An evaluation and design method for Ming-style furniture integrating Kansei engineering with particle swarm optimization-support vector regression

被引:16
作者
Fu, Lei [1 ]
Lei, Yiling [1 ]
Zhu, Ling [1 ]
Lv, Jiufang [1 ,2 ]
机构
[1] Nanjing Forestry Univ, Coll Furnishings & Ind Design, Nanjing 210037, Peoples R China
[2] Nanjing Forestry Univ, Coinnovat Ctr Efficient Proc & Utilizat Forest Res, Nanjing 210037, Peoples R China
关键词
Design evaluation; Ming-style furniture; User emotional requirements; Kansei engineering; Game theory; Particle swarm optimization; Support vector regression; PRODUCT DESIGN;
D O I
10.1016/j.aei.2024.102822
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional Kansei Engineering (KE) often relies heavily on the designers' prior knowledge to study user emotional requirements. However, cognitive differences between designers and users can result in Ming-style furniture failing to gain consumer acceptance when introduced to the market. To enhance the objectivity and accuracy of the design process, this study proposes an improved evaluation and design method that integrates Game Theory (GT) with Particle Swarm Optimization-Support Vector Regression (PSO-SVR) based on KE. This approach aims to identify truly critical emotional requirements and accurately translate them into design characteristics. First, emotional requirements are collected, and the product form is analyzed and deconstructed. Next, the Spherical Fuzzy Analytic Hierarchy Process (SFAHP) and Criteria Importance Through Intercriteria Correlation (CRITIC) are employed to calculate the subjective and objective weights of emotional requirements, respectively. Then, GT is used to find the optimal equilibrium weights to select the critical emotional requirements. Finally, an intelligent evaluation system is built using a combination of PSO and SVR to determine the relationship between critical user emotional requirements and product design characteristics, thereby identifying the optimal design parameters for Ming-style furniture. The results reveal that the most critical user emotional requirements are "concise", "ornate", and "dynamic". In addition, the user evaluation results of the optimal design closely match the system's predicted outcomes, validating the feasibility and advancement of the proposed method. Compared to most KE studies that focus solely on expert knowledge, this study better balances the subjective experience of designers with objective information of users, improving the accuracy of product design decisions and helping designers develop innovative products that align closely with user requirements.
引用
收藏
页数:14
相关论文
共 50 条
[1]   Wooden Furniture Design Based on Physiological- Psychological Measurement Technology and Kansei Engineering: Taking Ming-style Chair as an Example [J].
Lei, Yiling ;
Fu, Lei ;
Zhu, Ling ;
Lv, Jiufang .
BIORESOURCES, 2024, 19 (03) :6304-6324
[2]   Study of tourism flow forecasting based on a seasonally adjusted particle swarm optimization-support vector regression model [J].
Weng, Gangmin ;
Li, Lingyan .
Journal of Information and Computational Science, 2015, 12 (07) :2747-2757
[3]   Integrating Support Vector Regression with Particle Swarm Optimization for numerical modeling for algal blooms of freshwater [J].
Lou, Inchio ;
Xie, Zhengchao ;
Ung, Wai Kin ;
Mok, Kai Meng .
APPLIED MATHEMATICAL MODELLING, 2015, 39 (19) :5907-5916
[4]   A hybrid Kansei engineering design expert system based on grey system theory and support vector regression [J].
Wang, Kun-Chieh .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (07) :8738-8750
[5]   Parameters Optimization of Support Vector Regression Based on Immune Particle Swarm Optimization Algorithm [J].
Wang, Yan ;
Wang, Juexin ;
Du, Wei ;
Zhang, Chen ;
Zhang, Yu ;
Zhou, Chunguang .
WORLD SUMMIT ON GENETIC AND EVOLUTIONARY COMPUTATION (GEC 09), 2009, :997-1000
[6]   Immune Particle Swarm Optimization for Support Vector Regression on Forest Fire Prediction [J].
Wang, Yan ;
Wang, Juexin ;
Du, Wei ;
Wang, Chuncai ;
Liang, Yanchun ;
Zhou, Chunguang ;
Huang, Lan .
ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 2, PROCEEDINGS, 2009, 5552 :382-+
[7]   Model selection of support vector regression using particle swarm optimization algorithm [J].
Yang, HZ ;
Shao, XG ;
Chen, G ;
Ding, F .
DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES A-MATHEMATICAL ANALYSIS, 2006, 13 :1417-1425
[8]   Particle Swarm Optimization Based Support Vector Regression for Blind Image Restoration [J].
Dash, Ratnakar ;
Sa, Pankaj Kumar ;
Majhi, Banshidhar .
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2012, 27 (05) :989-995
[9]   Particle Swarm Optimization Based Support Vector Regression for Blind Image Restoration [J].
Ratnakar Dash ;
Pankaj Kumar Sa ;
Banshidhar Majhi .
Journal of Computer Science & Technology, 2012, 27 (05) :989-995
[10]   Particle Swarm Optimization Based Support Vector Regression for Blind Image Restoration [J].
Ratnakar Dash ;
Pankaj Kumar Sa ;
Banshidhar Majhi .
Journal of Computer Science and Technology, 2012, 27 :989-995