Neural Network to Select Dynamic Scheduling Heuristics
作者:
Henri Pierreval,
期刊:
Journal of Decision Systems
(Taylor Available online 1993)
卷期:
Volume 2,
issue 2
页码: 173-190
ISSN:1246-0125
年代: 1993
DOI:10.1080/12460125.1993.10511572
出版商: Taylor & Francis Group
关键词: neural networks;simulation;dynamic scheduling;machine learning;manufacturing;production management;back propagation;dispatching rules;réseaux de neurones;simulation;ordonnancement dynamique;production;apprentissage
数据来源: Taylor
摘要:
Frequently, several heuristic strategies are relevant to a given production scheduling problem. A choice must be made among them whenever these heuristics have different performances, and when none of them is globally better than the other ones. A neural network approach for selecting the most suited heuristic is discussed. The configuration of the shop floor, the characteristics of the manufacturing program to be carried out, and the performance criteria to optimize are presented as inputs to the first layer. The most suitable heuristic is given as output. Such a neural network is trained using a large sample of simulation results as training examples. This technique is illustrated through the dynamic scheduling problem of a simplified flow shop. A back propagation neural network finds the most appropriate dispatching rules in ninety four percent of the cases. The benefits of the neural network approach over other possible methods are discussed.
点击下载:
PDF (1021KB)
返 回