December 06, 2022
Prof. Pedro Camanho is from the university of Porto and will be visiting the lab next week on Tuesday 6/12. He is a expert and leading scientist in the field of polymer composites, particularly predicting their failure using numerical methods.
Strength prediction of composite laminates under uncertainties using theory-guided machine learning
This work represents a first study towards the application of theory-based machine learning techniques in the prediction of design allowables of notched polymer composite laminates accounting for material and geometric uncertainties. Building on data generated analytically using either phase-field methods or finite fracture mechanics, and reduced representations of composite lay-ups, four machine learning algorithms are used to predict the strength of composite laminates with notches of several geometries and the corresponding statistical distribution, associated to material and geometrical variability.
Excellent representations of the design space (relative errors of around ±10%) and very accurate representations of the distributions of notched strengths and corresponding B-basis allowables are obtained. The Gaussian Processes models proved to be the most reliable, considering their continuous nature and fast training process. This work serves as basis for the prediction of first-ply failure, ultimate strength and failure mode of composite specimens based on non-linear finite element simulations, providing further reduction of the computational time required to virtually obtain the design allowables for composite laminates.