Surrogate model based optimizations on variable stiffness composite plates

What is it about?

Due to the high computational cost of variable stiffness composite laminates, a surrogate model is used to optimize the fiber lay-up for the composite laminate. The surrogate model used is Radial Basis Functions (RBFs). Two different heuristic algorithms are used to perform the optimization, Particle Swarm Optimization (PSO) and Whale Optimization Algorithm (WOA). These optimization methods' performances are compared with simple metrics. Also the surrogate model based optimization shows satisfactory results.

Featured Image

Why is it important?

This work shows that surrogate models are reliable and faster to use in the variable stiffness composite laminates. Also a new optimization algorithm's (WOA) performance is tested first time with the variable stiffness composites with respect to a well known optimization algorithm (PSO). It is concluded that even if WOA has some drawbacks with respect to PSO, it is a simple and robust algorithm which can be used easily in variable stiffness composites.

Perspectives