An optimal extreme learning-based classification method for power quality events using fractional Fourier transform
- PDF / 1,929,497 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 80 Downloads / 236 Views
(0123456789().,-volV) (0123456789().,-volV)
ORIGINAL ARTICLE
An optimal extreme learning-based classification method for power quality events using fractional Fourier transform Indu Sekhar Samanta1 • Pravat Kumar Rout2 • Satyasis Mishra1 Received: 5 December 2019 / Accepted: 5 August 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract 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 multidomain 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 processingbased 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. Keywords Time–frequency analysis Signal processing techniques PQ events Fractional Fourier transform (FRFT) Extreme learning machine (ELM) Teaching–learning-based optimization
1 Introduction The fast growth of industrialization, extensive utilization of sensitive electronic devices, nonlinear loads, power electronic converters, and automatic relaying/protecting devices are the major cause of power quality (PQ) degradation [1]. It is highly desirable to make a power system capable of delivering undistorted voltage, current, and frequency signals to supply quality power. Looking at the smart grid and micro-grid structure, recently the integration of various renewable energy resources (REEs), energy storage, and electric vehicle (EV) charging system associated & Pravat Kumar Rout [email protected] 1
Department of Electronics and Communication Engineering, Centurion University, Paralakhemundi, India
2
Department of Electrical and Electronics Engineering, Siksha ‘O’ Anusandhan University, Bhubaneswar, India
equipment with the conventional power grid is another source of generating power quality disturbances (PQDs) [2]. Under these conditions, it is indispensable to reduce and improve the PQ due to i
Data Loading...