Reduced KPCA based Ensemble Learning Approach for Fault Diagnosis of Grid-Connected PV Systems

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

The main objective of this work is to develop novel fault diagnosis techniques using ensemble learning and multivariate statistical techniques. The proposed methods are capable of identifying and classifying PV faults. First, an ensemble learning (EL) method that combines several base models is proposed. Next, kernel principal components analysis (KPCA) and reduced KPCA are proposed to extract and select the pertinent characteristics from raw data. Then, the extracted significant characteristics are transmitted to the EL model for classification purposes. The main idea behind these proposals is to provide the best accuracy and also improve the results in terms of computation time. The diagno-sis results demonstrated the efficiency of the proposed frameworks.

Original languageEnglish
Title of host publication2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages841-845
Number of pages5
ISBN (Electronic)9781665471084
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022 - Setif, Algeria
Duration: 6 May 202210 May 2022

Publication series

Name2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

Conference

Conference19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022
Country/TerritoryAlgeria
CitySetif
Period6/05/2210/05/22

Keywords

  • Ensemble Learning
  • Fault Classification
  • Fault Diag-nosis
  • Grid-Connected PV (GCPV)
  • Machine Learning

Fingerprint

Dive into the research topics of 'Reduced KPCA based Ensemble Learning Approach for Fault Diagnosis of Grid-Connected PV Systems'. Together they form a unique fingerprint.

Cite this