Optimal Desigin of Structures with Frequency Constraints Using Wavelet Back Propagation Neural

A combination of improved genetic algorithm and neural networks is proposed to find the optimal weight of structures subject to multiple natural frequency constraints. The structural optimization is carried out by an evolutionary algorithm employing the discrete design variables. To reduce the computational time of the optimization process, the natural frequencies of structures are evaluated by using properly trained back propagation (BP) and wavelet back propagation (WBP) neural networks. The numerical results reveal the robustness and high performance of the suggested methods for the structural optimization with frequency constraints. It is found that the best results are obtained using WBP network.