A hybrid Bayesian framework integrating physics-informed yield strength corrections with neural networks for fatigue life prediction of additively manufactured metals. Overview: This repository implements a novel probabilistic framework for fatigue life prediction in additively manufactured (AM) metals, combining Bayesian Neural Networks with a physics-informed yield strength correction procedure. The methodology addresses critical limitations of conventional deterministic ap

A multistage computational methodology combining the local strain-life approach with fracture mechanics for fatigue life prediction in notched components. Overview: This repository presents a comprehensive defect-aware fatigue life prediction framework that integrates short-crack initiation and long-crack propagation phases for corroded mooring chains. The methodology addresses microstructural defects, stress concentrations, and material heterogeneity across different zones,

A hybrid computational framework integrating finite element analysis and recurrent neural networks for fracture prediction. Overview This...

Fatigue strength assessment of advanced metallic alloys Overview: We present a conditional probability framework to address the challenge...

Understanding Fatigue Properties of Additively Manufactured Ti-6Al-4V We investigate additively manufactured titanium alloys regarding...

Enhancing Fatigue Strength in High-Strength Steel Welds: HFMI and TIG Dressing Techniques The demand for lightweight structural solutions...