Global contextual residual convolutional neural networks for motor fault diagnosis under variable-speed conditions

Xu, Yadong; Yan, Xiaoan; Sun, Beibei; Liu, Zheng

doi:10.1016/j.ress.2022.108618

Cited by 58 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prove the effectiveness of the proposed ASG-HOMGATbased fault diagnosis method, the standard graph convolutional neural network (GCN) [33], the multiple-receptive field graph convolutional neural network (MRF-GCN) [24], the graph attention network (GATv2) [41], the GraphSAGE [42], the three kinds of Chebyshev graph convolutional networks with receptive fields k of 1,2,3, respectively [43], the GC-ResCNN [44], the ASG-HOGCN (not using multi-head attention mechanism network) for comparative experiments, these models are able to capture the structural relationship between samples and achieve effective fault diagnosis, GCN can effectively aggregate the information of neighboring nodes in the graph structure through spectral convolution, which in turn improves the ability of fault feature extraction, MRF-GCN helps the model to analyze the fault features in a more comprehensive way by converting the data samples into a weighted graph and learning the feature representations from multiple neighborhoods, GATv2 uses the attention mechanism combined with assigning different weights to neighboring node in the graph-structured data, GraphSAGE generates new feature representations for each node by learning an aggregation function to aggregate the neighboring features of the nodes, Chebynet by using chebyshev polynomial expansions of different orders, ChebyNet can flexibly handle graphs with different sensory wild sizes of the data and enables efficient graph convolution operations through approximate computation.…”

Section: Domain Adaptability Of Variable Loadsmentioning

confidence: 99%

ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis

Ding,

Chen,

Liu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Traditional Euclidean spatial data processing is difficult to capture the inherent relationships of unstructured data such as bearing vibration signals. Representing vibration signals in graphical form helps to preserve their topologi-cal structure and temporal information. Secondly, most existing graph convolutional network methods are based on large graph structured data, which incurs certain memory overhead when aggregating high-order neighborhood node information and ignores important information between samples in the global graph structure. To address these issues, this paper proposes a high-order multi-head graph attention network based on an adaptive small graph struc-ture (ASG-HOMGAT) for fault diagnosis of rolling bearings. Firstly, the adaptive preprocessing layer is used to adaptively denoise and compress the one-dimensional time-domain vibration signal, generating small rule graph data with topological structure. Then, these small graph structured data samples are input into a higher-order graph neural network, which aggregates features from multiple higher-order neighborhoods to achieve richer feature repre-sentations and fully explore the intrinsic correlation between samples. Finally, these features are aggregated into a reinforced representation of graph nodes through a multi head attention mechanism, and a SoftMax classifier is used for fault classification. The experimental results show that the ASG-HOMGAT method has better performance com-pared to mainstream graph neural network diagnostic models. The code and model will be released at: https://github.com/ding-ss/ASG-HOMGAT.

show abstract

Section: Domain Adaptability Of Variable Loadsmentioning

confidence: 99%

ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis

Ding,

Chen,

Liu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The study conducted by Ribeiro et al [6] suggests using Short Time Fourier Transform (STFT) in a CNN to extract information from vibration signals . A global context residual convolutional neural network was developed by Xu et al [7] . The aim was to find a suitable global context module that would enhance focus on global discriminative features within the model.…”

Section: Stage 2: Improved Cnn For Motor Fault Diagnosismentioning

confidence: 99%

Research on convolutional neural networks in motor fault diagnosis

Wang,

2024

Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023)

View full text Add to dashboard Cite

The state of the motor greatly affects the overall performance of the transmission system, and implementing advanced motor fault diagnosis technology can prevent substantial financial losses. Deep learning algorithms, such as convolutional neural networks, are increasingly gaining popularity due to their ability to handle the prominent challenges posed by high feature dimensionality, large datasets, ambiguous labels, and sparse occurrence of motor fault types and causes. This paper extensively examines the usage of convolutional neural networks (CNN) and their different versions in different motor fault diagnosis problems by analyzing a wide range of international journal papers, leading to essential findings.

show abstract

“…Then, backpropagation is used to continuously adjust the model weight parameters according to the objective function to find the weight parameters that are most suitable for the target task. As shown in figure 1, the CNN includes a convolution layer, pooling layer and fully connected (FC) layer [19,20], and the corresponding functions of these layers are convolution, downsampling and full connection, respectively.…”

Section: Cnnmentioning

confidence: 99%

An anti-noise fault diagnosis approach for rolling bearings based on multiscale CNN-LSTM and a deep residual learning model

Chen¹,

Wei²,

Li³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Bearing fault vibration signals collected in real engineering cases often contain environmental noise, which easily causes the fault type characteristics of vibration signals to not be apparent, making it difficult to determine the corresponding fault type when traditional deep learning methods are used for fault diagnosis. To solve the above problems, a neural network model named MCL-DRL was designed, which combines a multiscale wide convolution kernel CNN-LSTM module and a deep residual module for rolling bearing fault diagnosis. In this model, a wide convolution kernel CNN-LSTM structure with different convolution scales is used to extract a variety of different types of frequency and sequential features from vibration signals. It is worth noting that the wide convolution kernel CNN-LSTM structure not only has stronger feature extraction performance compared with the common convolution layer but can also reduce the interference of high-frequency noise. Moreover, the deep residual module with a wide convolution kernel CNN-LSTM structure is used to further improve the feature expression ability of the proposed model. The above algorithm enables the proposed model to better extract the fault features hidden in the noise signal.When compared with some state-of-the-art methods, the experimental results showed that this model has better antinoise performance and better generalization ability for rolling bearing fault diagnosis.

show abstract

Global contextual residual convolutional neural networks for motor fault diagnosis under variable-speed conditions

Cited by 58 publications

References 30 publications

ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis

ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis

Research on convolutional neural networks in motor fault diagnosis

An anti-noise fault diagnosis approach for rolling bearings based on multiscale CNN-LSTM and a deep residual learning model

Contact Info

Product

Resources

About