摘要
针对利用粒子群优化算法进行多极值点函数优化时,存在陷入局部极小点和搜寻效率低的问题.提出旋转曲面变换方法,将被优化函数映射到一个同胚曲面上.它将当前局部极小点变换为全局最大点,并保持被优化函数值在当前局部极小点以下部分的形状不变,从而克服陷入局部极小点的问题.最后将其用于解一个非线性系统的最优控制问题,实验结果证明了该方法的可行性和有效性.
Particle swarm optimization (PSO) algorithm is easy to be trapped into local minima in optimizing multimodal function. Rotate surface transformation (RST) method is proposed to overcome the defect. RST method transforms local minimum to global maximum and keeps the values of the optimized function unchanged under the local minimum. A nonlinear optimal control problem regarding ferry ship is employed for examing the validity of the proposed method. Experimental results show that the method is effective.
作者
熊勇
路文初
刘继忠
胡上序
XIONG Yong;LU Wen-chu;LIU Ji-zhong;HU Shang-xu(Institute of Intelligent Information Engineering,Zhejiang University,Hangzhou 310027,China;Department of Automation,Wuhan University,Wuhan 430072,China)
出处
《控制与决策》
EI
CSCD
北大核心
2005年第4期474-477,共4页
Control and Decision
关键词
粒子群
旋转曲面变换
局部极小
非线性
最优控制
Computer simulation
Iterative methods
Nonlinear control systems
Optimization
Parameter estimation
