Title: A review from physics based models to artificial intelligence aided models in fatigue prediction for industry applications

Authors: Müge Gürgen; Mete Bakır; Ersin Bahceci; Hakkı Özgür Ünver

Addresses: Department of Mechanical Engineering, TOBB University of Economics and Technology, Ankara, 06560, Turkey; Turkish Aerospace, Ankara, 06980, Turkey ' Turkish Aerospace, Ankara, 06980, Turkey; Ankara Yildirim Beyazit University, Ankara, 06220, Turkey ' Iskenderun Technical University, Hatay, 31200, Turkey ' Department of Mechanical Engineering, TOBB University of Economics and Technology, Ankara, 06560, Turkey

Abstract: 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.

Keywords: metal fatigue; aerospace alloys; machine learning; artificial intelligence; fatigue prediction; reliability.

DOI: 10.1504/IJMMS.2023.133400

International Journal of Mechatronics and Manufacturing Systems, 2023 Vol.16 No.2/3, pp.171 - 200

Received: 30 Dec 2022
Accepted: 24 Apr 2023
Published online: 14 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article