Robustness in Fatigue Strength Estimation

TL;DR

This paper explores a machine learning-based method for estimating fatigue strength that aims to reduce experimental costs, analyzing its robustness against common practical issues like prior misspecification and load discretization.

Contribution

It introduces a modular ML approach for fatigue strength estimation and evaluates its robustness and applicability compared to traditional methods.

Findings

The ML approach reduces the number of experiments needed.

It remains robust against prior misspecification.

It outperforms state-of-the-art methods in certain scenarios.

Abstract

Fatigue strength estimation is a costly manual material characterization process in which state-of-the-art approaches follow a standardized experiment and analysis procedure. In this paper, we examine a modular, Machine Learning-based approach for fatigue strength estimation that is likely to reduce the number of experiments and, thus, the overall experimental costs. Despite its high potential, deployment of a new approach in a real-life lab requires more than the theoretical definition and simulation. Therefore, we study the robustness of the approach against misspecification of the prior and discretization of the specified loads. We identify its applicability and its advantageous behavior over the state-of-the-art methods, potentially reducing the number of costly experiments.