Machine learning assisted coupled frequency analysis of skewed multi-phase magnetoelectric composite plates with temperature and moisture dependent properties

In this article, the application of an artificial neural network (ANN)-based machine learning (ML) strategy to predict coupled frequency geometrically skewed multiphase magnetoelectric (MME) composite plate exposed hygrothermal environment is presented. The ANN model trained using a dataset comprising more than one million simulations conducted in-house developed finite element formulation. underlying multiphysics governing equations are derived Hamilton’s principle and higher-order shear deformation theory (HSDT). influence on elastic stiffness MME composites defined by empirical constants in constitutive relations. Four prominent combinations leading different relations have been considered study. Alongside, geometrical skewness fundamental also assessed. For training model, Levenberg–Marquardt optimization algorithm with 30 neurons along tangent sigmoid activation function used. tested unseen dataset, from data, it shown accurately natural maximum error 2.3%. Further, excluding time considering computational alone, found be 6.3 times faster FE simulations. It anticipated that such ML-based reduced order models can effective design process, especially complex problems, as work, involving multitude geometric, loading material parameters.