Ochella, Sunday, Shafiee, Mahmood, Sansom, C (2021) Requirements for Standards and Regulations in AI-Enabled Prognostics and Health Management. In: 2021 26th International Conference on Automation and Computing (ICAC). . IEEE, UK ISBN 978-1-66544-352-4. E-ISBN 978-1-86043-557-7. (doi:10.23919/ICAC50006.2021.9594069) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:92166)
PDF
Author's Accepted Manuscript
Language: English Restricted to Repository staff only |
|
Contact us about this Publication
|
![]() |
Official URL: https://doi.org/10.23919/ICAC50006.2021.9594069 |
Abstract
The fundamental understanding of the core aspects of prognostics and health management (PHM) as a field of practice is somewhat fully established. However, the various approaches used in the field have continuously evolved. With the recent surge in the adoption of artificial intelligence (AI) algorithms for predictive analytics, data-driven PHM is now more prominent. Notwithstanding the popularity of AI approaches, actual adoption and implementation in fielded systems has been minimal. One of the reasons for this is the lag in an ancillary area, which is the development of corresponding standards and regulations to guide the practice. This paper aims to synthesize various studies in the literature regarding standards and regulations in data-driven PHM and then sets out the necessary requirements for a standards and regulations regime to support the full adoption of AI-enabled PHM. An acceptability criterion is proposed, which incorporates the various factors that must be considered for verification, validation, and certification of AI-enabled PHM technologies. The use of the acceptability criterion is demonstrated, which will potentially be very useful to certification bodies and regulatory agencies in the process of approving AI-enabled PHM for use in safety-critical assets.
Item Type: | Conference or workshop item (Paper) |
---|---|
DOI/Identification number: | 10.23919/ICAC50006.2021.9594069 |
Uncontrolled keywords: | artificial intelligence (AI), prognostics and health management (PHM), standards and regulations, data-driven prognostics, remaining useful life (RUL) |
Subjects: |
Q Science > Q Science (General) > Q335 Artificial intelligence T Technology > TJ Mechanical engineering and machinery |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts |
Depositing User: | Mahmood Shafiee |
Date Deposited: | 06 Dec 2021 10:01 UTC |
Last Modified: | 06 Dec 2021 10:01 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/92166 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):