Developing Prognostic Models Using Duality Principles for DC-to-DC Converters
- Submitting institution
-
The University of Westminster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 98y68
- Type
- D - Journal article
- DOI
-
10.1109/TPEL.2014.2376413
- Title of journal
- IEEE Transactions on Power Electronics
- Article number
- -
- First page
- 2872
- Volume
- 30
- Issue
- 5
- ISSN
- 0885-8993
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2014
- 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
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In the era of increased automation fuelled by AI/ML and big data, developing trustworthy prognostic models for critical systems has been an elusive task. This is mainly due to the lack of high quality training data and the fact that collecting past failure data may come too late. The paper took a radical new approach to solving this problem in that the development of prognostic models becomes a matter of semantic similarity and the underpinning fundamental principle of duality in physics. This research impacted not only prognostic models for critical systems, but also how 'black-box' ML prediction models are interpreted.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
