Fault Detection and Isolation in Industrial Processes Using Deep Learning Approaches
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1344
- Type
- D - Journal article
- DOI
-
10.1109/tii.2019.2902274
- Title of journal
- IEEE Transactions on Industrial Informatics
- Article number
- -
- First page
- 3077
- Volume
- 15
- Issue
- 5
- ISSN
- 1551-3203
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2019
- 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
-
3
- Research group(s)
-
A - Artificial Intelligence (AI)
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research developed a highly-novel automated fault detection methodology for computer-based manufacturing assembly lines. The resulting hierarchical deep learning generative modelling technique is capable of processing heterogeneous input data to determine spatial /temporal relationships and is applied in automotive instrument cluster assembly and testing for detecting and isolating faults. The system was patented (GB2554038A) and is being applied in several automotive projects by Interactive Coventry Ltd (Dr.Rahat-Iqbal). Significance comes from the combination of techniques in addition to the spin-out company. The methodology also underpins subsequent development of an advanced urban flood forecasting platform as part of an InnovateUK project (101279-579246).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -