A Genetic Algorithm for Laminate Layups

The design of laminate layups using a genetic algorithm function optimizer has been investigated using a generate-and-test evaluation function and the layup-synthesis rule-base from a knowledge based design system. A simple coding of plies to genes is shown to be applicable in each case when coupled with a penalty function that constrains genetic search to permissable layup candidates. Experiments with the generate-and-test evaluation demonstrate the robustness and accuracy of the system in the design of small scale asymmetric laminates. Comparative tests with a knowledge based laminate design system are also presented for four different load types which confirm the ability of the genetic system to search laminate configuration spaces with a rule-based evaluation function.