Weight optimization of hybrid composite laminate using learning-oriented artificial algae algorithm

Abstract

The optimal design of parameters is vital for the effective use of hybrid composite laminated structures. This is due to a highly dependent property of laminated composite structures strength on its fiber orientation, stacking sequence and the number of ply in each laminate. The main aim of this study is to apply Learning-Oriented Artificial Algae Algorithm for optimization of the weight of rectangular hybrid composite laminated plate subjected to compressive in-plane loading. The design parameters are number of plies and stacking sequence of the laminate. The critical buckling factor is the constraint of the optimization process. The parameters of the hybrid composite plate are optimized using Learning-Oriented Artificial Algae Algorithm with the aim of minimizing weight. The performance of the algorithm was compared with previous studies that employed the GA and ACO algorithms. The Learning-Oriented method is integrated to reduce the number of functions evaluated and in turn reducing computational cost. The results showed that Learning-Oriented Artificial Algae Algorithm outperformed GA and ACO, and hence can be successfully applied in the optimization of laminated composite structures.