Fault diagnosis of rolling bearings based on multi-scale deep subdomain adaptation network

This study presents a fault diagnosis method for rolling bearing based on multi-scale deep subdomain adaptation network (MSDSAN). The proposed MSDSAN, as improvement of deep subdomain adaptation network (DSAN), is an unsupervised transfer learning method. MSDSAN reduces the subdomain distribution discrepancy between domains rather than marginal distribution discrepancy, and so better domain invariant fault features are derived to avoid misalignment between domains. Aiming at avoiding fault information loss by fixed receptive fields feature extraction, selective kernel convolution module is introduced into feature extraction of MSDSAN, by which multiple receptive fields are applied to ensure an optimal receptive field for each working condition. Moreover, contribution rates are adaptively assigned to all receptive fields, and the disturbing information extracted by inappropriate receptive fields is further eliminated. As a result, more comprehensive and effective fault information is derived for bearing fault diagnosis. Fault diagnosis experiment of bearings is performed to verify the superiority of the proposed method, and the experimental results demonstrate that MSDSAN achieves better transfer effects and higher accuracy than SOTA methods under varying working conditions.

Download Full-text

An Anti-Noise Fault Diagnosis Method of Bearing based on Multi-Scale 1DCNN

10.20944/preprints202008.0164.v1 ◽

2020 ◽

Author(s):

Jie Cao ◽

Zhidong He ◽

Jinhua Wang ◽

Ping Yu

Keyword(s):

Fault Diagnosis ◽

Activation Function ◽

Diagnostic Model ◽

Bearing Fault Diagnosis ◽

Multi Scale ◽

Fault Features ◽

Convolution Structure ◽

Diagnosis Method ◽

Diagnosis Accuracy ◽

Comparison Algorithms

In recent years, intelligent fault diagnosis algorithms using deep learning method have achieved much success. However, the signals collected by sensors contain a lot of noise, which will have a great impact on the accuracy of the diagnostic model. To address this problem, we propose a one-dimensional convolutional neural network with multi-scale kernels (MSK-1DCNN) and apply this method to bearing fault diagnosis. We use a multi-scale convolution structure to extract different fault features in the original signal, and use the ELU activation function instead of the ReLU function in the multi-scale convolution structure to improve the anti-noise ability of MSK-1DCNN; then we use the training set with pepper noise to train the network to suppress overfitting. We use the Western Reserve University bearing data to verify the effectiveness of the algorithm and compare it with other fault diagnosis algorithms. Experimental results show that the improvements we proposed have effectively improved the diagnosis performers of MSK-1DCNN under strong noise and the diagnosis accuracy is higher than other comparison algorithms.

Download Full-text

Compound Faults Feature Extraction for Rolling Bearings Based on Parallel Dual-Q-Factors and the Improved Maximum Correlated Kurtosis Deconvolution

Applied Sciences ◽

10.3390/app9081681 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1681 ◽

Cited By ~ 2

Author(s):

Cui ◽

Du ◽

Yang ◽

Xu ◽

Song

Keyword(s):

Rolling Bearing ◽

Rolling Bearings ◽

Outer Race ◽

Spectral Kurtosis ◽

Bearing Fault Diagnosis ◽

Fault Features ◽

Q Factors ◽

The Impact ◽

Fault Information ◽

Fault Characteristic

Vibration analysis is one of the main effective ways for rolling bearing fault diagnosis, and achallenge is how to accurately separate the inner and outer race fault features from noisy compoundfaults signals. Therefore, a novel compound fault separation algorithm based on parallel dual-Qfactorsand improved maximum correlation kurtosis deconvolution (IMCKD) is proposed. First, thecompound fault signal is sparse-decomposed by the parallel dual-Q-factor, and the low-resonancecomponents of the signal (compound fault impact component and small amount of noise) are obtained,but it can only highlight the impact of compound faults, and failed to separate the inner and outerrace compound fault signal. Then, the MCKD is improved (IMCKD) by optimizing the selection ofparameters (the shift order M and the filter length L) based on the iterative calculation method withthe Teager envelope spectral kurtosis (TEK) index. Finally, after the composite fault signal is filteredand de-noised by the proposed method, the inner and outer race fault signals are obtained respectively.The fault characteristic frequency is consistent with the theoretical calculation value. The results showthat the proposed method can efficiently separate the mixed fault information and avoid the mutualinterference between the components of the compound fault.

Download Full-text

A Feature Extraction Method Using Improved Multi-Scale Entropy for Rolling Bearing Fault Diagnosis

Entropy ◽

10.3390/e20040212 ◽

2018 ◽

Vol 20 (4) ◽

pp. 212 ◽

Cited By ~ 12

Author(s):

Bin Ju ◽

Haijiao Zhang ◽

Yongbin Liu ◽

Fang Liu ◽

Siliang Lu ◽

...

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Extraction Method ◽

Rolling Bearing ◽

Feature Extraction Method ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Multi Scale

Download Full-text

An intelligent fault diagnosis method for rolling bearings based on feature transfer with improved DenseNet and joint distribution adaptation

Measurement Science and Technology ◽

10.1088/1361-6501/ac3b0b ◽

2021 ◽

Author(s):

Chenhui Qian ◽

Quansheng Jiang ◽

Yehu Shen ◽

Chunran Huo ◽

Qingkui Zhang

Keyword(s):

Fault Diagnosis ◽

Joint Distribution ◽

Marginal Distribution ◽

Vibration Signal ◽

Rolling Bearing ◽

Mechanical Equipment ◽

Intelligent Fault Diagnosis ◽

Rolling Bearings ◽

Bearing Fault Diagnosis ◽

Diagnosis Method

Abstract Mechanical intelligent fault diagnosis is an important method to accurately identify the health status of mechanical equipment. Traditional fault diagnosis methods perform poorly in the diagnosis of rolling bearings under complex conditions. In this paper, a feature transfer learning model based on improved DenseNet and joint distribution adaptation (FT-IDJ) is proposed. With this model, we apply it to implement rolling bearing fault diagnosis. A lightweight DenseNet model is firstly proposed to extract the transferable features of the raw vibration signal. Furthermore, the parameters in the DenseNet are constrained by the domain adaptive regularization term and pseudo label learning. The marginal distribution discrepancy and the conditional distribution discrepancy of the learned transferable features are reduced by this way. The proposed method is validated by the diagnosis experiments with CWRU and Jiangnan University rolling bearing datasets. The experimental results showed that the proposed FT-IDJ has higher classification accuracy than DAN and other eight methods, which demonstrated its effectively learning transferable features from auxiliary data.

Download Full-text

Rolling Bearing Fault Diagnosis based on Residual Neural Network

Frontiers of Mechatronical Engineering ◽

10.18282/fme.v2i4.1547 ◽

2020 ◽

Vol 2 (4) ◽

pp. 89

Author(s):

Haopeng Liang

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Rolling Bearing ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Multi Scale ◽

Diagnosis Method ◽

Hilbert Envelope ◽

Envelope Spectrum ◽

Residual Block

<div class="Section0"><div>Because rolling bearings have been working in an environment with complex and variable working conditions and large noise interference for a long time, the bearing fault diagnosis method has a poor diagnostic effect under variable working conditions. To solve this problem, we propose a residual neural network based on the diagnosis method of rolling bearing fault. The proposed method takes rolling bearing time-domain signal data as input. Because bearing signals have strong time-varying properties, we construct a multi-scale residual block that can not only learn features at different levels, but also expand the width and depth of the residual neural network. We use the advantages of the dilated convolution to expand the receptive field, replace part of the ordinary convolution in the multi-scale residual block with the dilated convolution, and design a multi-scale hollow residual block. The advantage is that the method is made by expanding the receptive field. It has a strong feature learning ability and can learn better features under limited data. Finally, we add a Dropout layer to discard a certain proportion of neurons after the fully connected layer, which can effectively avoid the negative impact of overfitting, and use Case Western Reserve University bearing dataset, the simulation experiment, and the SVM + EMD + Hilbert envelope spectrum, BPNN + EMD + Hilbert envelope spectrum and Resnet three ways of comparative analysis, the results show that the method under the variable condition of the fault diagnosis of rolling bearing has higher diagnosis accuracy, stronger noise resistance, and generalization ability.</div><p> </p></div><p> </p>

Download Full-text

A Novel Method for Extracting Maximum Kurtosis Component and Its Applications in Rolling Bearing Fault Diagnosis

Shock and Vibration ◽

10.1155/2019/8218237 ◽

2019 ◽

Vol 2019 ◽

pp. 1-17

Author(s):

Yonggang Xu ◽

Zeyu Fan ◽

Kun Zhang ◽

Chaoyong Ma

Keyword(s):

Fault Diagnosis ◽

Frequency Band ◽

Rolling Bearing ◽

Rolling Bearings ◽

Frequency Bands ◽

Bearing Fault Diagnosis ◽

Important Index ◽

Novel Method ◽

Simulation Signal ◽

Fault Information

Rolling bearing plays an important role in the overall operation of the mechanical system; therefore, it is necessary to monitor and diagnose the bearings. Kurtosis is an important index to measure impulses. Fast Kurtogram method can be applied to the fault diagnosis of rolling bearings by extracting maximum kurtosis component. However, the final result may disperse the effective fault information to different frequency bands or find wrong frequency band, resulting in inaccurate frequency band selection or misdiagnosis. In order to find the maximum component of kurtosis accurately, an algorithm of frequency band multidivisional and overlapped based on EWT (MDO-EWT) is proposed in this paper. This algorithm changes the traditional Fast Kurtogram frequency bands division method and filtering method. It builds the EWT boundaries based on the maximum kurtosis component in each iteration and finally obtains the maximum kurtosis component. Through the simulation signal and the rolling bearing inner and outer ring fault signals verification, it is proved that the proposed method has a good performance on accuracy and effectiveness.

Download Full-text

Fault Diagnosis of Rolling Bearing Based on MED and Morphological Filtering

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.989-994.3220 ◽

2014 ◽

Vol 989-994 ◽

pp. 3220-3223

Author(s):

Shang Kun Liu ◽

Gui Ji Tang ◽

Bin Pang

Keyword(s):

Fault Diagnosis ◽

Background Noise ◽

Amplitude Spectrum ◽

Rolling Bearing ◽

Minimum Entropy ◽

Rolling Bearings ◽

Bearing Fault Diagnosis ◽

Morphological Filtering ◽

Diagnosis Method ◽

Fault Characteristic

One rolling bearing fault diagnosis method based on minimum entropy deconvolution (MED) and morphological filtering is proposed. Firstly, the strong background noise of rolling bearings is decreased by the MED method, then the morphological filtering which have different length of structure elements is designed and applied to the de-noised signal. Subsequently, bearing’s fault characteristic frequency is extracted by the amplitude spectrum analysis to the best morphological filtering component which have the maximum kurtosis. This method is used to analyze both a simulated bearing signal and an experimental inner ring fault signal, and the good result validated the effectiveness of this method.

Download Full-text