Global Optimization Method Based on Incremental Radial Basis Functions

Global optimization techniques have been used extensively due to their capability in handling complex engineering problems. Metamodel becomes effective method to enhance global optimization. In this paper, we propose a new global optimization method base on incremental metamodel. At each sampling step, we adopt inherited Latin HyperCube design to sample points step by step, and propose a new incremental metamodel to update the cofficient matrix gradually. Experiments proved that the global optimization method has highest efficiency and can be finding global minimum fastly.