Deep Residual Shrinkage Networks for Fault Diagnosis

Zhao, Minghang; Zhong, Shisheng; Fu, Xuyun; Tang, Baoping; Pecht, Michael

doi:10.1109/tii.2019.2943898

Cited by 889 publications

(331 citation statements)

References 22 publications

Supporting

Mentioning

329

Contrasting

Unclassified

Order By: Relevance

“…(1) Enough source-domain samples are used to pre-train a source modified CNN by minimizing cross-entropy error between the true and predicted labels according to Eqs. (7)(8)(9). (2) Prepare a target modified CNN holding the same structure and hyperparameters as the source model.…”

Section: B Construction Of Modified Transfer Cnnmentioning

confidence: 99%

“…A large number of studies have claimed that the diagnosis results of different shallow learning models are largely affected by the effectiveness of extracted features [7][8][9]. Recently, more and more attention has been paid to deep learning-based approaches with automatic feature learning capability, such as deep belief network (DBN), stacked auto-encoder (SAE), convolutional neural network (CNN), long short-term memory (LSTM), etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images

Shao

Xia

Han

et al. 2021

IEEE Trans. Ind. Inf.

334

View full text Add to dashboard Cite

The existing intelligent fault diagnosis methods of rotor-bearing system mainly focus on vibration analysis under steady operation, which has low adaptability to new scenes. In this paper, a new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using a modified convolutional neural network (CNN) with transfer learning. First, infrared thermal images are collected and used to characterize the health condition of rotor-bearing system. Second, modified CNN is developed by introducing stochastic pooling and Leaky rectified linear unit to overcome the training problems in classical CNN. Finally, parameter transfer is used to enable the source modified CNN to adapt to the target domain, which solves the problem of limited available training data in the target domain. The proposed method is applied to analyze thermal images of rotor-bearing system collected under different working conditions. The results show that the proposed method outperforms other cutting edge methods in fault diagnosis of rotor-bearing system.

show abstract

Section: B Construction Of Modified Transfer Cnnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images

Shao

Xia

Han

et al. 2021

IEEE Trans. Ind. Inf.

334

View full text Add to dashboard Cite

show abstract

“…whereĤ is the channel matrix obtained by the estimator, represents the SNR of the communication chain, and I N is the identity matrix of size N × N . [26]. This structure consists of a series of residual shrink building units (RSBUs).…”

Section: Channel Equalisermentioning

confidence: 99%

Deep learning‐based digital signal modulation identification under different multipath channels

Zhang

et al. 2021

IET Communications

View full text Add to dashboard Cite

Deep learning (DL) has been applied to digital signal modulation identification (DSMI) due to its powerful feature learning ability. However, most of the existing DL-based DSMI methods are limited to specific experimental scene relating to the additive white Gaussian noise (AWGN) channel or static multipath channel. The result is that the trained network has deteriorative identification accuracy when the channel conditions change unless retrained. To solve the problem, this paper proposes a DSMI method suitable for orthogonal frequency division multiplexing (OFDM) under different multipath channels, including the variation of delay, path number and channel coefficient. This method can accurately detect the modulation feature rather than the channel's to identify the modulation type, thus reducing the network training amount. The method is divided into two parts. Firstly, traditional signal processing methods are combined, including various channel estimators and equalisers to compensate for the channel. Then a robust DL network, RSN-MI, is designed as a classifier. Unlike other DL-based DSMI methods, the influence of signal processing algorithms on DSMI performance are focused on rather than model parameters. Besides, the proposed classifier is compared with the DSMI classifier in other contributions. The results show that the classifier works better in different multipath channels. INTRODUCTIONDigital signal modulation identification (DSMI) is of great significance in wireless communication systems. As a necessary step between signal detection and demodulation, it has attracted more and more attention. The main task of DSMI is to identify the modulation type of the received signal without using any prior knowledge or using a small amount of prior knowledge, which lays the foundation for subsequent signal demodulation and information acquisition. DSMI plays an important role in both military and civil fields [1], especially in military fields, modulation identification is the prerequisite of jamming and monitoring enemy communications. It can also be used for spectrum detection and signal confirmation etc. in civil fields. Two traditional digital signal modulation identification approaches have been extensively studied: one is the maximum likelihood (ML) approach, and the other is the pattern recognition (PR) approach [2]. The maximum likelihood approach is based on the likelihood function of received signal, and the likelihood ratio is compared with the appropriate threshold value to achieve the best classification effect under the minimum errorThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…The number of convolution kernels of the first and the second convolutional layers was 32, while the numbers of convolution kernels for the four modules in the dashed box were 64, 96, 128, and 160, respectively. For the module in the dashed box, we adopted a residual connection method [31] similar to the deep residual network to make the model fully use the global context information, and introduced a Squeezeand-Excitation (SE) module [32] to improve the sensitivity of our model for channel features. When the convolutional network performs convolution layer by layer, the obtained features are transferred from details (textures, lines, etc.)…”

Section: Description Of Cnn Layersmentioning

confidence: 99%

Interpretation of Electrocardiogram (ECG) Rhythm by Combined CNN and BiLSTM

Xue

Jeong

2020

IEEE Access

View full text Add to dashboard Cite

Computer-aided detection and diagnosis in ECG signals for heart diseases are gaining increasing attention. However, developing and selecting the highly performing diagnostic model suitable for clinical implications is still challenging. In this paper, we proposed a combined network of convolutional neural network (CNN) and Recurrent Neural Network (RNN), designed for the classification of ECG heart signals for diagnostic purpose. The proposed network consists of 2 convolutional layers with 5x5 kernels and ReLU activations, followed by 4 residual blocks, 2 bidirectional long short-term memory (biLSTM) layers, as well as 2 fully connected layers. Each residual block involved the structure of a Squeeze-and-Excitation Network (SENet) with lightweight property to recalibrate the feature map of the network. The last dense layer has 5 outputs, equivalent to the classes considered: non-ectopic beats, supraventricular ectopic beats, ventricular ectopic beats, fusion beats, and unknown beats. To train and evaluate the combined CNN and RNN, we transferred the knowledge acquired on beat classification tasks in 2017 PhysioNet/CinC Challenge to that in PhysionNet's MIT-BIH dataset. The developed network achieved a recognition sensitivity of 95.90%, accuracy = 95.90% and specificity = 96.34% with classification time of single sample = 6.23 s in detecting 5 ECG classes. A comparative analysis proved the high performance of the proposed combined CNN and RNN against previous methods, demonstrated the potential of our proposed network in the analysis of beat patterns. The proposed model can be applied in cloud computing or implemented in mobile devices to evaluate cardiac health with the highest precision.

show abstract

Deep Residual Shrinkage Networks for Fault Diagnosis

Cited by 889 publications

References 22 publications

Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images

Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images

Deep learning‐based digital signal modulation identification under different multipath channels

Interpretation of Electrocardiogram (ECG) Rhythm by Combined CNN and BiLSTM

Contact Info

Product

Resources

About