Working Group 2

Analysis of Fatigue Data

WG2 focuses on developing accurate computational models for fatigue estimation, comparing deterministic and probabilistic approaches, and integrating AI to enhance fatigue prediction.

Working Group Leader and Co-Leader

Dr Anghel Cernescu & Prof Tea Marohnic

W.G.2.1

Deterministic vs. Probabilistic Modeling

Analyzes existing regression models to determine the best approach for deterministic and probabilistic fatigue estimations.

W.G.2.2

Treating the Benchmarking Output

Standardizes benchmarking procedures by defining clear evaluation criteria for assessing fatigue prediction accuracy.

W.G.2.3

Artificial Intelligence in Fatigue Estimation

Explores AI-driven methods for processing fatigue data, aiming to improve prediction accuracy and expand material characterization capabilities.

Activities

The WG will conduct comparative studies on various modeling techniques and organize workshops on AI applications in fatigue estimation. Training sessions will be held to educate researchers on regression analysis and benchmarking techniques.

Deliverables

WG2 will produce technical reports on AI-driven fatigue analysis, publish open-access articles on probabilistic modeling, and develop standardized benchmarking guidelines for fatigue solvers.

Prague FABER MC2&WG6 Meetings 2025

First call for applications for Short-Term Scientific Missions (STSMs)

CA23109 – Fatigue Benchmark Repository (FABER) is now on LinkedIn

Working Group 2

Analysis of Fatigue Data

Dr Anghel Cernescu & Prof Tea Marohnic

W.G.2.1

W.G.2.2

W.G.2.3

Activities

Deliverables

Working Group Task Leaders

WG 2.1, Mr Diego Díaz Salamanca

John Doe

John Doe

Downloads

View Gallery

View Downloads