This work represents the first step towards the application of machine learning techniques in the prediction of statistical design allowables of composite laminates. Building on data generated analytically, four machine algorithms (XGBoost, Random Forests, Gaussian Processes and Artificial Neural Networks) are used to predict the notched strength of composite laminates and their statistical distribution, associated to the uncertainty related to the material properties and geometrical features. This work focuses not only on the so-called Legacy Quad Laminates (0°/90°/±45°), typically used in the design of composite aerostructures, but also on the newer concept of double-double (or double-angle ply) laminates. Very good representations of the design space, translating in low generalization relative errors of around ±10%, and very accurate representations of the distributions of notched strengths around single design points and corresponding B-basis allowables are obtained. All machine learning algorithms, with the exception of the Random Forests, show very good performances, with Gaussian Processes outperforming the others for very small number of data points while Artificial Neural Networks have better performance for larger training sets. 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.

To simplify the analysis and characterisation of composite laminates, an invariant-based approach to stiffness that takes the trace of the plane stress stiffness matrix as a material property was recently proposed. In the present work, a study based on micro-mechanical models brings new insight to this invariant-based approach. The Rule of Mixtures and the Halpin-Tsai models are used to establish the relations between the fibre volume fraction, the fibre/matrix stiffness ratios, and the trace-normalised engineering constants of unidirectional laminae and multidirectional laminates. For sufficiently high longitudinal fibre/matrix stiffness ratios and for fibre volume fractions between 50% and 70%, typical of advanced CFRPs, the variation of the trace-normalised longitudinal Young's modulus is within 6% for unidirectional laminae and within 1% for multidirectional laminates, supporting the definition of an invariant-based approach to stiffness based on a Master Ply concept and laminate factors derived thereof, defining clearly a domain of applicability of the invariant theory and confirming the empirical observations of the past.