CBAM-CNN based analog circuit fault diagnosis

被引：0

作者：

Du X.-J. ^{[1
,2
]}

Gong B. ^{[1
]}

Yu P. ^{[1
,2
]}

Shi Y.-K. ^{[1
]}

Angelina K.V. ^{[1
]}

Cheng S.-Y. ^{[1
,2
]}

机构：

[1] College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou

[2] Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou

来源：

Kongzhi yu Juece/Control and Decision | 2022年 / 37卷 / 10期

关键词：

analog circuit; attention mechanism; convolutional neural network; fault diagnosis; feature extraction;

D O I：

10.13195/j.kzyjc.2021.1111

中图分类号：

学科分类号：

摘要：

The difficulty in extracting the fault features of analog circuits leads to complex calculation and poor precision with the model. A fault diagnosis method for analog circuits based on the attention mechanism and the convolutional neural network (CBAM-CNN) is proposed. Firstly, the image features of the input layer are extracted by using the convolution kernel, and a rectifying linear unit (ReLU) is connected behind each convolution layer, and a batch normalization (BN) layer is added to solve the problem of internal covariate migration, so as to improve the expression ability of the nonlinear model. Secondly, the convolutional block attention module (CBAM) is added after the batch normalization layer to extract the important features. After that, the pooling layer is connected to reduce the computational complexity of the network and improve the accuracy and efficiency of the network. Finally, the Sallen-Key low-pass filter and the two-stage four-op amplifier double-order low-pass filter are taken as the research objects. The results of fault diagnosis experiments demonstrate that the proposed method can effectively improve the diagnosis accuracy and realize the classification and location of all faults with high difficulty. © 2022 Northeast University. All rights reserved.

引用

页码：2609 / 2618

页数：9

共 45 条

[1] Sai S V A, Long B, Pecht M., Diagnostics and prognostics method for analog electronic circuits, IEEE Transactions on Industrial Electronics, 60, 11, pp. 5277-5291, (2013)
[2] Jia R X, Wang J, Zhou J L., Fault diagnosis of industrial process based on the optimal parametric t-distributed stochastic neighbor embedding, Science China Information Sciences, 64, 5, pp. 1-3, (2020)
[3] Gao M Z, Xu A Q, Tang X F, Et al., Analog circuit diagnostic method based on multi-kernel learning multiclass relevance vector machine, Acta Automatica Sinica, 45, 2, pp. 434-444, (2019)
[4] Mei H R, Yin L S, Liu D M, Et al., Analogue circuit fault diagnosis based on SVM optimized by IPSO, Journal of Electronic Measurement and Instrumentation, 31, 8, pp. 1239-1246, (2017)
[5] Tang X F, Xu A Q., Practical analog circuit diagnosis based on fault features with minimum ambiguities, Journal of Electronic Testing, 32, 1, pp. 83-95, (2016)
[6] Tadeusiewicz M, Hagas S., A method for local parametric fault diagnosis of a broad class of analog integrated circuits, IEEE Transactions on Instrumentation and Measurement, 67, 2, pp. 328-337, (2018)
[7] Aminian M, Aminian F., A modular fault-diagnostic system for analog electronic circuits using neural networks with wavelet transform as a preprocessor, IEEE Transactions on Instrumentation and Measurement, 56, 5, pp. 1546-1554, (2007)
[8] Zhang C L, He Y G, Du B L., Analog circuit incipient fault diagnosis method based on DBN feature extraction, Chinese Journal of Scientific Instrument, 40, 10, pp. 112-119, (2019)
[9] Zhang C L, He Y G, Yuan L F, Et al., A novel approach for diagnosis of analog circuit fault by using GMKL-SVM and PSO, Journal of Electronic Testing, 32, 5, pp. 531-540, (2016)
[10] Gan X S, Gao W M, Dai Z, Et al., Research on WNN soft fault diagnosis for analog circuit based on adaptive UKF algorithm, Applied Soft Computing, 50, pp. 252-259, (2017)

← 1 2 3 4 5 →