Non-intrusive load identification based on CF-MF-SE joint feature

Aiming at the problems of the current non-intrusive load identification,such as too long model training time and low identification accuracy of electrical appliances with similar load characteristics,a non-intrusive load identification method based on CF-MF-SE joint feature was proposed.Based on the...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Guoqing AN, Yufei LIANG, Ziyao JIANG, Zheng LI, Qi AN, He CHEN, Qiang WANG, Jiacheng BAI
Formato: article
Lenguaje:ZH
Publicado: Hebei University of Science and Technology 2021
Materias:
T
Acceso en línea:https://doaj.org/article/1242fae63b104b89b618c424c6e7f7fd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:1242fae63b104b89b618c424c6e7f7fd
record_format dspace
spelling oai:doaj.org-article:1242fae63b104b89b618c424c6e7f7fd2021-11-23T07:09:07ZNon-intrusive load identification based on CF-MF-SE joint feature1008-154210.7535/hbkd.2021yx05004https://doaj.org/article/1242fae63b104b89b618c424c6e7f7fd2021-10-01T00:00:00Zhttp://xuebao.hebust.edu.cn/hbkjdx/ch/reader/create_pdf.aspx?file_no=b202105004&flag=1&journal_https://doaj.org/toc/1008-1542Aiming at the problems of the current non-intrusive load identification,such as too long model training time and low identification accuracy of electrical appliances with similar load characteristics,a non-intrusive load identification method based on CF-MF-SE joint feature was proposed.Based on the steady-state current signal,the peak factor was extracted to represent the distortion degree of the waveform,the margin factor was extracted to represent the stability degree of the signal,the spectral entropy was extracted to represent the complexity degree of the spectrum structure,and PSO-SVM was combined to realize load identification.Experimental results show that this method can solve the problem that the electrical current waveform is too similar to identify successfully,reduce the training time,and improve the recognition accuracy and efficiency.This method introduces the vibration signal characteristics as load characteristics into the field of load identification,which provides a new idea for feature selection of non-invasive load identification technology.As a key feature sensitive to load,spectral entropy can significantly improve the identification rate when combined with other features,which provides reference for the flexible selection of load characteristics in practical application.[HQ]Guoqing ANYufei LIANGZiyao JIANGZheng LIQi ANHe CHENZheng LIQiang WANGJiacheng BAIHebei University of Science and Technologyarticleelectrical measuring technology and its instrumentation; non-intrusive load identification; spectral entropy; support vector machine; particle swarm optimizationTechnologyTZHJournal of Hebei University of Science and Technology, Vol 42, Iss 5, Pp 462-469 (2021)
institution DOAJ
collection DOAJ
language ZH
topic electrical measuring technology and its instrumentation; non-intrusive load identification; spectral entropy; support vector machine; particle swarm optimization
Technology
T
spellingShingle electrical measuring technology and its instrumentation; non-intrusive load identification; spectral entropy; support vector machine; particle swarm optimization
Technology
T
Guoqing AN
Yufei LIANG
Ziyao JIANG
Zheng LI
Qi AN
He CHEN
Zheng LI
Qiang WANG
Jiacheng BAI
Non-intrusive load identification based on CF-MF-SE joint feature
description Aiming at the problems of the current non-intrusive load identification,such as too long model training time and low identification accuracy of electrical appliances with similar load characteristics,a non-intrusive load identification method based on CF-MF-SE joint feature was proposed.Based on the steady-state current signal,the peak factor was extracted to represent the distortion degree of the waveform,the margin factor was extracted to represent the stability degree of the signal,the spectral entropy was extracted to represent the complexity degree of the spectrum structure,and PSO-SVM was combined to realize load identification.Experimental results show that this method can solve the problem that the electrical current waveform is too similar to identify successfully,reduce the training time,and improve the recognition accuracy and efficiency.This method introduces the vibration signal characteristics as load characteristics into the field of load identification,which provides a new idea for feature selection of non-invasive load identification technology.As a key feature sensitive to load,spectral entropy can significantly improve the identification rate when combined with other features,which provides reference for the flexible selection of load characteristics in practical application.[HQ]
format article
author Guoqing AN
Yufei LIANG
Ziyao JIANG
Zheng LI
Qi AN
He CHEN
Zheng LI
Qiang WANG
Jiacheng BAI
author_facet Guoqing AN
Yufei LIANG
Ziyao JIANG
Zheng LI
Qi AN
He CHEN
Zheng LI
Qiang WANG
Jiacheng BAI
author_sort Guoqing AN
title Non-intrusive load identification based on CF-MF-SE joint feature
title_short Non-intrusive load identification based on CF-MF-SE joint feature
title_full Non-intrusive load identification based on CF-MF-SE joint feature
title_fullStr Non-intrusive load identification based on CF-MF-SE joint feature
title_full_unstemmed Non-intrusive load identification based on CF-MF-SE joint feature
title_sort non-intrusive load identification based on cf-mf-se joint feature
publisher Hebei University of Science and Technology
publishDate 2021
url https://doaj.org/article/1242fae63b104b89b618c424c6e7f7fd
work_keys_str_mv AT guoqingan nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT yufeiliang nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT ziyaojiang nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT zhengli nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT qian nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT hechen nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT zhengli nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT qiangwang nonintrusiveloadidentificationbasedoncfmfsejointfeature
AT jiachengbai nonintrusiveloadidentificationbasedoncfmfsejointfeature
_version_ 1718416808550072320