摘要
Hopfield网络 (HNN)中引入混沌机制 ,首先在混沌动态下粗搜索 ,并利用退火策略控制混沌动态退出和逆分岔出现 ,进而HNN梯度优化搜索 ,提出了一种具有随机性和确定性并存的优化算法 .对经典旅行商 (TSP)的研究 ,表明算法具有很强的克服陷入局部极小能力 ,较大程度提高了优化、时间和对初值的鲁棒性能 ,同时给出了模型参数对性能影响的一些结论 .
This paper presents a self organization optimization algorithm,which combines stochastic with deterministic property to introduce chaos mechanism into Hopfield neural network(HNN) to coarsely search the optimum under chaotic dynamics and control the chaotic dynamics by annealing strategy to perform inverse bifurcation and disappear.After that,the gradient property of HNN is used to reach stable point.Simulation results about two typical TSP problems show that such an algorithm,which is robust with initial states,can avoid getting stuck in local minima and has better convergence property as well as time property.Moreover,some conclusions about the effect of parameters on the model are summed up.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2000年第1期139-142,共4页
Control Theory & Applications
基金
国家自然科学基金!( 696840 0 1)
国家攀登计划资助项目
