An intelligent diagnosis method of rolling bearing based on multi-scale residual shrinkage convolutional neural network

Zhao, Xiaoqiang; Zhang, Yazhou

doi:10.1088/1361-6501/ac68d1

Cited by 11 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the superior performance of the proposed method, we chose to compare it with advanced deep learning methods, including WDCNN [6], ResNet [10], MRSCNN [11], and MSDARN [2]. WDCNN uses wide convolution in the first layer, which can effectively suppress the interference of strong noise.…”

Section: Comparison Methodsmentioning

confidence: 99%

A dual attention module and convolutional neural network based bearing fault diagnosis

2022

jeis

View full text Add to dashboard Cite

Vibration signals of rolling bearings are affected by changing operating conditions and environmental noise, so they are characterized by a high degree of complexity. Although deep learning fault diagnosis methods have achieved considerable success in practical applications, the high complexity characteristics are ignored. To address this issue, we propose a dual attention module and convolutional neural network (DAM-CNN) for rolling bearing fault diagnosis. In this method, we designed a dual-attention module (DAM) by using a channel-attention module and a spatial-attention module. DAM can recode feature information in channel and spatial dimensions, so as to achieve adaptive enhancement of effective network information and suppression of interference information. In addition, to enhance the extraction of long-range features of the convolutional network, we introduce the non-local feature extraction module. This module can significantly expand the perceptual field of convolutional operations and enhance the generalization ability of the network. By verifying the effectiveness of the method in CWRU datasets, the results show that the method in this paper not only has good noise immunity in strong noise environment, but also has high diagnostic accuracy and good generalization performance in different load condition domains.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

A dual attention module and convolutional neural network based bearing fault diagnosis

2022

jeis

View full text Add to dashboard Cite

show abstract

“…Research outcomes manifest that this approach boasts a high level of accuracy under variable working situations as well as in the absence of dataset. Zhao and Zhang [20] introduced a novel CNN model using multiscale residual shrinkage framework, which develops multiscale residual shrinkage layers and residual shrinkage blocks. Such a method facilitates the automatic learning of signal features through input data.…”

Section: Introductionmentioning

confidence: 99%

A novel fault diagnosis approach of rolling bearing using intrinsic feature extraction and CBAM-enhanced InceptionNet

Yuan

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Rolling bearings play a crucial role as components in mechanical equipment. Malfunctioning rolling bearings can disrupt the normal operation of the equipment and pose safety hazards. Traditional deep learning (DL)-based methods for diagnosing faults in rolling bearings present several issues, such as insufficient feature information of fault samples, high model complexity and low accuracy. To overcome these challenges, this paper introduces an intelligent approach for rolling bearing fault diagnosis using intrinsic feature extraction (IFE) and convolutional block attention module (CBAM)-enhanced InceptionNet. In our researches, variational mode decomposition (VMD) is adopted to decompose the original signal into multiple band-limited intrinsic mode functions (BLIMFs). In the decomposition process of VMD, the number of decomposition layers k is determined by center frequency method and the optimal BLIMF is chosen based on minimum envelope entropy. Subsequently, the continuous wavelet transform (CWT) is employed to transform the optimal BLIMF into time-frequency images. Finally, the obtained time-frequency images are fed into the proposed CBAM-enhanced InceptionNet for fault state diagnosis. Experiments on two different datasets prove that the method has stable and reliable accuracy. Comparative experiments have demonstrated that this method can reduce network model parameters and improve diagnosis efficiency while achieving high accuracy.

show abstract

“…This novel approach alleviates the difficulties associated with parameter optimization and achieves denoising through soft thresholding, where the threshold is automatically determined by the attention sub-network. As a result of its remarkable denoising and parameter optimization capabilities, various fault diagnosis methods based on DRSN have been proposed [22][23][24][25]. For example, Tong et al [22] combined DRSN with bidirectional LSTM to enhance spatial feature extraction, resulting in commendable performance in diagnosing bearing faults.…”

Section: Introductionmentioning

confidence: 99%

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Zhang

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Recently, the fault diagnosis domain has witnessed a surge in the popularity of the deep residual shrinkage network (DRSN) due to its robust denoising capabilities. In our previous research, an enhanced version of DRSN named global multi-attention DRSN (GMA-DRSN) is introduced to augment the feature extraction proficiency of DRSN specifically for noised vibration signals. However, the utilization of multiple attention structures in GMA-DRSN leads to an escalation in the computational complexity of the network, which may pose practical deployment challenges. To address this limitation, this paper proposes a lightweight variant of GMA-DRSN, referred to as LGMA-DRSN, building upon our prior work. Firstly, the numerical variation regularity of the adaptive inferred slope parameters in the global parametric rectifier linear unit (GPReLU) is analyzed, where we surprisingly find that a convex parameter combination always occurs in pairs. Based on this convex regularity, the sub-network structure of the adaptive inferred slope with attention mechanism is optimized, which greatly reduces the computational complexity compared to our previous work. Finally, the experimental outcomes demonstrate that LGMA-DRSN not only enhances diagnostic efficiency, but also ensures a high level of diagnostic accuracy in the presence of noise interference, when compared with our prior work.

show abstract

An intelligent diagnosis method of rolling bearing based on multi-scale residual shrinkage convolutional neural network

Cited by 11 publications

References 39 publications

A dual attention module and convolutional neural network based bearing fault diagnosis

A dual attention module and convolutional neural network based bearing fault diagnosis

A novel fault diagnosis approach of rolling bearing using intrinsic feature extraction and CBAM-enhanced InceptionNet

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Contact Info

Product

Resources

About