Experimental validation of an ANN model for random loading fatigue analysis
- Submitting institution
-
Oxford Brookes University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 188062683
- Type
- D - Journal article
- DOI
-
10.1016/j.ijfatigue.2019.04.028
- Title of journal
- International Journal of Fatigue
- Article number
- -
- First page
- 112
- Volume
- 126
- Issue
- -
- ISSN
- 0142-1123
- Open access status
- Compliant
- Month of publication
- May
- 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
-
4
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper uniquely demonstrated that the artificial neural network approach developed by the authors and the large synthetic data sets generated in the work can be used with actual experimental input data to predict fatigue life under generalized loading, alloy and different component conditions. The paper tested spectral experimental random fatigue data from a Society of Automotive Engineers study, which is one of such few available in the open literature for the demonstration. Two materials, three load levels and three different component types were analysed with the predictions made being better than those from existing frequency and time domain methods.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -