A neural network-based computer aided design tool for automotive form design

被引:6
作者
Chang, Yu-Ming [1 ]
Chen, Hung-Yuan [1 ]
机构
[1] Natl Cheng Kung Univ, Dept Ind Design, Tainan 701, Taiwan
关键词
back-propagation neural networks; Computer Aided Design (CAD); Kansei engineering; numerical definition;
D O I
10.1504/IJVD.2007.012300
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Although the functionality and performance are both important aspects in vehicle design, an automotive form is a crucial factor in determining a consumer's image perception and purchase decision. Hence, an effective tool for designing successful automotive form was suggested. Based on Kansei Engineering principles, the relationship between the profile characteristics and the consumer's image perception is established using a Back-Propagation Neural (BPN) network. A Computer Aided Design (CAD) tool, which uses the trained BPN to predict the consumer perception of an automotive profile expressed in the form of a numerical definition, is constructed using Visual Basic software. The performance of the CAD prototype tool is verified by comparing its predictions to the actual consumer perception evaluations. A good similarity is identified between the two sets of results. Therefore, the developed tool provides designers with powerful means of creating automotive designs from a consumer's image perception perspective.
引用
收藏
页码:136 / 150
页数:15
相关论文
共 30 条
[1]  
Akinori H., 1995, INT J IND ERGONOM, V15, P25
[2]  
[Anonymous], 1989, J SOC AUTOMOTIVE ENG
[3]   The new product design - a transverse approach [J].
Aoussat, A ;
Christofol, H ;
Le Coq, M .
JOURNAL OF ENGINEERING DESIGN, 2000, 11 (04) :399-417
[4]  
B~ezier P., 1972, Numerical Control Mathematics and Applications
[5]  
Cavalier S, 2004, INT J PROD ECON, V91, P165, DOI [10.1016/j.ijpe.2003.08.005, 10.1016/j.ijpe.2004.08.005]
[6]  
Chang Y. M., 1993, B JAPANESE SOC SCI D, V40, P7
[7]  
CHANG YM, 1993, J JAPAN SOC FUZZY TH, V5, P1233
[8]  
CROSS, 1994, ENG DESIGN METHODS N
[9]  
Golden R.M., 1996, Mathematical Methods for Neural Network Analysis and Design
[10]   CONJOINT ANALYSIS IN CONSUMER RESEARCH - ISSUES AND OUTLOOK [J].
GREEN, PE ;
SRINIVASAN, V .
JOURNAL OF CONSUMER RESEARCH, 1978, 5 (02) :103-123