Deep learning aided power quality disturbance detection with improved time–frequency resolution employing adaptive superlet transform

Accurate identification of power quality disturbances is important for reliable operation of power system network as it may lead to unwanted and premature failure of power system components. Considering the above said fact, in this paper, a novel technique for detection and classification of power quality disturbance events (PQDE) is proposed employing adaptive superlet transform (ALST)-based time–frequency analysis and deep learning technique. ALST is a powerful signal processing tool for analysis of non-stationary signals in time–frequency frame. To this end, synthetic PQDEs were initially generated following IEEE std. 1159–2009. The generated 1D PQDEs were transformed to 2-D time–frequency RGB images using ASLT. The transformed time–frequency images of 1D PQDEs employing ALST showed enhanced resolution in time–frequency frame and showed distinct representations of different events even in the presence of very high noise level. The obtained PQDEs obtained using ASLT were finally fed as inputs to a designed lightweight customized convolutional neural network (CNN) architecture for automated feature extraction and classification. In addition, the performance of the proposed model was further evaluated using benchmark CNN models and also on real-life PQDE signals. It has been found that the proposed method returned 99.52% and 98.18% accuracies for classification of simulated PQDEs and real-life PQDEs, respectively. The performance of the proposed CNN aided ASLT is superior compared to other time–frequency representation methods and requires less computational time and memory compared to existing CNN models. Besides, the proposed framework is capable of diagnosis of power quality disturbance events in both noise-free and strong noisy environment.