Intelligent optimization model for computerized fabric-cutting system

Pao Yue-kong Library Electronic Theses Database

Intelligent optimization model for computerized fabric-cutting system

 

Author: Wong, Wai-keung
Title: Intelligent optimization model for computerized fabric-cutting system
Degree: Ph.D.
Year: 2002
Subject: Hong Kong Polytechnic University -- Dissertations
Textile fabrics -- Cutting -- Data processing
Garment cutting -- Data processing
Department: Institute of Textiles and Clothing
Pages: xxii, 353 leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1667773
URI: http://theses.lib.polyu.edu.hk/handle/200/1691
Abstract: Searching for an optimal and feasible production planning and control solution is significant for the apparel manufacturers in a dynamic apparel market. The optimization problems in apparel manufacturing process have characteristics that cannot be solved in polynomial time. Emulating and improving the decision-making process of the industrial experts under different manufacturing environments will become feasible by developing an intelligent optimization model. Since the late 80s, computerized fabric-cutting system has became popular in apparel manufacturing process. The performance of a cutting system, which is generally neglected by most manufacturers, is a significant factor on the smoothness of operation of sewing lines and hence the overall efficiency of an apparel manufacturing plant. In this thesis, three problems relating to the optimization of a computerized fabric-cutting system: selection of system configuration before installation, table-planning before production, and production control during production (which significantly influence the productivity and potentiality of a computerized cutting system) were addressed and handled by an intelligent optimization model. The formulation of the intelligent optimization model for computerized fabric-cutting system (IOMCFS) used in this research consists of a Queuing model, a Hybrid Flowshop Table-Planning (HFTP) model, and a Fuzzy Capacity-Allocation (FCA) model which is based on two artificial intelligence techniques (Genetic Algorithms and Fuzzy Logic) and one operation research theory (Queuing Theory). Three experiments were designed to demonstrate the performance of the proposed intelligent model, hi each experiment, actual production data were collected from three different types of manufacturing environments which operate small-sized, medium-sized, and large-sized production orders in the cutting rooms of local apparel manufacturing companies. In order to evaluate the performance of the proposed techniques, the experimental results generated by the three models of IOMCFS were compared with industrial practice. The experimental results indicated that the performance of the HFTP and FCA model were better than that of industrial experts. In these experiments, the author validates the applicability of the Queuing model on system configuration decision making; the results demonstrated that the solutions generated by the Queuing model were very close to those derived by the HFTP model. The results also indicated that the IOMCFS could emulate the decision-making process of the industrial experts and apparel manufacturers to achieve the optimization of a computerized fabric-cutting system.

Files in this item

Files Size Format
b16677730.pdf 13.65Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information