Intelligent fault diagnosis method of rolling bearing based on stacked denoising autoencoder and convolutional neural network

Abstract

Purpose The purpose of this study is to analyze the intelligent fault diagnosis method of rolling bearing. Design/methodology/approach The vibration signal data of rolling bearing has long time series and strong noise interference, which brings great difficulties for the accurate diagnosis of bearing faults. To solve those problems, an intelligent fault diagnosis model based on stacked denoising autoencoder (SDAE) and convolutional neural network (CNN) is proposed in this paper. The SDAE is used to process the time series data with multiple dimensions and noise interference. Then the dimension-reduced samples can be put into CNN model, and the fault classification results can be obtained by convolution and pooling operations of hidden layers in CNN. Findings The effectiveness of the proposed method is validated through experimental verification and comparative experimental analysis. The results demonstrate that the proposed model can achieve an average classification accuracy of 96.5% under three noise levels, which is 3-13% higher than the traditional models and single deep-learning models. Originality/value The combined SDAE–CNN model proposed in this paper can denoise and reduce dimensions of raw vibration signal data, and extract the in-depth features in image samples of rolling bearing. Consequently, the proposed model has more accurate fault diagnosis results for the rolling bearing vibration signal data with long time series and noise interference. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-11-2019-0496/

The multilabel fault diagnosis model of bearing based on integrated convolutional neural network and gated recurrent unit

“…In the generalized regression neural network model proposed by Li et al (2021), variational mode decomposition (VMD) was carried out for feature extraction of vibration signals. Che et al (2020) proposed an intelligent fault diagnosis model based on stacked denoising autoencoder (SDAE) and convolutional neural network (CNN), the SDAE is used to process the time series data with multiple dimensions and noise interference. Sun and Che (2017) proposed a novel compound data classification method based on the discrete wavelet transform and the support vector machine (SVM), feature vectors are constructed based on several time-domain indices of the denoised signal.…”

Fault diagnosis of rolling bearings based on improved direct fast iterative filtering and spectral amplitude modulation

“…2 Therefore, the accurate diagnosis of early fault of rolling bearings has become a popular topic of research. 3,4 Randall and Antoni thoroughly summarized some common methods for the diagnosis of rolling bearings. 5 To accurately detect bearing faults, one of the issues is to extract their fault features.…”

Intelligent Fault Diagnosis Method for Blade Damage of Quad-Rotor UAV Based on Stacked Pruning Sparse Denoising Autoencoder and Convolutional Neural Network

“…A wide convolution kernel can improve the anti-interference ability of convolutional neural network to some extent. In reference to the problem of inaccurate diagnosis results for data with large noise signals, the literature [27] proposed to denoise the data based on the stack denoising autoencoder, and achieved good results, but due to the introduction of a new network structure, the convergence speed of the training network has been adversely affected to a large extent. Most of the existing fault diagnosis algorithms need to preprocess the data to eliminate the noise interference in the data, thereby improving the accuracy of classification, but there are few methods to directly classify the original noisy data and obtain a good classification accuracy.…”