Vibrational genetic algorithm enhanced with fuzzy logic and neural networks

A new optimization algorithm called multi-frequency vibrational genetic algorithm (mVGA) is significantly improved and tested for two different test cases: an inverse design of an airfoil in subsonic flow and a direct shape optimization of an airfoil in transonic flow. The algorithm emphasizes a new mutation application strategy and diversity variety, such as, the global random diversity and the local controlled diversity. The local controlled diversity is based on either a fuzzy logic controller or an artificial neural network depending on the problem type. For both of the demonstration problems considered, remarkable reductions in the computational times have been accomplished.