Generating interpretable fuzzy rules for adaptive job dispatching

Cited 9 time in webofscience Cited 0 time in scopus
  • Hit : 845
  • Download : 24
Adaptive scheduling is an approach that selects and applies the most suitable strategy considering the current state of the system. The performance of an adapt ive scheduling system relies on the effectiveness of the mapping knowledge between system states and the best rules in the states. This study proposes a new fuzzy adaptive scheduling method and an automated knowledge acquisition method to acquire and continuously update the required knowledge. In this method, the criteria for scheduling priority are selected to correspond to the performance measures of interest. The decisions are made by rules that reflect those criteria with appropriate weights that are determined according to the system states. A situated rule base for this mapping is built by an automated knowledge acquisition method based on system simulation. Distributed fuzzy sets are used for evaluating the criteria and recognizing the system states. The combined method is distinctive in its similarity to the way human schedulers accumulate and adjust their expertise: qualitatively establishing meaningful criteria and quantitatively optimizing the use of them. As a result, the developed rules may readily be interpreted, adopt ed and, when necessary, modified by human experts. An application of the proposed method to a job-dispatching problem in a hypothetical flexible manufacturing system (FMS) shows that the method can develop effective and robust rules.
Publisher
TAYLOR FRANCIS LTD
Issue Date
2001-03
Language
English
Article Type
Article
Keywords

MANUFACTURING SYSTEMS; SIMULATION; MACHINE; KNOWLEDGE

Citation

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, v.39, no.5, pp.1011 - 1030

ISSN
0020-7543
URI
http://hdl.handle.net/10203/2992
Appears in Collection
IE-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 9 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0