Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine
The increasing household loads make series arc faults more complex, which are difficult to be detected by traditional circuit breakers and lead to the frequent occurrence of residential fire accidents. In this paper, a comprehensive approach of complex load recognition and series arc detection is pr...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8667831/ |
id |
doaj-6b706252bb574a75904cae8102fc5e4c |
---|---|
record_format |
Article |
spelling |
doaj-6b706252bb574a75904cae8102fc5e4c2021-03-29T22:28:54ZengIEEEIEEE Access2169-35362019-01-017472214722910.1109/ACCESS.2019.29053588667831Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector MachineJun Jiang0https://orcid.org/0000-0002-1349-3225Zhe Wen1Mingxin Zhao2Yifan Bie3Chen Li4Mingang Tan5Chaohai Zhang6Center for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCenter for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCenter for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCenter for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaState Grid Zhejiang Electric Power Co., Ltd., Research Institute, Hangzhou, ChinaCenter for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCenter for More-Electric-Aircraft Power System, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaThe increasing household loads make series arc faults more complex, which are difficult to be detected by traditional circuit breakers and lead to the frequent occurrence of residential fire accidents. In this paper, a comprehensive approach of complex load recognition and series arc detection is proposed on the basis of principal component analysis and support vector machine (PCA-SVM) combination model. Several typical loads were selected and analyzed, especially nonlinear and complex loads like power electronics load and multi-state load. Three time-domain parameters, maximum slip difference (MSD), zero current period (ZCP) and maximum Euclidean distance (MED), and nine frequency-domain harmonics information are collected to complex waveforms. To decrease the computation cost and further to enhance the response velocity, all the time-domain and frequency-domain information were blended and dimensionally reduced to three parameters by principal component analysis (PCA). Prior to the series arc detection, load recognition is trained and completed with the artificial intelligence (AI) algorithm. At last, the comprehensive model of load recognition and series arc detection is achieved based on a support vector machine (SVM). The accuracy of load recognition and series arc detection reaches 99.1% and 99.3%, respectively, demonstrating the excellent performances of the intelligent approach to diagnose the series arcing activities in modern household applications.https://ieeexplore.ieee.org/document/8667831/Series arc faultsdimensionality reductionsupport vector machineload recognitionarc detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jun Jiang Zhe Wen Mingxin Zhao Yifan Bie Chen Li Mingang Tan Chaohai Zhang |
spellingShingle |
Jun Jiang Zhe Wen Mingxin Zhao Yifan Bie Chen Li Mingang Tan Chaohai Zhang Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine IEEE Access Series arc faults dimensionality reduction support vector machine load recognition arc detection |
author_facet |
Jun Jiang Zhe Wen Mingxin Zhao Yifan Bie Chen Li Mingang Tan Chaohai Zhang |
author_sort |
Jun Jiang |
title |
Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine |
title_short |
Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine |
title_full |
Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine |
title_fullStr |
Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine |
title_full_unstemmed |
Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine |
title_sort |
series arc detection and complex load recognition based on principal component analysis and support vector machine |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The increasing household loads make series arc faults more complex, which are difficult to be detected by traditional circuit breakers and lead to the frequent occurrence of residential fire accidents. In this paper, a comprehensive approach of complex load recognition and series arc detection is proposed on the basis of principal component analysis and support vector machine (PCA-SVM) combination model. Several typical loads were selected and analyzed, especially nonlinear and complex loads like power electronics load and multi-state load. Three time-domain parameters, maximum slip difference (MSD), zero current period (ZCP) and maximum Euclidean distance (MED), and nine frequency-domain harmonics information are collected to complex waveforms. To decrease the computation cost and further to enhance the response velocity, all the time-domain and frequency-domain information were blended and dimensionally reduced to three parameters by principal component analysis (PCA). Prior to the series arc detection, load recognition is trained and completed with the artificial intelligence (AI) algorithm. At last, the comprehensive model of load recognition and series arc detection is achieved based on a support vector machine (SVM). The accuracy of load recognition and series arc detection reaches 99.1% and 99.3%, respectively, demonstrating the excellent performances of the intelligent approach to diagnose the series arcing activities in modern household applications. |
topic |
Series arc faults dimensionality reduction support vector machine load recognition arc detection |
url |
https://ieeexplore.ieee.org/document/8667831/ |
work_keys_str_mv |
AT junjiang seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT zhewen seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT mingxinzhao seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT yifanbie seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT chenli seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT mingangtan seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine AT chaohaizhang seriesarcdetectionandcomplexloadrecognitionbasedonprincipalcomponentanalysisandsupportvectormachine |
_version_ |
1724191512381620224 |