PSI - Issue 57

Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2023) 000 – 000

www.elsevier.com/locate/procedia

ScienceDirect

Procedia Structural Integrity 57 (2024) 228–235

© 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0 ) Peer-review under responsibility of the scientific committee of the Fatigue Design 2023 organizers Abstract To foresee the life of fretting fatigue with variable shear amplitude loading, a hybrid model incorporating non-local multiaxial fatigue parameters and artificial neural networks (ANN) in conjunction with cumulative damage models has been proposed. The model has been developed based on equivalent stress parameters associated with crack nucleation and Miner's cumulative damage rule-inspired models, enabling the assessment of the impact of variable amplitude loading. To validate the models, fretting fatigue tests conducted under variable shear loading amplitude are employed to compare the predictions of four different models. The results demonstrate that while all models provide satisfactory estimates falling within the two-band limit, the hybrid model combining two ANN models outperforms the others and emerges as the most effective in predicting fretting fatigue life under these conditions. The proposed methodology effectively addresses the inherent complexities of fretting fatigue under variable amplitude stress, while also examining the influence of load block order on material behavior. Additionally, these types of fatigue ANN models have been demonstrating a strong capacity for generalization, making them highly promising for future industrial applications. © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2023 organizers Keywords: Fretting Fatigue, Artificial Neural Networks, Variable Amplitude Loading, Fatigue Design 2023 (FatDes 2023) A Hybrid ANN Multiaxial Fatigue Model for the Assessment of Fretting Fatigue under Variable Amplitude Shear Loading. Giorgio A. B. Oliveira a *, Raphael A. Cardoso b , Raimundo C. S. Freire Júnior b , José A. Araújo a a University of Brasilia, Department of Mechanical Engineering, CEP: 70.910-900. DF-Brasília, Brazil b Federal University of Rio Grande do Norte, Department of Mechanical Engineering, CEP: 59072-970. Natal-RN, Brazil.

* Corresponding author. Tel.: +0-000-000-0000 ; E-mail address: giorgio.oliveira@aluno.unb.br

2452-3216 © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2023 organizers

2452-3216 © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2023 organizers 10.1016/j.prostr.2024.03.025