在运用Hopfield神经网络求解优化方面问题的同时 ,引进GCM混沌神经网络 ,对求解过程进行了改进。通过混沌遍历 ,可使Hopfield网络在整个相空间进行搜索 ,从而避免网络在运行过程中陷入局部极小值。通过对一个物流配送的实例进行实验 ,结果显示Hopfield网络的寻优特性获得了较大改进 While using Hopfield neural network to solve the problem of optimization, the introduction of GCM chaotic neural network improves the solution process. Through chaotic traversal, the Hopfield network can search the entire phase space to avoid the network from falling into a local minimum during operation. Through an example of a logistics distribution, the results show that the optimization characteristics of Hopfield network have been greatly improved