<ul><li>Researchers propose DeepOFormer, a deep operator learning framework for fatigue life prediction.</li><li>It addresses the challenge of overfitting using a transformer-based encoder and a mean L2 relative error loss function.</li><li>Domain-informed features, such as Stussi, Weibull, and Pascual and Meeker (PM), are considered to improve prediction accuracy.</li><li>DeepOFormer achieves superior performance compared to state-of-the-art deep/machine learning methods in predicting fatigue life in aluminum alloys.</li></ul>

DeepOFormer: Deep Operator Learning with Domain-informed Features for Fatigue Life Prediction

Discover more