Abstract

This work represents the first study towards the application of machine learning techniques in the prediction of statistical design allowables of composite laminates. Building on data generated analytically [1], four machine learning algorithms are used to predict the notched strength of composite laminates and their statistical distribution, associated to material and geometrical variability.

Very good 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.

References

[1] C. Furtado, A. Arteiro, M.A. Bessa, B.L. Wardle, P.P. Camanho. Prediction of size effects in open hole laminates using only the Young's modulus, the strength, and the R-curve of the 0° ply, Composites Part A, 101, pp. 306-317, 2017.