A review from physics based models to artificial intelligence aided models in fatigue prediction for industry applications
International Journal of Mechatronics and Manufacturing Systems, cilt.16, sa.2-3, ss.171-200, 2023 (Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 16 Sayı: 2-3
- Basım Tarihi: 2023
- Doi Numarası: 10.1504/ijmms.2023.133400
- Dergi Adı: International Journal of Mechatronics and Manufacturing Systems
- Derginin Tarandığı İndeksler: Scopus, PASCAL, Aerospace Database, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
- Sayfa Sayıları: ss.171-200
- Anahtar Kelimeler: aerospace alloys, artificial intelligence, fatigue prediction, machine learning, metal fatigue, reliability
- Ankara Yıldırım Beyazıt Üniversitesi Adresli: Evet
Özet
For a mechanical part to be certified, it should be assessed whether its mechanical, optical or thermal properties satisfy service requirements. Fatigue is one of the critical properties of functional materials, particularly in the aviation industry, where new materials, such as alloys, fibre-reinforced composites and additively manufactured alloys, dominate increasingly. This trend puts a heavy burden on fatigue characterisation, which is expensive and time-consuming. However, recent developments in artificial intelligence offer novel methods to decrease the test load cost-effectively. Hence, this literature survey first summarises predominant fatigue models both theoretical and numerical, and then covers and classifies recent studies (2000–2023) using recent machine learning techniques.