Deep neural networks for understanding and diagnosing partial discharge data

V. M. Catterson, B. Sheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

11 Citations (Scopus)
365 Downloads (Pure)

Abstract

Artificial neural networks have been investigated for many years as a technique for automated diagnosis of defects causing partial discharge (PD). While good levels of accuracy have been reported, disadvantages include the difficulty of explaining results, and the need to hand-craft appropriate features for standard two-layer networks. Recent advances in the design and training of deep neural networks, which contain more than two layers of hidden neurons, have resulted in improved results in speech and image recognition tasks. This paper investigates the use of deep neural networks for PD diagnosis. Defect samples constructed in mineral oil were used to generate data for training and testing. The paper demonstrates the improvements in accuracy and visualization of learning which can be gained from deep learning.
Original languageEnglish
Title of host publication2015 IEEE Electrical Insulation Conference (EIC)
Place of PublicationPiscataway, NJ, USA
PublisherIEEE
Pages218-221
Number of pages4
ISBN (Print)9781479973521
DOIs
Publication statusPublished - 7 Jun 2015
EventIEEE Electrical Insulation Conference 2015 - Seattle, United States
Duration: 7 Jun 201510 Jun 2015

Conference

ConferenceIEEE Electrical Insulation Conference 2015
CountryUnited States
CitySeattle
Period7/06/1510/06/15

Keywords

  • artificial neural networks
  • deep neural networks
  • partial discharge
  • diagnostics
  • UHF monitoring
  • defects in oil

Fingerprint Dive into the research topics of 'Deep neural networks for understanding and diagnosing partial discharge data'. Together they form a unique fingerprint.

  • Cite this

    Catterson, V. M., & Sheng, B. (2015). Deep neural networks for understanding and diagnosing partial discharge data. In 2015 IEEE Electrical Insulation Conference (EIC) (pp. 218-221). Piscataway, NJ, USA: IEEE. https://doi.org/10.1109/ICACACT.2014.7223616