Entropy-based feature extraction for electromagnetic discharges classification in high-voltage power generation
- Submitting institution
-
Glasgow Caledonian University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 33608789
- Type
- D - Journal article
- DOI
-
10.3390/e20080549
- Title of journal
- Entropy
- Article number
- 549
- First page
- -
- Volume
- 20
- Issue
- 8
- ISSN
- 1099-4300
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work developed an analytic approach for EMI discharge signals measured from different sites, followed by EMI expert’s data analysis and labelling according to the discharge source type contained within the signal. This work demonstrates the ability to transform the EMI signals to low dimension feature space through four entropy features while requiring minimal computation. The features, along with expert labels, were used to train a classification algorithm to distinguish between various discharge sources and achieving high performance. The system can be exploited for a potential application to online condition monitoring based on EMI.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -