A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults
- Submitting institution
-
Sheffield Hallam University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3637
- Type
- D - Journal article
- DOI
-
10.3390/s20185112
- Title of journal
- Sensors
- Article number
- ARTN 5112
- First page
- e5112
- Volume
- 20
- Issue
- 18
- ISSN
- 1424-8220
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2020
- 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
-
1
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Originality: A novel approach for identification of faults in electro-mechanical drive systems is proposed for use in machinery monitoring for the Industrial Internet-of-Things.
Significance: A result of the £544,435 BBSRC-funded “Next generation rice milling” project (BB/S020993/1), a novel method was proposed for detecting maintenance issues using vibration data that significantly outperforms the current state-of-the-art, is exceptionally robust to noisy environments, and can be used in real-time. This is now being used for condition monitoring of rice mill grinding plates (Koolmill–A. Anderson).
Rigour: Extensive statistical analysis using a range of performance metrics performed and comparison made with several state-of-the-art methods.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -