An Intelligent Approach for Power Quality Events Detection and Classification

This paper proposes an intelligent approach to detect and classify the power quality (PQ) events with the combination of machine learning and advanced signal processing techniques. It selects Stockwell transform, one of the efficient signal processing tools for feature extraction from the recorded signals. The extracted features are then fetched to one of the popular machine-learning tools, namely the artificial neural network (ANN), to develop the proposed intelligent PQ events detection and classification approach. This paper selects the hyper-parameters, e.g., number of hidden layer neurons, training algorithm, and activation functions through a systematic trial and error approach. To enhance the proposed approach performance, the weights and biases of the ANN are optimized using the grey wolf optimization (GWO) technique. Simulation results confirm the efficacy of the developed intelligent methodology in distinguishing PQ events from non-PQ events. Moreover, separates different PQ events, e.g., sag, swell, interruption, fluctuation, spike, notch, harmonics, from each other with reasonable accuracy. This research also investigates the efficacy of the proposed signal processing-based machine learning approach in the presence of measurement noises.