Graduate Thesis Or Dissertation
 

An Expert system for flexible manufacturing system scheduling : knowledge acquisition and development

Pubblico Deposited

Contenuto scaricabile

Scarica il pdf
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/v979v6000

Descriptions

Attribute NameValues
Creator
Abstract
  • Expert systems have been suggested as a solution for difficult problems, including FMS scheduling. As one of the aspects of artificial intelligence (AI), expert systems have achieved considerable success in recent years in medical science, chemistry, and engineering. However, building an expert system is a difficult task, the most crucial problem being that of knowledge acquisition. Obtaining expert knowledge is a difficult and time-consuming process. Moreover, since FMSs represent a relatively new technology, experts capable of FMS planning and scheduling are generally unavailable. One possible solution for this problem is to train a non-expert operator, allow the operator to practice with a simulated system and accumulate experience, and then build an expert system using the newly acquired knowledge. To this end, an interactive graphic simulation method for the effective utilization of human pattern-recognition ability is proposed. Once the required knowledge is elicited through an interactive graphic simulation model, an expert system is developed from acquired rules. The method includes an FMS simulation model, a Gantt chart-based schedule, a simulator, an expert system, and a human operator. First, an initial schedule is simulated, utilizing the expert system to determine the loading sequence and a dispatching rule. The schedule is then updated by an expert system and/or human operator with the capability of maximizing schedule objectives, while at the same time saving reasons for changes as new production rules, which are subsequently generalized and added to the expert system knowledge base. The system is implemented in Smalltalk/V on an IBM PC/AT and the implementation is based upon a detailed sample problem. It was determined that a human operator can obtain near-optimum schedules in short time periods, at the same time gaining valuable experience in use of the scheduling process. Furthermore, it was determined that this model can be a useful training device for inexperienced operators and a time-saving decision-making aid for expert schedulers.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Dichiarazione dei diritti
Publisher
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using ScandAll PRO 1.8.1 on a Fi-6770A in PDF format. CVista PdfCompressor 5.0 was used for pdf compression and textual OCR.
Replaces

Le relazioni

Parents:

This work has no parents.

In Collection:

Elementi

Thumbnail Titolo Data caricata Visibilità Azioni
file details KimJoohee1989.pdf 2017-08-16 Pubblico Scaricare