A Review of Input Strategies and Model Architectures in Machine Learning Approaches for Multiaxial Fatigue Life Prediction

Authors

DOI:

https://doi.org/10.20535/2521-1943.2026.10.2(109).356925

Keywords:

multiaxial fatigue, machine learning methods, fatigue life prediction, neural networks, data-driven analysis, modeling, review

Abstract

This paper presents a review of machine learning methods for predicting fatigue life under multiaxial loading. The problem addressed in this work is the lack of a unified approach for accurate fatigue life prediction under complex proportional and non-proportional loading paths.
The results of the study consist in a systematic review and classification of modern machine learning approaches based on model architectures and input data representation strategies. In the latter, the analyzed methods are grouped into approaches based on engineered features, time-series data and image-based representations. The literature review covers publications from 2015 to 2025 retrieved from Scopus, Web of Science, and Google Scholar.
It is shown that prediction accuracy depends not only on the choice of machine learning algorithm, but primarily on the way the loading history is represented and integrated into the model. Physically based parameters remain effective in the case of limited experimental data, whereas deep learning methods are more suitable for large datasets and complex loading histories.

The results can be applied in engineering practice for the selection of appropriate machine learning methods for fatigue life prediction, particularly in cases involving complex loading histories, limited experimental data, or the need for interpretable and physically consistent models.

Author Biographies

Pavlo Yakovchuk, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

Аспірант кафедри динаміки і міцності машин та опору матеріалів

Sergiy Shukayev, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

Доктор технічних наук, професор кафедри динаміки і міцності машин та опору матеріалів

References

  1. S. Salifu and P. A. Olubambi, “A Review of Fatigue Failure and Life Estimation Models: From Classical Methods to Innovative Approaches,” Science, Engineering and Technology, vol. 4, no. 2, pp. 123–151, Nov. 2024, doi: 10.54327/set2024/v4.i2.140.
  2. X. Ding, G. He, and C. Chen, “Study on the dislocation sub-structures of Al–Mg–Si alloys fatigued under non-proportional loadings,” Journal of Materials Science, vol. 45, no. 15, pp. 4046–4053, Aug. 2010, doi: 10.1007/s10853-010-4487-3.
  3. S.-H. Doong, D. F. Socie, and I. M. Robertson, “Dislocation Substructures and Nonproportional Harden-ing,” Journal of Engineering Materials and Technology, vol. 112, no. 4, pp. 456–464, Oct. 1990, doi: 10.1115/1.2903357.
  4. M. Sakane and T. Itoh, “Microstructural study of multiaxial low cycle fatigue,” Frattura ed Integrità Strut-turale, vol. 9, no. 33, pp. 319–334, Jun. 2015, doi: 10.3221/IGF-ESIS.33.36.
  5. A. Fatemi and N. Shamsaei, “Multiaxial fatigue: An overview and some approximation models for life es-timation,” International Journal of Fatigue, vol. 33, no. 8, pp. 948–958, Aug. 2011, doi: 10.1016/j.ijfatigue.2011.01.003.
  6. Z.-Y. Yu, S.-P. Zhu, Q. Liu, and Y. Liu, “Multiaxial Fatigue Damage Parameter and Life Prediction without Any Additional Material Constants,” Materials, vol. 10, no. 8, p. 923, Aug. 2017, doi: 10.3390/ma10080923.
  7. P. V. Yakovchuk, E. V. Savchuk, and S. M. Shukayev, “Critical Plane Approach-Based Fatigue Life Predic-tion for Multiaxial Loading: A New Model and its Verification,” Strength of Materials, vol. 56, no. 2, pp. 281–291, Mar. 2024, doi: 10.1007/s11223-024-00647-3.
  8. P. M. Khanolkar, A. Vrolijk, and A. Olechowski, “Mapping artificial intelligence-based methods to engi-neering design stages: a focused literature review,” AIEDAM, vol. 37, p. e25, 2023, doi: 10.1017/S0890060423000203.
  9. M. P. Holubovskyi and V. P. Yasnii, “Ohliad zastosuvannia shtuchnoho intelektu ta mashynnoho navchannia u prykladnii mehanitsi,” SBIFNTUOG, no. 1(56), pp. 79–91, Jun. 2024, doi: 10.31471/1993-9965-2024-1(56)-79-91.
  10. D. P. Solomatine and A. Ostfeld, “Data-driven modelling: some past experiences and new approaches,” Journal of Hydroinformatics, vol. 10, no. 1, pp. 3–22, Jan. 2008, doi: 10.2166/hydro.2008.015.
  11. P. Liu, L. Wang, R. Ranjan, G. He, and L. Zhao, “A Survey on Active Deep Learning: From Model Driven to Data Driven,” ACM Comput. Surv., vol. 54, no. 10s, pp. 1–34, Jan. 2022, doi: 10.1145/3510414.
  12. B. M. De Silva, D. M. Higdon, S. L. Brunton, and J. N. Kutz, “Discovery of Physics From Data: Universal Laws and Discrepancies,” Front. Artif. Intell., vol. 3, p. 25, Apr. 2020, doi: 10.3389/frai.2020.00025.
  13. C. Zhou, H. Wang, S. Hou, and G. Jin, “A deep learning and physics-based method for multiaxial fatigue life prediction,” Aug. 29, 2023. doi: 10.22541/au.169328886.64998430/v1.
  14. Y. Wang, Y. Qiu, J. Li, and J. Bai, “Two Fatigue Life Prediction Models Based on the Critical Plane Theory and Artificial Neural Networks,” Metals, vol. 14, no. 8, p. 938, Aug. 2024, doi: 10.3390/met14080938.
  15. R. Pan, J. Gao, L. Meng, F. Heng, and H. Yang, “A new approach to multiaxial fatigue life prediction: A multi-dimensional multi-scale composite neural network with multi-depth,” Engineering Fracture Mechan-ics, vol. 310, p. 110501, Nov. 2024, doi: 10.1016/j.engfracmech.2024.110501.
  16. D. Faghihi, S. Sarkar, M. Naderi, J. E. Rankin, L. Hackel, and N. Iyyer, “A Probabilistic Design Method for Fatigue Life of Metallic Component,” ASCE-ASME Journal of Risk and Uncertainty in Engineering Sys-tems, Part B: Mechanical Engineering, vol. 4, no. 3, p. 031005, Sep. 2018, doi: 10.1115/1.4038372.
  17. X.-Y. Li, Z. Tao, J.-P. Wu, and W. Zhang, “Uncertainty theory based reliability modeling for fatigue,” En-gineering Failure Analysis, vol. 119, p. 104931, Jan. 2021, doi: 10.1016/j.engfailanal.2020.104931.
  18. G. Whelan and D. L. McDowell, “Machine Learning-Enabled Uncertainty Quantification for Modeling Structure–Property Linkages for Fatigue Critical Engineering Alloys Using an ICME Workflow,” Integr Mater Manuf Innov, vol. 9, no. 4, pp. 376–393, Dec. 2020, doi: 10.1007/s40192-020-00192-2.
  19. J. Chen and Y. Liu, “Probabilistic physics-guided machine learning for fatigue data analysis,” Expert Sys-tems with Applications, vol. 168, p. 114316, Apr. 2021, doi: 10.1016/j.eswa.2020.114316.
  20. M. X. Bastidas-Rodriguez, F. A. Prieto-Ortiz, and E. Espejo, “Fractographic classification in metallic mate-rials by using computer vision,” Engineering Failure Analysis, vol. 59, pp. 237–252, Jan. 2016, doi: 10.1016/j.engfailanal.2015.10.008.
  21. Y. Ech-Choudany, M. Assarar, D. Scida, F. Morain-Nicolier, and B. Bellach, “Unsupervised clustering for building a learning database of acoustic emission signals to identify damage mechanisms in unidirectional laminates,” Applied Acoustics, vol. 123, pp. 123–132, Aug. 2017, doi: 10.1016/j.apacoust.2017.03.008.
  22. Y. Jin and S. Misra, “Controlling mixed-mode fatigue crack growth using deep reinforcement learning,” Applied Soft Computing, vol. 127, p. 109382, Sep. 2022, doi: 10.1016/j.asoc.2022.109382.
  23. B. Madika et al., “Artificial Intelligence for Materials Discovery, Development, and Optimization,” ACS Nano, vol. 19, no. 30, pp. 27116–27158, Aug. 2025, doi: 10.1021/acsnano.5c04200.
  24. R. Liu, A. Kumar, Z. Chen, A. Agrawal, V. Sundararaghavan, and A. Choudhary, “A predictive machine learning approach for microstructure optimization and materials design,” Sci Rep, vol. 5, no. 1, p. 11551, Jun. 2015, doi: 10.1038/srep11551.
  25. J. Chen and Y. Liu, “Fatigue modeling using neural networks: A comprehensive review,” Fatigue & Frac-ture of Engineering Materials & Structures, vol. 45, no. 4, pp. 945–979, Apr. 2022, doi: 10.1111/ffe.13640.
  26. A. Hamada et al., “Advancing fatigue life prediction with machine learning: A review,” Materials Today Communications, vol. 43, p. 111525, Feb. 2025, doi: 10.1016/j.mtcomm.2025.111525.
  27. F. E. Bock, R. C. Aydin, C. J. Cyron, N. Huber, S. R. Kalidindi, and B. Klusemann, “A Review of the Appli-cation of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics,” Front. Ma-ter., vol. 6, p. 110, May 2019, doi: 10.3389/fmats.2019.00110.
  28. M. Gürgen, M. Bakır, E. Bahceci, and H. Ö. Ünver, “A review from physics based models to artificial intel-ligence aided models in fatigue prediction for industry applications,” IJMMS, vol. 16, no. 2/3, pp. 171–200, 2023, doi: 10.1504/IJMMS.2023.133400.
  29. G. A. Tefera and E. G. Koricho, “Prediction of Fatigue Life of Materials Using Machine Learning Ap-proach: A Review,” in Advancement of Science and Technology, A. Birhane, F. Shewarega, M. A. Bitew, M. Wagaw, and A. Abebe Ashetehe, Eds., in EAI/Springer Innovations in Communication and Computing. , Cham: Springer Nature Switzerland, 2025, pp. 147–172. doi: 10.1007/978-3-031-64151-0_11.
  30. P. Negi, “Application of Machine Learning in Predicting the Fatigue behaviour of Materials Using Deep Learning,” TURCOMAT, vol. 9, no. 2, pp. 541–553, Dec. 2018, doi: 10.17762/turcomat.v9i2.13858.
  31. S. Gbagba, L. Maccioni, and F. Concli, “Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures,” Applied Sciences, vol. 14, no. 1, p. 398, Dec. 2023, doi: 10.3390/app14010398.
  32. K. Pałczyński, D. Skibicki, Ł. Pejkowski, and T. Andrysiak, “Application of machine learning methods in multiaxial fatigue life prediction,” Fatigue Fract Eng Mat Struct, vol. 46, no. 2, pp. 416–432, Feb. 2023, doi: 10.1111/ffe.13874.
  33. P. V. Yakovchuk, V. V. Kravchenko, and S. M. Shukayev, “Prediction of the Multiaxial Fatigue Life of Metals Using Machine Learning Methods,” Strength of Materials, vol. 57, no. 2, pp. 279–288, Mar. 2025, doi: 10.1007/s11223-025-00764-7.
  34. J. Yang, G. Kang, Y. Liu, and Q. Kan, “A novel method of multiaxial fatigue life prediction based on deep learning,” International Journal of Fatigue, vol. 151, p. 106356, Oct. 2021, doi: 10.1016/j.ijfatigue.2021.106356.
  35. J. Gao, F. Heng, Y. Yuan, and Y. Liu, “A novel machine learning method for multiaxial fatigue life predic-tion: Improved adaptive neuro-fuzzy inference system,” International Journal of Fatigue, vol. 178, p. 108007, Jan. 2024, doi: 10.1016/j.ijfatigue.2023.108007.
  36. L. Sun and X. Huang, “Prediction of fatigue crack propagation lives based on machine learning and data-driven approach,” Journal of Ocean Engineering and Science, vol. 9, no. 6, pp. 592–604, Dec. 2024, doi: 10.1016/j.joes.2022.06.041.
  37. J. Li, X. Cao, R. Chen, C. Zhao, Y. Li, and X. Huang, “Prediction of remaining fatigue life of metal speci-mens using data-driven method based on acoustic emission signal,” Applied Acoustics, vol. 211, p. 109571, Aug. 2023, doi: 10.1016/j.apacoust.2023.109571.
  38. Y. Zhu, J. Zhang, J. Luo, X. Guo, Z. Liu, and R. Zhang, “A Real-Time Remaining Fatigue Life Prediction Approach Based on a Hybrid Deep Learning Network,” Processes, vol. 11, no. 11, p. 3220, Nov. 2023, doi: 10.3390/pr11113220.
  39. L. He, Z. Wang, H. Akebono, and A. Sugeta, “Machine learning-based predictions of fatigue life and fa-tigue limit for steels,” Journal of Materials Science & Technology, vol. 90, pp. 9–19, Nov. 2021, doi: 10.1016/j.jmst.2021.02.021.
  40. J. Fan, Z. Wang, C. Liu, D. Shi, and X. Yang, “A tensile properties-related fatigue strength predicted ma-chine learning framework for alloys used in aerospace,” Engineering Fracture Mechanics, vol. 301, p. 110057, May 2024, doi: 10.1016/j.engfracmech.2024.110057.
  41. J. Chang, D. Basvoju, A. Vakanski, I. Charit, and M. Xian, “Predictive Modeling and Uncertainty Quantifi-cation of Fatigue Life in Metal Alloys using Machine Learning,” Jan. 25, 2025, arXiv: arXiv:2501.15057. doi: 10.48550/arXiv.2501.15057.
  42. X. Sun, K. Zhou, S. Shi, K. Song, and X. Chen, “A new cyclical generative adversarial network based data augmentation method for multiaxial fatigue life prediction,” International Journal of Fatigue, vol. 162, p. 106996, Sep. 2022, doi: 10.1016/j.ijfatigue.2022.106996.
  43. Z. Zheng, X. Li, T. Sun, Z. Huang, and C. Xie, “Multiaxial fatigue life prediction of metals considering loading paths by image recognition and machine learning,” Engineering Failure Analysis, vol. 143, p. 106851, Jan. 2023, doi: 10.1016/j.engfailanal.2022.106851.
  44. T. C. H. Nguyen and N. Vu‐Bac, “Machine Learning‐Assisted Sensitivity Analysis for Stochastic Fatigue Life Modeling of Metals,” Int Journal of Mech Sys Dyn, p. msd2.70024, May 2025, doi: 10.1002/msd2.70024.
  45. A. Karolczuk, D. Skibicki, and Ł. Pejkowski, “Gaussian Process for Machine Learning-Based Fatigue Life Prediction Model under Multiaxial Stress–Strain Conditions,” Materials, vol. 15, no. 21, p. 7797, Nov. 2022, doi: 10.3390/ma15217797.
  46. A. Karolczuk and M. Słoński, “Application of the Gaussian process for fatigue life prediction under multi-axial loading,” Mechanical Systems and Signal Processing, vol. 167, p. 108599, Mar. 2022, doi: 10.1016/j.ymssp.2021.108599.
  47. T. Ma, W. Zhang, L. Chang, J. Zhao, and C. Zhou, “Study of Hybrid Machine Learning Multiaxial Low‐Cycle Fatigue Life Prediction Model of CP‐Ti,” Fatigue Fract Eng Mat Struct, p. ffe.14604, Feb. 2025, doi: 10.1111/ffe.14604.
  48. G. He, Y. Zhao, and C. Yan, “Uncertainty quantification in multiaxial fatigue life prediction using Bayesi-an neural networks,” Engineering Fracture Mechanics, vol. 298, p. 109961, Mar. 2024, doi: 10.1016/j.engfracmech.2024.109961.
  49. Z. Liang, X. Wang, Y. Cui, W. Xu, Y. Zhang, and Y. He, “A new data-driven probabilistic fatigue life pre-diction framework informed by experiments and multiscale simulation,” International Journal of Fatigue, vol. 174, p. 107731, Sep. 2023, doi: 10.1016/j.ijfatigue.2023.107731.
  50. J. Halamka, M. Bartošák, and M. Španiel, “Using hybrid physics-informed neural networks to predict life-time under multiaxial fatigue loading,” Engineering Fracture Mechanics, vol. 289, p. 109351, Sep. 2023, doi: 10.1016/j.engfracmech.2023.109351.
  51. X. Sun, T. Zhou, K. Song, and X. Chen, “An image recognition based multiaxial low-cycle fatigue life pre-diction method with CNN model,” International Journal of Fatigue, vol. 167, p. 107324, Feb. 2023, doi: 10.1016/j.ijfatigue.2022.107324.
  52. Z. Tianguo, S. Xingyue, and C. Xu, “A physics-guided modelling method of artificial neural network for multiaxial fatigue life prediction under irregular loading,” Phil. Trans. R. Soc. A, vol. 381, no. 2260, Jun. 2023.
  53. Y. Savchuk, P. Yakovchuk, and S. Shukayev, “Input Parameter Analysis for Low-Cycle Multiaxial Fatigue Models Using Artificial Neural Network,” KEM, vol. 1035, pp. 59–69, Dec. 2025, doi: 10.4028/p-YA35mB.
  54. P. Zhang, K. Tang, A. Wang, H. Wu, and Z. Zhong, “Neural network integrated with symbolic regression for multiaxial fatigue life prediction,” International Journal of Fatigue, vol. 188, p. 108535, Nov. 2024, doi: 10.1016/j.ijfatigue.2024.108535.
  55. B. Zhao et al., “Multiaxial fatigue life prediction method based on the back-propagation neural network,” International Journal of Fatigue, vol. 166, p. 107274, Jan. 2023, doi: 10.1016/j.ijfatigue.2022.107274.
  56. T. Itoh, M. Sakane, M. Ohnami, and D. F. Socie, “Nonproportional Low Cycle Fatigue Criterion for Type 304 Stainless Steel,” Journal of Engineering Materials and Technology, vol. 117, no. 3, pp. 285–292, Jul. 1995, doi: 10.1115/1.2804541.
  57. S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” Nov. 25, 2017, arXiv: arXiv:1705.07874. Accessed: Nov. 13, 2024. [Online]. Available: http://arxiv.org/abs/1705.07874
  58. Z. Zheng, J. Yang, C. Lin, L. Jiang, and L. Li, “Multiaxial Fatigue Life Prediction Based on Deep Symbolic Regression,” Fatigue Fract Eng Mat Struct, p. ffe.70154, Dec. 2025, doi: 10.1111/ffe.70154.
  59. Y. Yang et al., “A deep learning approach for low-cycle fatigue life prediction under thermal–mechanical loading based on a novel neural network model,” Engineering Fracture Mechanics, vol. 306, p. 110239, Aug. 2024, doi: 10.1016/j.engfracmech.2024.110239.
  60. S. Chen, Y. Bai, X. Zhou, and A. Yang, “A deep learning dataset for metal multiaxial fatigue life predic-tion,” Sci Data, vol. 11, no. 1, p. 1027, Sep. 2024, doi: 10.1038/s41597-024-03862-4.
  61. J. Papuga, M. Nesládek, and J. Jurenka, “Differences in the response to in-phase and out-of-phase multiax-ial high-cycle fatigue loading,” Frattura ed Integrità Strutturale, vol. 13, no. 50, pp. 163–183, Aug. 2019, doi: 10.3221/IGF-ESIS.50.15.

Published

2026-06-18

How to Cite

[1]
P. Yakovchuk and S. Shukayev, “A Review of Input Strategies and Model Architectures in Machine Learning Approaches for Multiaxial Fatigue Life Prediction”, Mech. Adv. Technol., vol. 10, no. 2(109), Jun. 2026.

Issue

Vol. 10 No. 2(109) (2026): in progress

Section

Mechanics

License

Copyright (c) 2026 Павло Яковчук, Сергій Шукаєв

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The ownership of copyright remains with the Authors.
 
Authors may use their own material in other publications provided that the Journal is acknowledged as the original place of publication and National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” as the Publisher.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work