Source code for paper: "A Multi-Objective Variable Fidelity Optimization Method for Genetic Algorithms"

Abstract

Source code supporting a novel variable-fidelity optimization (VFO) scheme is presented for multi-objective genetic algorithms. The technique uses a low- and high-fidelity ver-sion of the objective function with a Kriging scaling model to interpolate be- tween them. The Kriging model is constructed online through a fixed updating schedule. Results for three standard genetic algorithm test cases and a two- objective stiffened panel optimization problem are presented. For the stiffened panel problem statistical analysis of four performance metrics are used to com- pare the Pareto fronts between the VFO method, full high-fidelity optimizer runs, and Pareto fronts developed by enumeration. The fixed updating ap- proach is shown to reduce the number of high-fidelity calls significantly while approximating the Pareto front in an efficient manner.