Automatic machine learning versus human knowledge-based models, property-based models and the fatigue problem.

This paper is devoted to emphasizing the importance of human-based knowledge and to present the original property-based models. The main idea is that models are built in terms of equations that reproduce and guarantee their satisfaction, which leads to non-arbitrary parametric models. The methods based on data alone are not sufficient to be applied to fatigue S-N and GRV-N models: first, the required high number of results in machine learning is not attained in fatigue; second, a black box cannot supply a comprehension of the fatigue phenomenon; third, the absence of a supporting model impedes extrapolation beyond the scope of experimentation; and fourth, many other data are required to include the stress ratio, , while robust models are already available.

Probabilistic Assessment of Fracture Toughness of Epoxy Resin EPOLAM 2025 Including the Notch Radii Effect.

Many design scenarios of components made of polymer materials are concerned with notches as representative constructive details. The failure hazard assessment of these components using models based on the assumption of cracked components leads to over-conservative failure estimations. Among the different alternative approaches proposed that are based on the apparent fracture toughness, KcN is considered.

Special Issue: Probabilistic Mechanical Fatigue and Fracture of Materials.

When designing structural and mechanical components, general structural integrity criteria must be met in order to ensure a valid performance according to its designed function, that is, supporting loads or resisting any kind of action causing stress and strains to the material without catastrophic failure. For these reasons, the development of solutions to manage the test conditions, failure mechanism, damage evolution, component functionalities and loading types should be implemented. The aim of this Special Issue "Probabilistic Mechanical Fatigue and Fracture of Materials" is to contribute to updating current and future state-of-the-art methodologies that promote an objective material characterization and the development of advanced damage models that ensure a feasible transferability from the experimental results to the design of real components.

A Probabilistic Approach to Assessing and Predicting the Failure of Notched Components.

This work presents a probabilistic model to evaluate the strength results obtained from an experimental characterisation program on notched components. The generalised local method (GLM) is applied to the derivation of the primary failure cumulative distribution function (PFCDF) as a material property (i.e.

Fatigue Assessment Strategy Using Bayesian Techniques.

Different empirical models have been proposed in the literature to determine the fatigue strength as a function of lifetime, according to linear, parabolic, hyperbolic, exponential, and other shaped solutions. However, most of them imply a deterministic definition of the S-N field, despite the inherent scatter exhibited by the fatigue results issuing from experimental campaigns. In this work, the Bayesian theory is presented as a suitable way not only to convert deterministic into probabilistic models, but to enhance probabilistic fatigue models with the statistical distribution of the percentile curves of failure probability interpreted as their confidence bands.