Application of IWO-SVM approach in fault diagnosis of analog circuits

Support vector machine (SVM) is a machine learning algorithm which has been applied to fault diagnosis of analog circuits. Invasive weed optimization (IWO) is a novel numerical optimization algorithm inspired from weed colonization. An approach that combines IWO and SVM (IWO-SVM) is proposed to fault diagnosis of analog circuits in this paper. The process of fault diagnosis of analog circuits using IWO-SVM approach is introduced in details. A biquadrate filter is used to test the performance of IWO-SVM approach for fault diagnosis. The simulation experiments show that the IWO-SVM approach proposed in this paper has a higher diagnosis accuracy rate than the conventional SVM in fault diagnosis of analog circuits.

[1]  Fang Chen,et al.  Methods of Handling the Tolerance and Test-Point Selection Problem for Analog-Circuit Fault Diagnosis , 2011, IEEE Transactions on Instrumentation and Measurement.

[2]  Michele Marchesi,et al.  Wavelet analysis for diagnostic problems , 1996, Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96).

[3]  Liang Huang,et al.  Fault diagnosis of analog circuit based on support vector machines , 2009, 2009 IEEE International Conference on Communications Technology and Applications.

[4]  Hui Li,et al.  Analog Circuits Fault Diagnosis Using Support Vector Machine , 2007, 2007 International Conference on Communications, Circuits and Systems.

[5]  Caro Lucas,et al.  A novel numerical optimization algorithm inspired from weed colonization , 2006, Ecol. Informatics.

[6]  Dong Liu,et al.  Entropy-based optimum test points selection for analog fault dictionary techniques , 2004, IEEE Transactions on Instrumentation and Measurement.

[7]  Sun Li.  Tuning of Auto-disturbance-rejection Controller for a Class of Nonlinear Plants , 2004 .

[8]  Hua Li,et al.  An algorithm of soft fault diagnosis for analog circuit based on the optimized SVM by GA , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.

[9]  F. Aminian,et al.  Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor , 2000 .

[10]  Yanfeng Wang,et al.  A modified invasive weed optimization with crossover operation , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[11]  Tao Lin,et al.  Analog circuit fault diagnosis based on fuzzy support vector machine and kernel density estimation , 2010, 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE).

[12]  Shuo Wang,et al.  Tuning of Auto-Disturbance Rejection Controller Based on the Invasive Weed Optimization , 2011, 2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications.