Power quality disturbances classification using support vector machines with optimised time-frequency kernels

Detection and classification of power system disturbances is necessary to ensure good power supply. The paper presents a method for accurate classification of power quality signals using support vector machines (SVM) with optimised time-frequency kernels. The Cohen’s class of time-frequency-transformation has been chosen as the kernel for the SVM. A stochastic genetic algorithm (StGA) has been used to optimise the parameters of the kernels. Comparative simulation results demonstrate a significant improvement in the classification accuracy with such optimised kernels.