City University of Hong Kong
DSpace
 

CityU Institutional Repository >
3_CityU Electronic Theses and Dissertations >
ETD - Dept. of Manufacturing Engineering and Engineering Management  >
MEEM - Doctor of Philosophy  >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2031/4515

Title: Case-based reasoning for computer-aided inspection process planning
Other Titles: An li tui li fa shi dian nao fu zhu wei jian gong xu gui hua de yan jiu
案例推理法式電腦輔助維檢工序規劃的研究
Authors: Wong, Francis Seung Yin (黃尚賢)
Department: Dept. of Manufacturing Engineering and Engineering Management
Degree: Doctor of Philosophy
Issue Date: 2005
Publisher: City University of Hong Kong
Subjects: CAD/CAM systems
Production planning -- Data processing
Notes: CityU Call Number: TS183.3.W66 2005
Includes bibliographical references (leaves 164-175)
Thesis (Ph.D.)--City University of Hong Kong, 2005
xi, 249 leaves : ill. ; 30 cm.
Type: Thesis
Abstract: Success in the implementation of computer-integrated manufacturing (CIM) or concurrent engineering (CE) depends, inter alia, on the degree to which the planning of manufacturing operations can be automated through computerization by computer-aided process planning (CAPP). Review of literature on CAPP has revealed that relatively little research work has been conducted in inspection process planning which, despite its industrial importance, has not yet received due attention. Although much of the inspection process carried out in industry continues to be conducted using conventional metrological equipment, most previous work on computer-aided inspection process planning (CAIPP) has been directed towards inspection operations performed on coordinate measuring machines (CMM). Recent literature has reported that case based reasoning (CBR) can be applied to obtain significant improvements in the development of various CIM sub-systems particularly in process planning and control, except in the context of CAPP and especially to CAIPP. This research study addresses these gaps. Since, this is the first ever serious research effort in the area of inspection process planning, this thesis starts with the more tractable problem of planning the inspection of parts consisting of prismatic, cylindrical and free-formed features. The overall research aim is to develop the methodology and solution to CBR for CAIPP problems in CIM environment. This thesis firstly describes the development of a GCAPPSS (Generic Computer-aided Process Planning Support System) which is a new strategy for CAPP development and is capable to serve a common platform for CAPP in different domains and tasks. GCAPPSS helps to eliminate the “Island of Automation” in CAPP, overlap of work and duplication of effort. An environment for automated inspection process planning is developed by adapting this GCAPPSS as front end platform. Secondly it presents a structured representation of inspection features through a new MASG (Multi-Attributed Spatial Graph) and method that enables the automatic identification and recognition of inspection features which include prismatic, cylindrical and free-formed features. The thesis focuses on non-CMM based inspection process planning of engineering parts that include free-formed surface. The thesis then puts forward a “filter” approach that facilitates the identification of necessary inspection features automatically. A set of eleven filters capable of handling general engineering applications is reported. This is followed by a new graph representation technique “PLTFG” (Parametric-list Technological Feature Graph) that is able to recognize the associated inspection constraints in the structural representation of inspection features. It presents a formal case representation scheme for primitive inspection case through the PLTFG for “low level inspection case” of a CBR system as well as sub-case representation scheme for “high level inspection case” of a CBR system. The thesis finally describes the framework of CBR System for CAIPP as well as a new approach to recall case developed through the technological feature recognition. The various CAIPP sub-systems and modules are developed and tested. The results obtained show clearly that a CBR based CAIPP system is feasible and, with further development, is suitable for application in industrial environment. The thesis contributes fundamental knowledge, methodology and solution for CBR based CAIPP.
Online Catalog Link: http://lib.cityu.edu.hk/record=b1988765
Appears in Collections:MEEM - Doctor of Philosophy

Files in This Item:

File Description SizeFormat
fulltext.html159 BHTMLView/Open
abstract.html159 BHTMLView/Open

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

 

Valid XHTML 1.0!
DSpace Software © 2013 CityU Library - Send feedback to Library Systems
Privacy Policy · Copyright · Disclaimer