Analog Circuit Fault Diagnosis Based on LVQ Neural Network

Abstract:

As an application of artificial intelligence technique in the field of analog circuit fault diagnosis, intelligent fault diagnosis system based on artificial neural network achieved certain success in practice. However, because neural network need for normalization preprocessing of sample before training, prolong the time of fault diagnosis, which is limited in the actual use of the diagnosis system. And the characteristics of LVQ(learning vector quantization) network is not need for normalization and other preprocessing of training samples, therefore, reducing the training time of neural networks. In this paper, the structure and training methods of the LVQ 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 simple and practical and so on.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 828-832
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.828
• Online since: August 2013
• Authors: Shi Guan Zhou, Guo Jun Li, Zai Fei Luo, Yan Zheng
• Keywords: Analog Circuit, Fault Diagnosis, LVQ, Neural Network (NN)

References

[1] L.J. Xu, J.G. Huang, H.J. Wang, A Method for the Diagnosis of the Incipient Faults in Analog Circuits Using HMM, Journal of Computer-Aided Design & Computer Graphics, 2010, 22(6): 1215-1222.

DOI: 10.3724/sp.j.1089.2010.10900

[2] J. Cui, Y. Wang, A novel approach of analog circuit fault diagnosis using support vector machines classifier, Measurement, 2011, 44(1): 281-289.

DOI: 10.1016/j.measurement.2010.10.004

[3] S.G. Zhou, Z.F. Luo, Application of Fuzzy Neural Network to Analog Circuit Fault Diagnosis, Applied Mechanics and Materials, 2012, 182: 1179-1183.

DOI: 10.4028/www.scientific.net/amm.182-183.1179

[4] D. Wu, L. Ping, Y. Fan, Fault Diagnosis of Power Electronic Circuits Based on BP Neural Network, Informatics and Management Science III, 2013: 115-120.

DOI: 10.1007/978-1-4471-4790-9_15

[5] X. Li, Y. Xie, Analog Circuits Fault Detection Using Cross-Entropy Approach, Journal of Electronic Testing, 2013: 1-6.

[6] Y.F. Huang, B. Jing, H.L. Zhou, Test point selection method for analog circuits based on essential degree, Control and Decision, 2011, 26(12): 1895-1899.

[7] P.F. YAN, C.S. ZHANG, Artificial neural networks and evolutionary computation. Beijing: Tsinghua University press. (2000).

[8] J. HUANG, Y.G. HE, The State-of-the-Art of Fault Diagnosis of Analog Circuits and Its Prospect, Microelectronics, 2004，34(1): 21-25.

[9] Pal N R, Bezdek J C, Tsao E C K, Generalized clustering networks and Kohonen's self-organizing scheme, Neural Networks, IEEE Transactions on, 1993, 4(4): 549-557.

DOI: 10.1109/72.238310

[10] TERRANCE L H, AJJIMARANGSEE P, Parallel self-organizing feature maps for unsupervised pattern recognition, International Journal Of General System, 1990, 16(4): 357-372.

DOI: 10.1080/03081079008935088

[11] Kohonen T, Self-organizing maps. Springer Verlag, (2001).

[12] S.G. Zhou, Y. Zhang, Analog Circuit Fault Diagnosis Using Evolving Neural Networks, Computer measurement and control，2007, 15(8), 991-993.