A Heuristic Framework for Reliability Based Optimization of Laminated Composite Structures

The design of anisotropic laminated composite structures is very susceptible to changes in loading, angle of fiber orientation and ply thickness. Thus, optimization of such structures, using a reliability index as a constraint, is an important problem to be dealt. The problem of structural optimization of laminated composite materials with reliability constraint using a genetic algorithm and two types of neural networks is addressed in this paper. The reliability evaluation is performed using, alternatively, the following methods: First Order Reliability Method (FORM), FORM with Multiple Check Points (MCP), Standard Monte Carlo (MC) and Monte Carlo with Importance Sampling (MC-IS). The optimization process is performed using a genetic algorithm. To overcome high computational cost, Multilayer Perceptron or Radial Basis Artificial Neural Networks are used. This methodology can be used without loss of accuracy and large computational time savings, even when dealing with structures with non-linear behavior, as it is shown by some numerical examples.