| 基于改进能量函数的混沌神经网络JSP解法 |
| |
| 引用本文： | 李桂秋,陈志旺. 基于改进能量函数的混沌神经网络JSP解法[J]. 计算机应用研究, 2010, 27(5): 1726-1728. DOI: 10.3969/j.issn.1001-3695.2010.05.034 |
| |
| 作者姓名： | 李桂秋 陈志旺 |
| |
| 作者单位： | 1. 常州机电职业技术学院,江苏,常州,213164
2. 燕山大学,工业计算机控制工程河北省重点实验室,河北,秦皇岛,066004 |
| |
| 摘 要： | 针对传统Hopfield神经网络(HNN)在求NP类问题的解时易陷入局部最优点的不足，提出基于改进能量函数的模拟退火混沌神经网络算法。通过在Hopfield神经网络中引入混沌机制，并结合退火策略控制混沌动态，有效避免了陷入局部极小的缺陷，因此将其用于求解JSP（作业车间调度）。算法改进了表示JSP的换位矩阵，给出了包含目标函数的能量函数，保证了网络的稳态输出为全局可行解。
|
| 关 键 词： | 组合优化；作业车间调度；混沌神经网络；模拟退火；能量函数 |
Chaotic neural network method for job-shop scheduling problem based on improved energy function |
| |
| LI Gui-qiu,CHEN Zhi-wang. Chaotic neural network method for job-shop scheduling problem based on improved energy function[J]. Application Research of Computers, 2010, 27(5): 1726-1728. DOI: 10.3969/j.issn.1001-3695.2010.05.034 |
| |
| Authors: | LI Gui-qiu CHEN Zhi-wang |
| |
| Affiliation: | 1.Changzhou Institute of Mechtronic Technology/a>;Changzhou Jiangsu 213164/a>;China/a>;2.Key Lab of Industrial Computer Control Engineering of Hebei Province/a>;Yanshan University/a>;Qinhuangdao Hebei 066004/a>;China |
| |
| Abstract: | This paper presented chaotic neural network of simulated annealing(ACNN)method based on improved energy function for the shortage that the conventional Hopfield neural networks(HNN) tended to be trapped into local minima.Controled HNN with chaos mechanism and chaos dynamics by annealing strategy,therefore ACNN would not fall into local minima and was used to resolve the job-shop scheduling problem(JSP).This method improved permutation matrix of JSP and gave an energy function with objective function,which made the network steady-state output had the overall situation feasible solution. |
| |
| Keywords: | combinatorial optimization job-shop scheduling chaotic neural network simulated annealing energy function |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
