Feature extraction and power quality event classification using Curvelet transform and optimized extreme learning machine

This article presents an efficient method for power quality events (PQEs) detection and classification based on Curvelet transform (CT) and optimized extreme learning machine (OELM). Initially, various PQEs signal data are extracted even under noisy and simultaneously occurred multi-event conditions...

Full description

Saved in:
Bibliographic Details
Published in:Electrical engineering 2021-10, Vol.103 (5), p.2431-2446
Main Authors: Samanta, Indu Sekhar, Rout, Pravat Kumar, Mishra, Satyasis
Format: Article
Language:English
Subjects:
Artificial neural networks
Classification
Economics and Management
Electrical Engineering
Electrical Machines and Networks
Energy Policy
Engineering
Evolutionary computation
Feature extraction
Machine learning
Original Paper
Power Electronics
Real time
Transformations (mathematics)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article presents an efficient method for power quality events (PQEs) detection and classification based on Curvelet transform (CT) and optimized extreme learning machine (OELM). Initially, various PQEs signal data are extracted even under noisy and simultaneously occurred multi-event conditions to reflect the real-time conditions. Relevant features of all these extracted signals are computed by using a multi-resolution and multidirectional fast discrete CT (FDCT) approach. These features are used to classify the events accurately by the proposed OELM. In this classification strategy, a modified differential evolution (MDE) is introduced to optimize the conventional ELM to enhance its precision rate. The proposed novel approach is tested and analyzed under various noisy conditions with 20 dB, 30 dB, and 50 dB with single and multi PQEs conditions. Comparative results with other recently proposed approaches by various authors reveal that the proposed CT- and OELM-based classifier titled CT-OELM can be considered as a competitive choice for implementing in the real-time monitoring system.
ISSN:0948-7921
1432-0487
DOI:10.1007/s00202-021-01243-3