Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/182140
Title: A NEURO-FUZZY EXPERT SYSTEM TO SUPPORT PRODUCT MANUFACTURABILITY EVALUATION
Authors: LIU YADOIN
Issue Date: 1997
Citation: LIU YADOIN (1997). A NEURO-FUZZY EXPERT SYSTEM TO SUPPORT PRODUCT MANUFACTURABILITY EVALUATION. ScholarBank@NUS Repository.
Abstract: It is widely recognized that the design process commits about 70 percent of the total life cycle cost of a product. Concurrent engineering and design for manufacturing (DFM) are the two commonly employed technologies to achieve reduction of production cost and production time while improving the quality of products. Research emphases have been focused on characterizing the design process and integrating design with manufacturing. The present research is motivated by the lack of computational tools to support decision making in design evaluation. In this project, the concept of hierarchical decision making is introduced, which is common in the DFM environment and the design process itself. The higher level decision making, e.g. manufacturability evaluation, is characterized by making decisions based on relatively uncertain, incomplete and abstract information. On the other hand, more detailed and precise information is needed for lower level decision making, e.g. production cost and production time estimation. This thesis describes a general hierarchical design evaluation framework to facilitate hierarchical decision making in the design process. The concept of comprehensive manufacturability index (CMI) is introduced to represent the overall assessment of product manufacturability. The CMI is expressed by a fuzzy variable that takes on fuzzy values or fuzzy subsets, namely very good, good, fair, poor and very poor. A neuro-fuzzy expert system prototype is implemented to derive a CMI from three different perspectives of production life cycle, namely production cost, production time and manufacturing capacity. Particularly, manufacturing resources in specific workshop or enterprise are taken into account to evaluate the overall manufacturability. This enables better decision making in evaluating a product design. The developed neuro-fuzzy expert system has been applied to injection moulded plastic product design. The results show that the developed system is able to provide the designers with appropriate evaluation on product manufacturability and give feedbacks and/or suggestions to guide the redesign direction.
URI: https://scholarbank.nus.edu.sg/handle/10635/182140
Appears in Collections:Master's Theses (Restricted)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
b20171456.pdf3.67 MBAdobe PDF

RESTRICTED

NoneLog In

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.