Physics-Informed Review of Machine-Learned Fatigue Capacity

Which invariants should be checked independently of predictive accuracy? This review answers by treating physics-informed assurance as a property of a sociotechnical workflow rather than a feature that can be read from average accuracy. The focal setting is multiaxial lattice loading, where a fast surrogate can move a design decision far outside the domain where its training simulations were physically credible. Evidence from the assigned publications is synthesized with foundational studies of calibration, distribution shift, causal structure, and responsible deployment. Four requirements follow: preserve the lineage of parameterized geometries, finite-element and multiscale outputs, loading histories, material properties, and validation measurements; measure stability across relevant perturbations; connect confidence to a specific action; and maintain a route for human challenge and correction. The framework distinguishes descriptive performance from decision utility and separates uncertainty about the world from uncertainty created by the model and its evaluator. It also shows why faster inference or richer reasoning is valuable only when it improves a defined decision under a transparent resource budget. The article is a literature review and research agenda, not a report of a newly completed trial.

1. Ma, Mingjun, et al. "MuSK: Multi-Scale Knowledge Learning for Provenance-Graph Anomaly Detection." *Computer Networks* 289 (2026): 112728.
2. Li, Yuanhao, et al. "BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models." *arXiv preprint arXiv:2605.09134* (2026).
3. Wang, Lizhe, et al. "Synergizing Machine Learning and Multiscale Shakedown Method for Shakedown Loading Capacity Evaluation of Parameterized Lattice Structures." *Extreme Mechanics Letters* 75 (2025): 102297.
4. Lundberg, Scott M., and Su-In Lee. "A Unified Approach to Interpreting Model Predictions." *Advances in Neural Information Processing Systems*, vol. 30, 2017.
5. Bendsoe, Martin P., and Ole Sigmund. *Topology Optimization: Theory, Methods, and Applications*. Springer, 2003.
6. Wilkinson, Mark D., et al. "The FAIR Guiding Principles for Scientific Data Management and Stewardship." *Scientific Data*, vol. 3, 2016, article 160018.
7. Suresh, S. *Fatigue of Materials*. 2nd ed., Cambridge University Press, 1998.
8. Miner, M. A. "Cumulative Damage in Fatigue." *Journal of Applied Mechanics*, vol. 12, 1945, pp. A159-A164.
9. Paris, P., and F. Erdogan. "A Critical Analysis of Crack Propagation Laws." *Journal of Basic Engineering*, vol. 85, no. 4, 1963, pp. 528-533.
10. Fatemi, Ali, and Darrell F. Socie. "A Critical Plane Approach to Multiaxial Fatigue Damage Including Out-of-Phase Loading." *Fatigue & Fracture of Engineering Materials & Structures*, vol. 11, no. 3, 1988, pp. 149-165.
11. Geers, M. G. D., V. G. Kouznetsova, and W. A. M. Brekelmans. "Multi-Scale Computational Homogenization: Trends and Challenges." *Journal of Computational and Applied Mathematics*, vol. 234, no. 7, 2010, pp. 2175-2182.
12. Kennedy, Marc C., and Anthony O'Hagan. "Bayesian Calibration of Computer Models." *Journal of the Royal Statistical Society: Series B*, vol. 63, no. 3, 2001, pp. 425-464.
13. Saltelli, Andrea, et al. "Variance Based Sensitivity Analysis of Model Output: Design and Estimator for the Total Sensitivity Index." *Computer Physics Communications*, vol. 181, no. 2, 2010, pp. 259-270.