Brute-force analysis of insight of phase-resolved partial discharge using a CNN
Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems...
Ausführliche Beschreibung
Autor*in: |
Kitani, Ryota [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2023 |
---|
Schlagwörter: |
---|
Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
---|
Übergeordnetes Werk: |
Enthalten in: Electrical engineering - Springer Berlin Heidelberg, 1994, 105(2023), 4 vom: 07. Apr., Seite 2373-2382 |
---|---|
Übergeordnetes Werk: |
volume:105 ; year:2023 ; number:4 ; day:07 ; month:04 ; pages:2373-2382 |
Links: |
---|
DOI / URN: |
10.1007/s00202-023-01808-4 |
---|
Katalog-ID: |
OLC2144463433 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | OLC2144463433 | ||
003 | DE-627 | ||
005 | 20240118095152.0 | ||
007 | tu | ||
008 | 240118s2023 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s00202-023-01808-4 |2 doi | |
035 | |a (DE-627)OLC2144463433 | ||
035 | |a (DE-He213)s00202-023-01808-4-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 621.3 |q VZ |
082 | 0 | 4 | |a 620 |q VZ |
100 | 1 | |a Kitani, Ryota |e verfasserin |0 (orcid)0000-0001-7151-2933 |4 aut | |
245 | 1 | 0 | |a Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
520 | |a Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. | ||
650 | 4 | |a Partial discharge | |
650 | 4 | |a Phase-resolved partial discharge | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Convolutional neural network | |
700 | 1 | |a Iwata, Shinya |0 (orcid)0000-0002-5431-457X |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Electrical engineering |d Springer Berlin Heidelberg, 1994 |g 105(2023), 4 vom: 07. Apr., Seite 2373-2382 |w (DE-627)182588734 |w (DE-600)1219035-4 |w (DE-576)045292310 |x 0948-7921 |7 nnns |
773 | 1 | 8 | |g volume:105 |g year:2023 |g number:4 |g day:07 |g month:04 |g pages:2373-2382 |
856 | 4 | 1 | |u https://doi.org/10.1007/s00202-023-01808-4 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-TEC | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_207 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_2018 | ||
912 | |a GBV_ILN_2020 | ||
912 | |a GBV_ILN_2048 | ||
912 | |a GBV_ILN_4277 | ||
951 | |a AR | ||
952 | |d 105 |j 2023 |e 4 |b 07 |c 04 |h 2373-2382 |
author_variant |
r k rk s i si |
---|---|
matchkey_str |
article:09487921:2023----::rtfrenlssfnihopaeeovdata |
hierarchy_sort_str |
2023 |
publishDate |
2023 |
allfields |
10.1007/s00202-023-01808-4 doi (DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p DE-627 ger DE-627 rakwb eng 621.3 VZ 620 VZ Kitani, Ryota verfasserin (orcid)0000-0001-7151-2933 aut Brute-force analysis of insight of phase-resolved partial discharge using a CNN 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network Iwata, Shinya (orcid)0000-0002-5431-457X aut Enthalten in Electrical engineering Springer Berlin Heidelberg, 1994 105(2023), 4 vom: 07. Apr., Seite 2373-2382 (DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 0948-7921 nnns volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 https://doi.org/10.1007/s00202-023-01808-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 AR 105 2023 4 07 04 2373-2382 |
spelling |
10.1007/s00202-023-01808-4 doi (DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p DE-627 ger DE-627 rakwb eng 621.3 VZ 620 VZ Kitani, Ryota verfasserin (orcid)0000-0001-7151-2933 aut Brute-force analysis of insight of phase-resolved partial discharge using a CNN 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network Iwata, Shinya (orcid)0000-0002-5431-457X aut Enthalten in Electrical engineering Springer Berlin Heidelberg, 1994 105(2023), 4 vom: 07. Apr., Seite 2373-2382 (DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 0948-7921 nnns volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 https://doi.org/10.1007/s00202-023-01808-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 AR 105 2023 4 07 04 2373-2382 |
allfields_unstemmed |
10.1007/s00202-023-01808-4 doi (DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p DE-627 ger DE-627 rakwb eng 621.3 VZ 620 VZ Kitani, Ryota verfasserin (orcid)0000-0001-7151-2933 aut Brute-force analysis of insight of phase-resolved partial discharge using a CNN 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network Iwata, Shinya (orcid)0000-0002-5431-457X aut Enthalten in Electrical engineering Springer Berlin Heidelberg, 1994 105(2023), 4 vom: 07. Apr., Seite 2373-2382 (DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 0948-7921 nnns volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 https://doi.org/10.1007/s00202-023-01808-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 AR 105 2023 4 07 04 2373-2382 |
allfieldsGer |
10.1007/s00202-023-01808-4 doi (DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p DE-627 ger DE-627 rakwb eng 621.3 VZ 620 VZ Kitani, Ryota verfasserin (orcid)0000-0001-7151-2933 aut Brute-force analysis of insight of phase-resolved partial discharge using a CNN 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network Iwata, Shinya (orcid)0000-0002-5431-457X aut Enthalten in Electrical engineering Springer Berlin Heidelberg, 1994 105(2023), 4 vom: 07. Apr., Seite 2373-2382 (DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 0948-7921 nnns volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 https://doi.org/10.1007/s00202-023-01808-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 AR 105 2023 4 07 04 2373-2382 |
allfieldsSound |
10.1007/s00202-023-01808-4 doi (DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p DE-627 ger DE-627 rakwb eng 621.3 VZ 620 VZ Kitani, Ryota verfasserin (orcid)0000-0001-7151-2933 aut Brute-force analysis of insight of phase-resolved partial discharge using a CNN 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network Iwata, Shinya (orcid)0000-0002-5431-457X aut Enthalten in Electrical engineering Springer Berlin Heidelberg, 1994 105(2023), 4 vom: 07. Apr., Seite 2373-2382 (DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 0948-7921 nnns volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 https://doi.org/10.1007/s00202-023-01808-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 AR 105 2023 4 07 04 2373-2382 |
language |
English |
source |
Enthalten in Electrical engineering 105(2023), 4 vom: 07. Apr., Seite 2373-2382 volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 |
sourceStr |
Enthalten in Electrical engineering 105(2023), 4 vom: 07. Apr., Seite 2373-2382 volume:105 year:2023 number:4 day:07 month:04 pages:2373-2382 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network |
dewey-raw |
621.3 |
isfreeaccess_bool |
false |
container_title |
Electrical engineering |
authorswithroles_txt_mv |
Kitani, Ryota @@aut@@ Iwata, Shinya @@aut@@ |
publishDateDaySort_date |
2023-04-07T00:00:00Z |
hierarchy_top_id |
182588734 |
dewey-sort |
3621.3 |
id |
OLC2144463433 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2144463433</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118095152.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00202-023-01808-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2144463433</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00202-023-01808-4-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">621.3</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kitani, Ryota</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-7151-2933</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Brute-force analysis of insight of phase-resolved partial discharge using a CNN</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Partial discharge</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Phase-resolved partial discharge</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Iwata, Shinya</subfield><subfield code="0">(orcid)0000-0002-5431-457X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Electrical engineering</subfield><subfield code="d">Springer Berlin Heidelberg, 1994</subfield><subfield code="g">105(2023), 4 vom: 07. Apr., Seite 2373-2382</subfield><subfield code="w">(DE-627)182588734</subfield><subfield code="w">(DE-600)1219035-4</subfield><subfield code="w">(DE-576)045292310</subfield><subfield code="x">0948-7921</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:105</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:4</subfield><subfield code="g">day:07</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:2373-2382</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00202-023-01808-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_207</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">105</subfield><subfield code="j">2023</subfield><subfield code="e">4</subfield><subfield code="b">07</subfield><subfield code="c">04</subfield><subfield code="h">2373-2382</subfield></datafield></record></collection>
|
author |
Kitani, Ryota |
spellingShingle |
Kitani, Ryota ddc 621.3 ddc 620 misc Partial discharge misc Phase-resolved partial discharge misc Machine learning misc Convolutional neural network Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
authorStr |
Kitani, Ryota |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)182588734 |
format |
Article |
dewey-ones |
621 - Applied physics 620 - Engineering & allied operations |
delete_txt_mv |
keep |
author_role |
aut aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
0948-7921 |
topic_title |
621.3 VZ 620 VZ Brute-force analysis of insight of phase-resolved partial discharge using a CNN Partial discharge Phase-resolved partial discharge Machine learning Convolutional neural network |
topic |
ddc 621.3 ddc 620 misc Partial discharge misc Phase-resolved partial discharge misc Machine learning misc Convolutional neural network |
topic_unstemmed |
ddc 621.3 ddc 620 misc Partial discharge misc Phase-resolved partial discharge misc Machine learning misc Convolutional neural network |
topic_browse |
ddc 621.3 ddc 620 misc Partial discharge misc Phase-resolved partial discharge misc Machine learning misc Convolutional neural network |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
hierarchy_parent_title |
Electrical engineering |
hierarchy_parent_id |
182588734 |
dewey-tens |
620 - Engineering |
hierarchy_top_title |
Electrical engineering |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)182588734 (DE-600)1219035-4 (DE-576)045292310 |
title |
Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
ctrlnum |
(DE-627)OLC2144463433 (DE-He213)s00202-023-01808-4-p |
title_full |
Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
author_sort |
Kitani, Ryota |
journal |
Electrical engineering |
journalStr |
Electrical engineering |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
600 - Technology |
recordtype |
marc |
publishDateSort |
2023 |
contenttype_str_mv |
txt |
container_start_page |
2373 |
author_browse |
Kitani, Ryota Iwata, Shinya |
container_volume |
105 |
class |
621.3 VZ 620 VZ |
format_se |
Aufsätze |
author-letter |
Kitani, Ryota |
doi_str_mv |
10.1007/s00202-023-01808-4 |
normlink |
(ORCID)0000-0001-7151-2933 (ORCID)0000-0002-5431-457X |
normlink_prefix_str_mv |
(orcid)0000-0001-7151-2933 (orcid)0000-0002-5431-457X |
dewey-full |
621.3 620 |
title_sort |
brute-force analysis of insight of phase-resolved partial discharge using a cnn |
title_auth |
Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
abstract |
Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
abstractGer |
Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
abstract_unstemmed |
Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_24 GBV_ILN_207 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2020 GBV_ILN_2048 GBV_ILN_4277 |
container_issue |
4 |
title_short |
Brute-force analysis of insight of phase-resolved partial discharge using a CNN |
url |
https://doi.org/10.1007/s00202-023-01808-4 |
remote_bool |
false |
author2 |
Iwata, Shinya |
author2Str |
Iwata, Shinya |
ppnlink |
182588734 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/s00202-023-01808-4 |
up_date |
2024-07-03T22:24:59.027Z |
_version_ |
1803598429197172736 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2144463433</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118095152.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00202-023-01808-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2144463433</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00202-023-01808-4-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">621.3</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kitani, Ryota</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-7151-2933</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Brute-force analysis of insight of phase-resolved partial discharge using a CNN</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract This study analyzes phase-resolved partial discharge (PD) signals using a convolutional neural network (CNN) for different electrode systems and attempts to reveal their relationship with the brute-force method. PD measurement is a diagnostic technique used for electrical insulating systems, and machine learning is needed to improve processing efficiency. However, the relationship between human insight and the learning model is unclear. The generated PD signals are first accumulated by each phase angle through applying a high AC voltage to four types of electrodes with a polyethylene sheet. Data are then converted to scatter images and classified using a CNN, with an accuracy rate of 98%. After cutting the data, including PD typical distribution, the classification demonstrates a slightly lower score of 95%. Finally, we divide the cut data into nine parts and choose whether to mask each part, then observe how the accuracy is affected. Results demonstrate that the CNN algorithm emphasizes specific parts of images. For example, when significant parts are contained, accuracy increases, and vice versa. In addition, the effect of noise on the insight and accuracy is partially revealed. It is clear from the results that appropriate parts need to be selected from big data.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Partial discharge</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Phase-resolved partial discharge</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Iwata, Shinya</subfield><subfield code="0">(orcid)0000-0002-5431-457X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Electrical engineering</subfield><subfield code="d">Springer Berlin Heidelberg, 1994</subfield><subfield code="g">105(2023), 4 vom: 07. Apr., Seite 2373-2382</subfield><subfield code="w">(DE-627)182588734</subfield><subfield code="w">(DE-600)1219035-4</subfield><subfield code="w">(DE-576)045292310</subfield><subfield code="x">0948-7921</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:105</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:4</subfield><subfield code="g">day:07</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:2373-2382</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00202-023-01808-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_207</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">105</subfield><subfield code="j">2023</subfield><subfield code="e">4</subfield><subfield code="b">07</subfield><subfield code="c">04</subfield><subfield code="h">2373-2382</subfield></datafield></record></collection>
|
score |
7.398756 |