Abstract: The inverse design is a novel modern design method, and it can provide strong theoretical support for the composite design. In this paper, the structural mechanical behaviors of composite laminates are considered as deterministic and uncertainty responses, respectively. On the basis of the finite element method (FEM) or experimental data, the advanced Group Method of Data Handling-Neural Network (GMDH-NN) algorithm is used to construct the relationship between input variables and output responses, and the genetic algorithm (GA) is employed in the optimization process of inverse simulation for the composite laminates. Furthermore, several examples are given to show that the presented methods are reliable and feasible in application to gain the elastic constants, which is of great significance in practical engineering.

Key words: inverse design, composite laminates, Group Method of Data Handling-Neural Network (GMDH-NN), genetic algorithm (GA), elastic constants