Analog Circuit Intelligent Fault Diagnosis Based on PCA and OAOSVM

Abstract:

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.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 802-806
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.802
• Online since: February 2012
• Authors: Ke Guo, Yi Zhu, Ye San
• Keywords: Analog Circuit, Fault Diagnosis, One-against-One Support Vector Machine, Principal Component Analysis (PCA)

References

[1] Aminian M, Aminian F: IEEE Transactions on Circuits and Systems—II: analog and digital signal processing Vol. 47 (2000), p.151

DOI: 10.1109/82.823545

[2] Jiang C, Wang Y R: Measurement Vol. 44 (2011), p.281

[3] Jolliffe I T: Principal Component Analysis (Springer, New York 2000)

[4] Chapelle O, Haffner P, Vapnik V N: IEEE Transactions on Neural Networks Vol. 10 (1999), p.1055

[5] Vapnik V N: IEEE Transactions on Neural Networks Vol. 10 (1999), p.988

[6] He X S, Wang Z, Cheng J: Pattern Recognition Letters Vol. 33 (2012), p.71

[7] Marcantonio C, Ada F: Measurement Vol. 28 (2000), p.147