Job-shop问题基于RBF网络的自学习算法  

The Self-learning Algorithm Based on Radial Basis Function for Job-shop Problem

作　　者：李国昊[1] 李文超[2] 

机构地区：[1]江苏大学管理学院,江苏镇江212013 [2]江苏大学汽车与交通工程学院,江苏镇江212013

出　　处：《工业工程与管理》2014年第6期105-109,116,共6页Industrial Engineering and Management

基　　金：国家自然科学基金资助项目(71401082);江苏省高校自然科学研究项目(3KJB460005)

摘　　要：通过对Job-shop问题分析,在逐步添加约束到有向图模型来获取可行调度方案基础上,提出一种具备自动学习功能智能算法。设计了可互换工序对4种选取函数,并以此作为网络输入构建了基于RBF的神经网络以实现对可互换工序对选取。利用最小均方算法对网络权重进行训练,经过对更新过的样本进行再学习后,网络选取可互换工序对的准确度得以提高,使算法具备自学习能力。数值仿真结果表明所提算法对于大规模Job-shop问题求解存在较好效果,具较好的应用价值。Through the analysis of job-shop problem（JSP）,an intelligent algorithm with self learning ability is presented on the basis of obtaining the feasible scheduling by adding constraints to its directed graph model step by step. A neural network based on radial basis function is constructed to choose the interchangeable operations and there are 4 functions being designed which are used as its inputs. The training of network^s parameters is realized by the least-mean- square algorithm and its continual learning ability improves the selection accuracy of the network for the interchangeable operations. The results of is computation shows that the algorithm performed well for Job-shop problem and there is some applied value for it.

关 键 词：车间作业调度 自学习 有向图模型 可互换工序对 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]