基于RSM代理模型的武器装备体系仿真优化算法研究

Research on Simulation Optimization Algorithms of Weapon Equipment Systems Based on RSM Surrogate Model

摘要: 体系优化是装备体系研究的核心问题，但是基于仿真的武器装备体系优化方法存在寻优效率低、费用高昂的缺陷。本文结合武器装备体系优化问题的特点，提出基于RSM (Response Surface Methodology)，代理模型的武器装备体系优化算法。其中，选用响应面模型作为代理模型，通过均匀设计方法生成初始样本点，运用最小化响应面法进行代理模型更新，采用梯度下降法进行迭代优化。实例分析表明，较之仿真方法，该算法具有较高的寻优精度和收敛速度，对提高武器装备体系优化的效率具有较高的理论和实用价值。

Abstract: System optimization is one of the core issues in research of the weapon equipment systems. How-ever, to overcome low efficiency and high cost of optimization methods of equipment systems based on simulation, an optimization algorithm of weapon equipment systems based on RSM surrogate model and uniform design was presented, in which the surrogate model was updated by the minimization response surface method, and gradient descent algorithm was using in the opti-mization algorithm. The optimization algorithm put forward in this paper had a high precision and high speed of convergence, and it also had high theoretical and practical value on solving non- liner problems that were proved in an experiment.