Volume Fraction Optimization of Four-Parameter FGM Beams Resting on Elastic Foundation

In this paper, volume fraction optimization of Functionally Graded (FG) beams resting on elastic foundation for maximizing the first natural frequency is investigated. The two-constituent functionally graded beam consists of ceramic and metal. These constituents are graded through the beam thickness according to a generalized power-law distribution. One of the advantages of generalized power- law distribution is the ability of controlling the materials volume fraction of FG structures for considered applications. The primary optimization variables are the four parameters in the power-law distribution. Since the optimization processes are complicated and time consuming, a novel meta?heuristic called Imperialist Competitive Algorithm (ICA) and Artificial Neural Networks (ANNs) are implemented to improve the speed of optimization problem. The performance of ICA is evaluated in comparison with Genetic Algorithm (GA). Results show the success of combination of ANN and ICA for design of material profile of FG beam. Results also show that the combination of ANN and ICA can reduce the run time considerably.