Bearing defect classification based on individual trained wavelet kernel local fisher discriminant analysis with particle swarm optimization
- Submitting institution
-
Queen's University of Belfast
- Unit of assessment
- 12 - Engineering
- Output identifier
- 184816749
- Type
- D - Journal article
- DOI
-
10.1109/TII.2015.2500098
- Title of journal
- IEEE Transactions on Industrial Informatics
- Article number
- -
- First page
- 124
- Volume
- 12
- Issue
- 1
- ISSN
- 1551-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- 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)
-
C - Electrical and Electronic
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research is an output of a cooperative project with Hyundai Motor Industry-Ulsan Branch on ‘fault diagnosis and fault tolerant control for industrial robots’ aimed at upgrading the reliability and safety level of industrial robots. The paper challenges conventional thinking by demonstrating that: (a) bearing defect data is a type of multimodal data; (b) conventional frequency domain approaches fail to identify the bearing faults when the signals are immersed in heavy noise. The findings have been providing a significant impact on detecting and isolating multiple bearing faults and have been successfully employed into Hyundai robots.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -