Masters Theses
Abstract
"This thesis presents case-based reasoning approach for estimating the cost and modeling cost uncertainty of a new product in the concept selection stage. Case-based reasoning (CBR) is an approach which uses old cases/experiences to understand and solve new problems. The CBR approach consists of creating a knowledge-base (or database) containing past cases (products), defining a new case (concept), retrieving cases similar to the new case, and adjusting the solution of the retrieved cases to the new case. The first paper compares case-based reasoning, in studying the effects of varying design attribute specifications on cost estimation accuracy and cost distribution reliability. Case-based reasoning with cost estimation is compared with three methods: analogy-based cost estimation, case-based reasoning without cost adjustment, and regression analysis. Four automobile concepts with similar performance attribute specifications but varying design attribute specifications are defined and the comparison is made using leave-one-out cross-validation technique to a knowledge-base of 345 automobiles. The second paper further establishes case-based reasoning with cost adjustment by studying the optimum number of design attributes for specifying a concept. The results show that case-based reasoning and with cost adjustment performed best for cost estimation accuracy and cost distribution reliability when one design attribute is specified for the concept in addition to performance attributes"--Abstract, page iv.
Advisor(s)
Takai, Shun
Committee Member(s)
Liou, Frank W.
Du, Xiaoping
Department(s)
Mechanical and Aerospace Engineering
Degree Name
M.S. in Mechanical Engineering
Publisher
Missouri University of Science and Technology
Publication Date
Fall 2010
Journal article titles appearing in thesis/dissertation
- Comparison of cost estimation and cost uncertainty modeling approaches
- Optimum number of design attributes for cost estimation and cost uncertainty modeling
Pagination
x, 78 pages
Note about bibliography
Includes bibliographical references (pages 73) and index (pages 74-77).
Rights
© 2010 Karan Banga, All rights reserved.
Document Type
Thesis - Open Access
File Type
text
Language
English
Subject Headings
Automobiles -- DesignCase-base reasoningManufacturing processes -- Dosts -- EstimatesRegression analysis
Thesis Number
T 9717
Print OCLC #
722441756
Electronic OCLC #
745912393
Recommended Citation
Banga, Karan, "A comparison of case-based reasoning and regression analysis approaches for cost uncertainty modeling" (2010). Masters Theses. 4986.
https://scholarsmine.mst.edu/masters_theses/4986