Second International Conference on Advances in Mechanical and Robotics Engineering- AMRE 2014
Author(s) : HIEU PHAM, HIROSHI HASEGAWA, TAM BUI
This paper describes an evolutionary strategy called PSOGA-NN, which uses Neural Network (NN) for self-adaptive control of hybrid Particle Swarm Optimization and Adaptive Plan system with Genetic Algorithm (PSO-APGA) to solve large scale problems and constrained real-parameter optimization. This approach combines the search ability of all optimization techniques (PSO, GA) for stability of convergence to the optimal solution and incorporates concept from neural network for self-adaptive of control parameters. It is shown to be statistically significantly superior to other Evolutionary Algorithms (EAs) on numerical benchmark problems and constrained real-parameter optimization.