A transfer convolutional neural network for fault diagnosis based on ResNet-50

Wen, Long; Li, Xinyu; Gao, Liang

doi:10.1007/s00521-019-04097-w

Cited by 462 publications

(224 citation statements)

References 43 publications

Supporting

Mentioning

193

Contrasting

Order By: Relevance

“…The raw vibration signal has also been transformed to an imagery form for diagnosis purposes using techniques like Continuous Interleaved Sampling (CIS) [108]- [112], Omnidirectional Regeneration Technique (ORT) [113] and Symmetrized Dot Pattern (SDP) [114], [115]. Armed with these transformation techniques and the transfer learning strategy, several pretrained CNNs, originally trained on natural images, were transferred to fault diagnosis applications using vibration data; examples include LeNet-5 [107], [109], [110], VGG-16 [106], AlexNet [95] and ResNet-50 [108]. We also found some studies using auto-encoder [105], [116], [117] and random projection [118] as a pre-posed layer before a deep neural network for the purpose of denoising and compressing.…”

Section: ) Vibration Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

show abstract

Section: ) Vibration Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To further verify the effectiveness of the proposed rolling-element bearing fault diagnosis methods, the performance of improved 2D LeNet-5 network and improved 1D LeNet-5 network are compared with that of the other nine different fault diagnosis methods based on machine learning or deep learning, including SVM [8], k-NN [9], K-Means [10], BPNN [11], compact 1D CNN without fine-tuning [27], AlexNet [23], VGG-19 [24], ResNet-50 [25] and traditional LeNet-5 network [31].…”

Section: Comparison With Other Fault Diagnosis Methodsmentioning

confidence: 99%

Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network

Wan

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

To address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following improvements to the traditional LeNet-5 network are made: the convolution and pooling layers are reasonably designed and the size and number of convolution kernels are carefully adjusted to improve fault classification capability; the batch normalization (BN) is adopted after each convolution layer to improve convergence speed; the dropout operation is performed after each full-connection layer except the last layer to enhance generalization ability. To further improve the efficiency and effectiveness of fault diagnosis, on the basis of improved 2D LeNet-5 network, an end-to-end rolling-element bearing fault diagnosis method based on the improved 1D LeNet-5 network is proposed, which can directly perform 1D convolution and pooling operations on raw vibration signals without any preprocessing. The results show that the improved 2D LeNet-5 network and improved 1D LeNet-5 network achieve a significant performance improvement than traditional LeNet-5 network, the improved 1D LeNet-5 network provides a higher fault diagnosis accuracy with a less training time in most cases, and the improved 2D LeNet-5 network performs better than improved 1D LeNet-5 network under small training samples and strong noise environment.Sensors 2020, 20, 1693 2 of 23 clustering [10], back propagation neural network (BPNN) [11], etc. The traditional rolling-element bearing fault diagnosis methods have been widely used, but with the increasing complexity of vibration signals, these methods have a certain limitation; however, the deep learning methods have a greater advantage in analyzing complicated and non-stationary vibration signals.The deep learning methods can automatically extract fault features from vibration signals [12], recently there are many researches are conducted on rolling-element bearing fault diagnosis using deep learning. Yin et al. [13] extracted the original features of vibration signals through time-domain analysis, frequency-domain analysis and wavelet transform, and obtained the low-dimensional features from 38 original features using the nonlinear global algorithm, and the low-dimensional features array is input into the deep belief network (DBN) to evaluate the performance status of rolling-element bearing. Liu et al. [14] obtained the spectrogram of vibration signals through STFT, used the stacked sparse auto-encoder (SAE) to automatically extract fault features, and employed the softmax regression to identify the fault type of rolling-element bearing. Liu et al. [15] used the recurrent neural network (RNN) to classify the faults of rolling-element bearing, and adopted the gated recurrent unit based denoising auto-encoder to enhance fault classification accuracy. Among different deep learning methods, compared with DBN, ...

show abstract

“…Because conventional convolutional neural network is limited to a fixed geometric structure during modeling and the sampling position of the convolution unit on the input image remains unchanged each time, not only is the feature loss serious, but also the fitting ability of loss function becomes weak, and the overall performance of the network degrades. To solve the above problems, this paper introduces deformable convolution [ 30 , 31 , 32 ] to reconstruct the convolutional layers of the basic network ResNet-50 [ 33 , 34 , 35 ]. The conventional convolution structure is defined as follows:

where

is the offset of each point relative to each point on the receptive field after sampling, usually an integer; R is the sampling grid; and

is the sampling weight.…”

Section: Theories and Methodsmentioning

confidence: 99%

Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

Zhao

Huang

et al. 2020

Sensors

View full text Add to dashboard Cite

To meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET) algorithm for detecting pointer defects. Firstly, the convolutional layers of ResNet-50 are reconstructed by deformable convolution, which enhances the learning of pointer surface defects by feature extraction network. Furthermore, the problems of missing detection caused by internal differences and weak features are effectively solved. Secondly, the idea of online hard example mining (OHEM) is used to improve the Cascade-RCNN detection network, which achieve accurate classification of defects. Finally, based on the fact that common pointer defect dataset and pointer defect dataset established in this paper have the same low-level visual characteristics. The network is pre-trained on the common defect dataset, and weights are transferred to the defect dataset established in this paper, which reduces the training difficulty caused by too few data. The experimental results show that the proposed method achieves a 0.933 detection rate and a 0.873 mean average precision when the threshold of intersection over union is 0.5, and it realizes high precision detection of pointer surface defects.

show abstract

A transfer convolutional neural network for fault diagnosis based on ResNet-50

Cited by 462 publications

References 43 publications

A Review on Deep Learning Applications in Prognostics and Health Management

A Review on Deep Learning Applications in Prognostics and Health Management

Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network

Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

Contact Info

Product

Resources

About