A Neural-Network-Based Fault Diagnosis Approach for Analog Circuits by Using Wavelet Transformation and Fractal Dimension as a Preprocessor

This paper presents a new method of analog fault diagnosis based on back-propagation neural networks (BPNNs) using wavelet decomposition and fractal dimension as preprocessors. The proposed method has the capability to detect and identify faulty components in an analog electronic circuit with tolerance by analyzing its impulse response. Using wavelet decomposition to preprocess the impulse response drastically de-noises the inputs to the neural network. The second preprocessing by fractal dimension can extract unique features, which are the fed to a neural network as inputs for further classification. A comparison of our work with [1] and [6], which also employs back-propagation (BP) neural networks, reveals that our system requires a much smaller network and performs significantly better in fault diagnosis of analog circuits due to our proposed preprocessing techniques.

• Wenji Zhu
• Yigang He

• Analog circuits
• fault diagnosis
• tolerance
• wavelettransform
• fractal dimension
• box dimension.

[1] Robert Spina, Shambhu Upadhyaya, "Linear circuit fault diagnosis using
neuromorphic anlayzers", IEEE transactions on circuits and systems-II:
analog and digital signal processing, Vol.44, No.3, March
1997,pp188-196.
[2] Xiaobai Mao, Liheng Wang, Changxi Li, "SVM classifier for analog fault
diagnosis using fractal features", Second international symposium on
intelligent information technology application, pp553-557, 2008.
[3] Zhu wenji, He Yigang. A GA-BPNNs based approach for fault diagnosis
of analog circuits and its application (J). Journal of computer-aided design
& computer graphics, Vol. 21, No. 9, pp1283- 1289, 2009.9.
[4] Zhu wenji, He Yigang.Neural network based soft fault diagnosis of
analog circuits with tolerances (J). Transactions of China Electrotechnical
Society, Vol. 24, No. 11, pp184-191, 2009.11.
[5] Yanghong Tan, Yigang He, Chun Cui, and GuanyuanQiu, "A novel
method for analog fault diagnosis based on neural networks and genetic
algorithms", IEEE Transactions on Instrumentation and Measurement,
Vol.57, No.11, pp2631-2639, November 2008.
[6] F. Aminian, M. Aminian, and H.W.Collins, "Analog fault diagnosis of
actual circuits using neural networks", IEEE Trans. Instrum. Meas.,
Vol.51, No.3, pp.544-550, Jun. 2002.
[7] Liu Zhansheng, Liu Chengmin, Liu Shuchun, Fan Xianfeng, Tang
Bingzhao, "Wavelet analysis and fractal geometry application to fault
diagnosis of rotor friction between dynamic and static parts", Journal of
Harbin Institute of Technology, Vol.31, No.1, pp55-56, 92, Feb.1999.
[8] Feisi r &d technology centre. Wavelet analysis and application with
Matlab6.5. Beijing, China: Publishing House of Electronics Industry,
2003.1.
[9] Sha Zheng, Yuan Huojun. Fractal and Fitting Theories. ZheJiang
University Press, 2005.3.
[10] Kenneth Falconer,Fractal Geometry: Mathematical Foundations and
Applications, Published by Willey Publishing, Inc.,2003.
[11] Li Bicheng, Shao Meizhen, and Huang Jie, Pattern recognition theories
and applications. Xian, China: University of Xian electronic science and
technology, Press, 2008.