 dB, the fault diagnosis accuracy of the gearbox can still reach 99.97%. Therefore, this paper provides a method support for gearbox fault diagnosis under noise environment.