Simulated micromechanical models using artificial neural networks

A new method, termed simulated micromechanical models using artificial neur al networks (MMANN), is proposed to generate micromechanical material model s for nonlinear and damage behavior of heterogeneous materials. Artificial neural networks (ANN) are trained with results from detailed nonlinear fini te-element (EE) analyses of a repeating unit cell (UC), with and without in duced damage, e.g., voids or cracks between the fiber and matrix phases. Th e FE simulations are used to form the effective stress-strain response for a unit cell with different geometry and damage parameters. The EE analyses are performed for a relatively small number of applied strain paths and dam age parameters. It is shown that MMANN material models of this type exhibit many interesting features, including different tension and compression res ponse, that are usually difficult to model by conventional micromechanical approaches. MMANN material models can be easily applied in a displacement-b ased FE for nonlinear analysis of composite structures. Application example s are shown where micromodels are generated to represent the homogenized no nlinear multiaxial response of a unidirectional composite with and without damage. In the case of analysis with damage growth, thermodynamics with irr eversible processes (TIP) is used to derive the response of an equivalent h omogenized damage medium with evolution equations for damage. The proposed damage formulation incorporates the generalizations generated by the MMANN method for stresses and other possible responses from analysis results of u nit cells with fixed levels of damage.