Analog circuit diagnosis based on support vector machine with parameter optimization by improved NKCGWO

Support vector machine (SVM) is a widely used machine learning method in analog circuit fault diagnosis. However, SVM parameters such as kernel parameters and penalty parameters can seriously affect the classification accuracy. The current parameter optimization methods have defects such as slow convergence speed, easy falling into local optimal solutions, and premature convergence. Because of this, an improved grey wolf optimization algorithm (GWO) based on the nonlinear control parameter strategy, the first Kepler’s law strategy, and chaotic search strategy (NKCGWO) is proposed to overcome the shortcomings of the traditional optimization methods in this paper. In the NKCGWO method, three strategies are developed to improve the performance of GWO. Thereafter, the optimal parameters of SVM are obtained using NKCGWO-SVM. To evaluate the performance of NKCGWO-SVM for analog circuit diagnosis, two analog circuits are employed for fault diagnosis. The proposed method is compared with GA-SVM, PSO-SVM and GWO-SVM. The experimental results show that the proposed method has higher diagnosis accuracy than the other compared methods for analog circuit diagnosis.