Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning

Researchers at an undisclosed institution present CV, a computer vision framework that estimates the fatigue life of lightweight alloy steels from optical micrographs, achieving an R² of 0.93 and RMSE of 0.18 log-cycles with ResNet-50 on a synthetic benchmark. The physics-informed pipeline, which uses a 28-dimensional feature extractor and a CNN with Gaussian negative log-likelihood loss, reduces Expected Calibration Error by 76% compared to a mean-squared-error baseline. The method runs in under 65 ms per image and is open-sourced, though validation is currently limited to synthetic micrographs.

arXiv:2607.28695v1 Announce Type: new Abstract: Here is the plain text version optimized for arXiv's submission form. Custom macros like \CV and \SI have been converted to standard text/math so they render correctly on the webpage: Evaluating the fatigue life of structural steels conventionally requires mechanical testing lasting tens to hundreds of hours, making it impractical for rapid quality control. We present CV, a computer vision framework that estimates the fatigue life $\log N f$ of lightweight alloy steels directly from optical micrographs without physical testing.The pipeline features a seven-stage OpenCV preprocessing routine to remove artifacts, a 28-dimensional physics-informed feature extractor quantifying crack morphology, grain structure, porosity, and texture , and a CNN regression model trained with a Gaussian negative log-likelihood GNLL loss to jointly predict $\log N f$ and sample-specific uncertainty $\hat{\sigma}$.Evaluating three architectures SE-CNN, ResNet-50, VGG-16 on a synthetic micrograph benchmark, ResNet-50 achieves $R^2 = 0.93$, RMSE = 0.18 log-cycles, and macro-F1 = 0.91. The GNLL objective reduces Expected Calibration Error by 76% compared to a mean-squared-error baseline ECE: $0.089 \rightarrow 0.021$ . Grad-CAM maps confirm the network attends to metallurgically meaningful microstructural features.Running in under 65 ms per image, the pipeline and synthetic dataset generator are open-sourced. Because validation relies entirely on synthetic micrographs, these results demonstrate methodological soundness under simulated conditions; a domain-transfer study on real field samples is the immediate next step.