An optimal extreme learning-based classification method for power quality events using fractional Fourier transform

Mitigation of power quality events (PQEs) needs an accurate, faster, and efficient detection and classification technique for designing the compensating devices as a remedial measure to the problem. This study motivates on this issue to formulate a better technique based on fractional Fourier transform (FRFT) and extreme learning machine (ELM). FRFT is considered for relevant feature extraction due to its characteristics like enhanced order control and capability to provide time, frequency, and intermediate time-frequency depictions for any non-stationary power signals. The possibility of multi-domain feature extraction capability due to its easy order control arrives at a robust feature matrix, which makes the classification more accurate. An optimal ELM-based classifier is designed by tuning its system parameters applying modified teaching-learning-based optimization (MTLBO). This optimal ELM is implemented in this study along with FRFT to formulate the proposed approach denoted as FRFT-MTLBO-ELM. To give a good reason for the enhanced performance of the proposed technique, noisy and hybrid synthetic signals of ten PQEs are generated and tested considering fully all real-time condition cases. At last, a comparative result is presented with other applied signal processing-based approaches and it is found that the proposed FRFT-MTLBO-ELM approach is very effective and comparatively better justifying its real-time implementation in the monitoring systems.