Amirkabir Journal of Mechanical Engineering

Amirkabir Journal of Mechanical Engineering

Hybrid Deep Learning-Based Lifetime Prediction from Multiaxial Fatigue Mechanical Data

Document Type : Research Article

Authors
Behnam Anbarlooie 1
Seyed Mohammadmahdi Rouholamini 2
1 Department of New Technologies & Aerospace Engineering, Shahid Beheshti University
2 Faculty of Aerospace and Advanced Technologies, Shahid Beheshti University
10.22060/mej.2026.25206.7929
Abstract
Accurate prediction of fatigue life in materials is a fundamental challenge in mechanical design since it strongly affects the safety, reliability, and maintenance cost of engineering structures. Traditional empirical and analytical fatigue models, while widely applied, often fail to capture nonlinear and multiaxial effects arising under variable loading conditions. In this study, a hybrid deep learning architecture is developed that integrates three complementary components: a fully connected (FC) network for static material features, a bidirectional long short term memory (Bi LSTM) network for sequential loading path, and a transformer encoder for multi path feature fusion and high level relational learning. Experimental stress–strain data were normalized and divided into training and testing sets, and the model was optimized using the Adam algorithm with a learning rate of 5×10⁻⁴ for 2000 epochs. Quantitative evaluation demonstrates that the proposed FC–BiLSTM–Transformer model achieves superior accuracy compared with five baseline networks, with MSE = 0.335, MAE = 0.1385, and R² = 0.9470. Physically, the model captures complex fatigue responses without empirical hypotheses, enabling data driven representation of material behavior. The developed framework provides a reliable computational tool for fatigue life estimation and can be extended to complex materials and multiaxial loading conditions in aerospace and automotive applications.
Keywords
Fatigue Life Prediction
Deep Learning
Bidirectional LSTM
Transformer
Subjects
[1] J.A. Bannantine, J.J. Comer, J.L. Handrock, Fundamentals of Metal Fatigue Analysis, Prentice Hall, 1990.
[2] S. Suresh, Fatigue of materials, Cambridge university press, 1998.
[3] Luke Pollock, Ayah Khalid Abdelwahab, John Murray, and Graham Wild. “The Need for Aerospace Structural Health Monitoring: A Review of Aircraft Fatigue Accidents”. International Journal of Prognostics and Health Management, ISSN 2153-2648, 2021
[4] S. Tavares, P. De Castro, An overview of fatigue in aircraft structures, Fatigue & Fracture of Engineering Materials & Structures, 40(10) (2017) 1510–1529.
[5] S.R. Hursh, D.P. Redmond, M.L. Johnson, D.R. Thorne, G. Belenky, T.J. Balkin, W.F. Storm, J.C. Miller, D.R. Eddy, Fatigue models for applied research in warFig.hting, Aviation, space, and environmental medicine, 75(3) (2004) A44–A53.
[6] T. Harris, W.K. Yu, Lundberg-Palmgren fatigue theory: considerations of failure stress and stressed volume, Journal of Tribology, 121(1) (1999) 85–89.
[7] J. Yang, G. Kang, Y. Liu, Q. Kan, A novel method of multiaxial fatigue life prediction based on deep learning, International Journal of Fatigue, 151 (2021) 106356.
[8] Y. Mizuno, A. Hosoi, H. Koshita, D. Tsunoda, H. Kawada, Fatigue life prediction of composite materials using strain distribution images and a deep convolution neural network, Scientific reports, 14(1) (2024) 25418.
[9] C.M. Bishop, H. Bishop, Deep Learning: Foundations and Concepts, Springer International Publishing, 2023.
[10] A. Graves, Long short-term memory, Supervised sequence labelling with recurrent neural networks (2012). Springer, ISBN: 978-3-642-24796-5.
[11] F. Chollet, F. Chollet, Deep Learning with Python, Second Edition, Manning, 2021.
[12] S. Chen, Y. Bai, X. Zhou, A. Yang, A deep learning dataset for metal multiaxial fatigue life prediction, Scientific Data, 11(1) (2024) 1027.
[13] K.P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.
[14] Z. Huang, W. Xu, K. Yu, Bidirectional LSTM-CRF models for sequence tagging, arXiv preprint arXiv:1508.01991,  (2015).
[15] D. GODOY, DEEP LEARNING WITH PYTORCH STEP-BY-STEP: A Beginner's Guide, INDEPENDENTLY PUBLISHED, 2022.
[16] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, Ł. Kaiser, I. Polosukhin, Attention is all you need, Advances in neural information processing systems, 30 (2017).
[17] A. Kazemnejad, I. Padhi, K. Natesan Ramamurthy, P. Das, S. Reddy, The impact of positional encoding on length generalization in transformers, Advances in Neural Information Processing Systems, 36 (2023) 24892–24928.
[18] K.D.B.J. Adam, A method for stochastic optimization, arXiv preprint arXiv:1412.6980, 1412(6) (2014).
[19] G. James, D. Witten, T. Hastie, R. Tibshirani, An Introduction to Statistical Learning: with Applications in R, Springer New York, 2013.
Amirkabir Journal of Mechanical Engineering
Volume 57, Issue 11
February 2026
Pages 1455-1476