scholarly journals Analog Circuit Fault Diagnosis Using a Novel Variant of aConvolutional Neural Network

Algorithms ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 17
Author(s):  
Liang Han ◽  
Feng Liu ◽  
Kaifeng Chen
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Electronic Systems ◽  
Average Difference ◽  
Multi Scale ◽  
Novel Variant ◽  
Circuit Fault Diagnosis

Analog circuits play an important role in modern electronic systems. Aiming to accurately diagnose the faults of analog circuits, this paper proposes a novel variant of a convolutional neural network, namely, a multi-scale convolutional neural network with a selective kernel (MSCNN-SK). In MSCNN-SK, a multi-scale average difference layer is developed to compute multi-scale average difference sequences, and then these sequences are taken as the input of the model, which enables it to mine potential fault characteristics. In addition, a dynamic convolution kernel selection mechanism is introduced to adaptively adjust the receptive field, so that the feature extraction ability of MSCNN-SK is enhanced. Based on two well-known fault diagnosis circuits, comparison experiments are conducted, and experimental results show that our proposed method achieves higher performance.

Analog Circuit Intelligent Fault Diagnosis Based on PCA and OAOSVM

2012 ◽  
Vol 468-471 ◽  
pp. 802-806 ◽  
Author(s):  
Ke Guo ◽  
Yi Zhu ◽  
Ye San
Keyword(s):  
Principal Component Analysis ◽  
Fault Diagnosis ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Principal Component ◽  
Electronic Systems ◽  
Analysis Technique ◽  
Fault Features ◽  
Major Fault ◽  
Circuit Fault Diagnosis

Fault diagnosis of analog circuits is essential for guaranteeing the reliability and maintainability of electronic systems. Analog circuit fault diagnosis can be regarded as a pattern recognition issue and addressed by one-against-one SVM. In order to obtain a good SVM-based fault classifier, the principal component analysis technique is adopted to capture the major fault features. The extracted fault features are then used as the inputs of SVM to solve fault diagnosis problem. The effectiveness of the proposed method is verified by the experimental results.

scholarly journals Open-circuit fault diagnosis of traction inverter based on improved convolutional neural network

2020 ◽  
Vol 1633 ◽  
pp. 012099
Author(s):  
Jun Liu ◽  
Junnian Wang ◽  
Wenxin Yu ◽  
Zhenheng Wang ◽  
Guang’an Zhong
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Open Circuit ◽  
Circuit Fault Diagnosis

Application of Fuzzy Neural Network to Analog Circuit Fault Diagnosis

2012 ◽  
Vol 182-183 ◽  
pp. 1179-1183 ◽  
Author(s):  
Shi Guan Zhou ◽  
Zai Fei Luo
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Fuzzy Neural Network ◽  
Analog Circuit ◽  
Training Methods ◽  
Fuzzy Neural ◽  
Circuit Fault Diagnosis ◽  
Specific Implementation ◽  
The Mathematical Model ◽  
And Training

Considering the discreteness and non-linearity of the component parameter and the advancement and limitations of neural network in the analogous circuit fault diagnosis and as the combination of the fuzzy logic and neural network, the fuzzy neural network’s having the merits of both, involving learning, association, recognition, adaptation and fuzzy information processing, a method with fuzzy neural network for the analogous circuit fault diagnosis is proposed. In this paper, the structure and training methods of the fuzzy neural network are presented and the specific implementation of the diagnosis system is illustrated with examples. Simulation results show that the mathematical model has a better diagnostic effect. Compared with other methods, this diagnostic method, with the broad application prospect of its structure and method, is scientific, simple, and practical and so on.

scholarly journals Fault diagnosis of rolling bearing based on multi-scale one-dimensional convolutional neural network

2021 ◽  
Vol 1207 (1) ◽  
pp. 012003
Author(s):  
Xukun Hou ◽  
Pengjie Hu ◽  
Wenliao Du ◽  
Xiaoyun Gong ◽  
Hongchao Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Rolling Bearing ◽  
One Dimensional ◽  
Bearing Fault ◽  
Multi Scale ◽  
Reconstructed Signal ◽  
Using Data

Abstract Aiming at the typical non-stationary and nonlinear characteristics of rolling bearing vibration signals, a multi-scale convolutional neural network method for bearing fault diagnosis based on wavelet transform and one-dimensional convolutional neural network is proposed. First, the signal is decomposed into multi scale components with wavelet transform, and then each scale component is reconstructed. The reconstructed signal is subjected to the Fourier transform to obtain the frequency spectrum representation, which is used as the input of the one-dimensional convolutional neural network. Finally, one-dimensional convolution neural network is used to learn the features of the input data and recognize the bearing fault. The performance of the model is verified by using data sets of rolling bearing. The results show that this method can intelligent feature extraction and obtain 99.94% diagnostic accuracy.

Sign in / Sign up

Export Citation Format

Share Document