Solving optimization problems is essential for many engineering applications and research tools. In a previous report, we proposed a new optimization method, MOST (Monte Carlo Stochastic Optimization), using the Monte...
详细信息
Solving optimization problems is essential for many engineering applications and research tools. In a previous report, we proposed a new optimization method, MOST (Monte Carlo Stochastic Optimization), using the Monte Carlo method, and applied it to benchmark problems for optimization methods, and optimization of neural network machine learning. While the proposed method MOST was a single objective, this study is an extension of MOST so that it can be applied to multi-objectivefunctions for the purpose of improving generality. As the verification, it was applied to the optimization problem with the restriction condition first, and it was also applied to the benchmark problem for the multi-objective optimization technique verification, and the validity was confirmed. For comparison, the calculation by genetic algorithm was also carried out, and it was confirmed that MOST was excellent in calculation accuracy and calculation time.& COPY;2023 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.
暂无评论