Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A LSTM-based deep learning method with application to voltage dip classification
Department of Electrical Engineering, Chalmers University of Technology.
Department of Electrical Engineering, Chalmers University of Technology.
Luleå tekniska universitet, Institutionen för teknikvetenskap och matematik, Energivetenskap.ORCID-id: 0000-0003-4074-9529
Luleå tekniska universitet, Institutionen för teknikvetenskap och matematik, Energivetenskap.ORCID-id: 0000-0001-8504-494X
Visa övriga samt affilieringar
2018 (Engelska)Ingår i: Proceedings of International Conference on Harmonics and Quality of Power, ICHQP, Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In this paper, a deep learning (DL)-based method for automatic feature extraction and classification of voltage dips is proposed. The method consists of a dedicated architecture of Long Short-Term Memory (LSTM), which is a special type of Recurrent Neural Networks (RNNs). A total of 5982 three-phase one-cycle voltage dip RMS sequences, measured from several countries, has been used in our experiments. Our results have shown that the proposed method is able to classify the voltage dips from learned features in LSTM, with 93.40% classification accuracy on the test data set. The developed architecture is shown to be novel for feature learning and classification of voltage dips. Different from the conventional machine learning methods, the proposed method is able to learn dip features without requiring transition-event segmentation, selecting thresholds, and using expert rules or human expert knowledge, when a large amount of measurement data is available. This opens a new possibility of exploiting deep learning technology for power quality data analytics and classification.

Ort, förlag, år, upplaga, sidor
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018.
Serie
International Conference on Harmonics and Quality of Power, E-ISSN 1540-6008
Nationell ämneskategori
Annan elektroteknik och elektronik
Forskningsämne
Elkraftteknik
Identifikatorer
URN: urn:nbn:se:ltu:diva-69511DOI: 10.1109/ICHQP.2018.8378893ISI: 000444771900082Scopus ID: 2-s2.0-85049260061ISBN: 978-1-5386-0517-2 (digital)OAI: oai:DiVA.org:ltu-69511DiVA, id: diva2:1218275
Konferens
18th International Conference on Harmonics and Quality of Power (ICHQP), Ljubljana, Slovenia, 13-16 May 2018
Tillgänglig från: 2018-06-14 Skapad: 2018-06-14 Senast uppdaterad: 2018-10-10Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Personposter BETA

Bollen, MathBagheri, Azam

Sök vidare i DiVA

Av författaren/redaktören
Bollen, MathBagheri, Azam
Av organisationen
Energivetenskap
Annan elektroteknik och elektronik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 2249 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf