Multiscale Kernel Based Residual Convolutional Neural Network for Motor Fault Diagnosis Under Nonstationary Conditions

Liu, Ruonan; Wang, Fei; Yang, Boyuan; Qin, S. Joe

doi:10.1109/tii.2019.2941868

Cited by 244 publications

(70 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sentiment word vector SWV is trained with sentiment words and text sentiment tags. e research of Liu et al [19] showed that from perceptron presentation to 2006, this stage is called shallow learning, and from 2006 to now, it is the third stage of the neural network, called deep learning. Deep learning is divided into the rapid development period (2006)(2007)(2008)(2009)(2010)(2011)(2012) and the outbreak period (2012-present).…”

Section: Related Workmentioning

confidence: 99%

Language Processing Model Construction and Simulation Based on Hybrid CNN and LSTM

Zhang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Deep learning is the latest trend of machine learning and artificial intelligence research. As a new field with rapid development over the past decade, it has attracted more and more researchers’ attention. Convolutional Neural Network (CNN) model is one of the most important classical structures in deep learning models, and its performance has been gradually improved in deep learning tasks in recent years. Convolutional neural networks have been widely used in image classification, target detection, semantic segmentation, and natural language processing because they can automatically learn the feature representation of sample data. Firstly, this paper analyzes the model structure of a typical convolutional neural network model to increase the network depth and width in order to improve its performance, analyzes the network structure that further improves the model performance by using the attention mechanism, and then summarizes and analyzes the current special model structure. In order to further improve the text language processing effect, a convolutional neural network model, Hybrid convolutional neural network (CNN), and Long Short-Term Memory (LSTM) based on the fusion of text features and language knowledge are proposed. The text features and language knowledge are integrated into the language processing model, and the accuracy of the text language processing model is improved by parameter optimization. Experimental results on data sets show that the accuracy of the proposed model reaches 93.0%, which is better than the reference model in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Language Processing Model Construction and Simulation Based on Hybrid CNN and LSTM

Zhang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…To verify the superiority of the proposed model, four existing multiscale CNN models, including MK-ResCNN [33], AWMSCNN [27], MS-DCNN [36], and MSCNN [32] are implemented as comparisons in this study. The MK-ResCNN uses three scale branches composed of three different kernel sizes (3×1, 5×1, and 7×1).…”

Section: E Comparison With Existing Multiscale Cnn Modelsmentioning

confidence: 99%

“…However, due to the defects of its multiscale signals acquisition method, the number of scales is constrained by the length of the input sample. In [33], an MK-ResCNN architecture was proposed, which provides a solution to the above problem. In MK-ResCNN, convolutional kernels with different sizes were utilized to extract multiscale features from vibration signals in parallel, and identity mapping and residual mapping were introduced to overcome the degradation problem caused by deep networks.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, existing multiscale models have to make a trade-off between diagnosis performance and the cost of storage and computation. As a result, they usually use fewer scales (four scales were used in [27,32,36], and three scales were used in [33]), or stack multiple convolutional layers with narrow kernels instead of a layer with wide kernel [33].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Lightweight Multiscale Convolutional Neural Network for Rolling Bearing Fault Diagnosis

et al. 2020

View full text Add to dashboard Cite

The vibration signals collected from rolling bearings in industrial systems are highly complex and contain intense environmental noise, which challenges the performance of traditional fault diagnosis methods. Moreover, the applicability of the model in engineering practice, especially in the Industrial Internet of Things context, puts forward higher requirements for its storage and computational costs. Considering these challenges, this article proposes an enhanced lightweight multiscale convolutional neural network (CNN) for rolling bearing fault diagnosis. Our contributions mainly fall into three aspects. Firstly, the proposed model is modular and easy to expand, which combines the idea of multiscale learning with attention mechanism and residual learning, enabling the network to extract more abundant and discriminative fault features directly from the raw vibration signal. Consequently, the proposed model can perform better. Secondly, the interpretability of the multiscale learning mechanism is explored by visualizing the extraction process of multiscale features. Finally, for the first time, we introduce the depthwise separable convolution into multiscale CNN to reduce the storage and computational costs of the model, which realizes the lightweight of the model and improves its applicability in the Industrial Internet of Things context. The experimental results on the rolling bearing dataset demonstrate that, compared with the state-of-the-art multiscale CNN models, the proposed model has better discriminative fault feature extraction ability and antinoise ability, and is more suitable for practical industrial systems.

show abstract

“…While some papers have proposed similar network architectures of multi-scale convolution [ 24 , 25 , 26 , 27 ], our approach differs from theirs in the following respects: (a) Most existing papers focus on general classification problems, but we have verified the effectiveness of multi-scale structure in domain adaptation; (b) Most methods do not clarify the physical meaning of multi-scale convolution, but our method is driven by the frequency-domain characteristics of convolution kernels, which has a clear physical meaning. Compared with the previous domain adaptation methods for fault diagnosis, our proposed method is unified and suitable for different domain adaptation losses.…”

Section: Introductionmentioning

confidence: 99%

Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Zheng

et al. 2021

Sensors

View full text Add to dashboard Cite

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN.

show abstract

Multiscale Kernel Based Residual Convolutional Neural Network for Motor Fault Diagnosis Under Nonstationary Conditions

Cited by 244 publications

References 33 publications

Language Processing Model Construction and Simulation Based on Hybrid CNN and LSTM

Language Processing Model Construction and Simulation Based on Hybrid CNN and LSTM

Enhanced Lightweight Multiscale Convolutional Neural Network for Rolling Bearing Fault Diagnosis

Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Contact Info

Product

Resources

About