基于移动最小二乘和粒子群算法的快速全局优化算法

Response surface model based on moving least squares and particle swarm optimization method

为解决电磁场逆问题分析计算过度依赖计算机资源这一"瓶颈"问题,提出了一种新的快速全局优化算法。该算法首先应用最小移动二乘近似方法重构原优化问题,然后应用改进的粒子群算法对重构的优化问题进行快速全局寻优。典型数值计算结果表明:所构造的基于移动最小二乘近似的表面响应模型具有灵活处理奇异采样点的能力和参数自适应能力。

A new response surface model （RSM） , the moving least squares （MLS） approximation, was proposed for reconstructing the objective/constraint functions for the design optimization of electromagnetic devices. The reconstructed functions were then combined with the particle swarm optimization （PSO） method to develop a computationally efficient technique to obtain the global solutions. The new method has： the flexibility in dealing with irregular sample points, the self-adaptive ability to regulate the parameters of the MLS models. Detailed numerical examples are given to validate the proposed technique.