Multi-Scale CNN based on Attention Mechanism for Rolling Bearing Fault Diagnosis

Recently, deep learning technology was successfully applied to mechanical fault diagnosis. The convolutional neural network (CNN), as a prevalent deep learning model, occupies a place in intelligent fault diagnosis, which reduces the need for human feature extraction and prior knowledge, thereby achieving an end-to-end intelligent fault diagnosis model. However, the data for mechanical fault diagnosis in practical application are limited, the CNN model is too deep and too complex, making it prone to overfitting, and a model with too simple a structure and shallow layers cannot fully learn the effective features of the data. Convolutional filters with fixed window sizes are widely used in existing CNN models, which cannot flexibly select variable pivotal features. The model may be interfered with by redundant information in feature maps during training. Therefore, in this paper, a novel shallow multi-scale convolutional neural network with attention is proposed for bearing fault diagnosis. The shallow multi-scale convolutional neural network structure can fully learn the feature information of input data without overfitting. For the first time, a feature attention mechanism is developed for fault diagnosis to adaptively select features for classification more effectively, where the pivotal feature was emphasized, and the redundant feature was weakened through an attention mechanism. The time frequency representations as the input of the model were obtained from the vibration time domain signals, which contain the complete time domain and frequency domain information of the vibration signals. Compared with the current popular diagnostic methods, the results show that the proposed diagnostic method has fairly high accuracy, and its performance is superior to the existing methods. The average recognition accuracy was 99.86%, and the weak recognition rate of I-07 and I-14 labels was improved.

Download Full-text

Parallel multi-scale entropy and it's application in rolling bearing fault diagnosis

Measurement ◽

10.1016/j.measurement.2020.108333 ◽

2021 ◽

Vol 168 ◽

pp. 108333

Author(s):

Dongfang Zhao ◽

Shulin Liu ◽

Shouguo Cheng ◽

Xin Sun ◽

Lu Wang ◽

...

Keyword(s):

Fault Diagnosis ◽

Rolling Bearing ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Multi Scale

Download Full-text

Rolling Bearing Fault Diagnosis Algorithm Based on Overlapping Group Sparse Model-Deep Complex Convolutional Neural Network

10.21203/rs.3.rs-888210/v1 ◽

2021 ◽

Author(s):

FENGPING AN ◽

Jianrong Wang

Keyword(s):

Neural Network ◽

Deep Learning ◽

Fault Diagnosis ◽

Convolutional Neural Network ◽

Rolling Bearing ◽

Operating Conditions ◽

Sparse Model ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Multi Scale

Abstract As the key component of a mechanical system, rolling bearings will cause paralysis of the entire mechanical system once they fail. In recent years, considering the high generalization ability and nonlinear modeling ability of deep learning, a rolling bearing fault diagnosis method based on deep learning has been formed, and good results have been achieved. However, because this kind of method is still in the initial development stage, its main problems are as follows. First, it is difficult to extract the composite fault signal feature of rolling bearing. Second, the existing deep learning rolling bearing fault diagnosis methods cannot well consider the problem of multi-scale information of rolling bearing signals. Therefore, this paper first proposes the overlapping group sparse model. It constructs weight coefficients by analyzing the salient features of the signal. It uses convex optimization techniques to solve the sparse optimization model, and applies the method to the feature extraction of rolling bearing composite faults. For the problem of multi-scale feature information extraction of rolling bearing composite fault signals, this paper proposes a new deep complex convolutional neural network model. This model fully considers the multi-scale information of rolling bearing signals. The complex information in this model not only contains rich representation ability, but also can extract more scale information. Finally, the classifier of this model is used to identify rolling bearing faults. Based on this, this paper proposes a new rolling bearing fault diagnosis algorithm based on overlapping group sparse model-deep complex convolutional neural network. The experimental results show that the method proposed in this paper can not only effectively identify rolling bearing faults under constant operating conditions, but also accurately identify rolling bearing fault signals under changing operating conditions. Additionally, the classification accuracy of the method proposed in this paper is greatly improved compared with traditional machine learning methods. It also has certain advantages over other deep learning methods.

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