Multi-Objective Optimization of Composite Angle Grid Plates for Maximum Buckling Load and Minimum Weight Using Genetic Algorithms and Neural Networks

Abstract

The present work describes an optimization process based on the ε-constraint method to find an optimum design to maximize the critical buckling load and minimize the structural weight of an angle grid plate. A comprehensive geometrical model is considered including all geometrical design variables of the grid. In order to achieve a precise and effective approximation of the buckling load, an artificial neural network (ANN) is employed. Training data for ANN is obtained by the Mindlin plate theory as well as the Ritz method. The ANN is combined with genetic algorithms (GA) to find the optimized design variables for an angle grid structure. The results provide a wide range of geometrical data for designers to choose the maximum buckling load at the minimum structural weight.