【摘要】 采用具有瞬态混沌特性的神经网络 (TCNN)解 Job- shop调度问题。利用神经元的自抑制反馈产生混沌动态 ,其随机搜索能力有效地避免了传统 Hopfield神经网络 (HNN)极易陷入局部极小的缺陷 ;同时利用一时变参数控制混沌行为 ,使网络在经过一个短暂的倍周期倒分岔后逐渐趋于一般的神经网络 ,从而收敛到一个最优或近似最优的稳定平衡点。仿真结果表明 ,该网络解 Job- shop调度问题比 HNN具有更强的全局搜索能力和寻优能力 ,并具有更高的搜索效率。更多还原

【Abstract】 Job shop schedule problems are solved by a neural network model with transient chaos(TCNN). Compared with the conventional Hopfield neural network(HNN),TCNN would not be stuck into local minima by introducing chaos which is generated by negative self feedback into HNN. With a time variant parameter to control the chaos,TCNN goes through an inverse bifurcation process and gradually approaches to HNN which converges to a stable equilibrium point. Numerical simulations of two Job shop schedule problems show that TCNN has higher ability of searching for globally optimal or near optimal solution to Job shop schedule problems than HNN and higher efficiency of searching.更多还原