| 基于Hopfield神经网络求解作业车间调度问题的新方法 |
| |
| 引用本文： | 王万良,吴启迪.基于Hopfield神经网络求解作业车间调度问题的新方法[J].计算机集成制造系统,2001,7(12):7-12. |
| |
| 作者姓名： | 王万良 吴启迪 |
| |
| 作者单位： | 1. 浙江工业大学信息工程学院,浙江,杭州,310014
2. 同济大学CIMS中心,上海,200092 |
| |
| 基金项目： | 国家 8 63/CIMS主题资助项目 (863 -5 11-945 -0 0 2 )，浙江省自然科学基金 (6980 73 ) |
| |
| 摘 要： | 对作业车间调度问题的换位矩阵表示方法进行了改进，给出新的作业车间调度问题的Hopfield神经网络计算能量函数表达式，然后提出改进的Hopfield神经网络作业车间调度方法。为了避免Hopfield神经网络容易收敛到局部极小的缺点，将模拟退火算法应用于Hopfield神经网络求解，提出随机神经网络作业车间调度方法。与已有算法相比，改进算法能够保证神经网络稳态输出为可行的作业车间调度方案。
|
| 关 键 词： | Hopfield神经网络 作业车间调度 组合优化 能量函数 计算机集成制造系统 |
| 文章编号： | 1006-5911(2001)12-0007-06 |
A New Method Solving Job Shop Scheduling Problems Based On Hopfield Neural Networks |
| |
| WANG Wan-liang ,WU Qi-di.A New Method Solving Job Shop Scheduling Problems Based On Hopfield Neural Networks[J].Computer Integrated Manufacturing Systems,2001,7(12):7-12. |
| |
| Authors: | WANG Wan-liang WU Qi-di |
| |
| Affiliation: | WANG Wan-liang 1,WU Qi-di 2 |
| |
| Abstract: | This paper improved existing permutation matrix of job-shop scheduling problems. A new computational energy function of Hopfield neural networks for the job-shop scheduling problems is given. Then, the modified method solving job-shop scheduling problem based on Hopfield neural network is proposed. For avoidng Hopfield neural network convergence to local minimum value, simulated annealing algorithm is avoiding to Hopfield neural network and the production scheduling method based on stochastic neural networks is proposed. Compared with existing method, modified method can keep the steady outputs of neural networks as feasible solution for job-shop scheduling problem. |
| |
| Keywords: | neural networks job-shop scheduling combinatorial optimization computational energy function |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
