Development of design system for product pattern design based on Kansei engineering and BP neural network

Chen, Daoling; Cheng, Pengpeng

doi:10.1108/ijcst-04-2021-0044

Cited by 27 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above two studies were limited to a combination of existing design component options and lacked the possibility of design changes beyond existing components. Chen and Cheng (2022) used a backpropagation neural network for the perceptual design of T-shirt patterns. Through the relationship between perceptual adjectives and pattern features, suggestions for the selection of pattern design features were given.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Applying Kansei engineering to the design of headwear pieces with traditional shape features

Tsai

Hsu²

2022

IJCST

View full text Add to dashboard Cite

PurposeIt is desirable that shape appeal in craft design takes people's cultural and emotional influencers into consideration. Five Royal Lords worship, prevalent in the southwest coastal part of Taiwan and a source of religious and spiritual support to the local residents, offers such a shape appeal. This study takes the design of Taiwan's cultural handicrafts as the main point of discussion and uses Kansei engineering with semantic technique to promote the linkage between shape and the mental image of the Five Royal Lords' headwear. There are only two types of traditional headwear for the Five Royal Lords: the Imperial Crown and Lord Crown, despite the different personal characteristics of the five deities. This study aims to design a crown for each that matches their individuality.Design/methodology/approachIn the first stage of the research process, the Kawakita Jiro method was used to arrive at appropriate descriptions representative of the deities' individuality. Fuzzy set theory was then applied to convert the relationship between the representative descriptions and headwear shape features into a quantitative one, after which the headwear could be redesigned and validated.FindingsThe study results show that: (1) analysis of the relationship between shape features and representative deity descriptions offered guidance to the redesign. (2) A method combining fuzzy theory and description terms could generate quantitative data that helped to provide design suggestions and result validation, supporting both scientific rationality and designers' sensibility. (3) The validation revealed that the redesigned headwear was better than the original headwear.Originality/valueThe study successfully established a design and development process featuring collaboration by folklore experts, designers, craftspeople and worshippers, and helping to promote new cultural product development. The success of the research process can serve as a reference to the development of other different products with shape features.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 99%

Applying Kansei engineering to the design of headwear pieces with traditional shape features

Tsai

Hsu²

2022

IJCST

View full text Add to dashboard Cite

show abstract

“…The CFD solving process generally consists of three main parts: pre-processing, solving and post-processing, of which the STAR-CCM+ solving process can be represented by the following flow chart [7][8]. As shown in figure 1.…”

Section: The Solution Process Of the Cfdmentioning

confidence: 99%

Design of an All-electric Bus Cooling System Incorporating Computational Fluid Dynamics

2022

KME

View full text Add to dashboard Cite

With the emphasis on renewable energy and environmental protection, new energy vehicles are gradually entering the social space and electric vehicles are once again moving to new heights. The aim of this paper is to investigate the design of a cooling system for a purely electric bus incorporating computational fluid dynamics. This paper follows the principle of "determine the heat source distribution of the prototype -calculate the temperature rise of the prototype -design an optimised cooling structure -analyse the cooling effect -propose the design of the prototype cooling structure". This paper studies the temperature rise and cooling of the prototype, focusing on the effect of different cooling structures on the temperature rise of the prototype. Based on the heat transfer, a finite element model of the engine is established and the losses and heat source distribution of the prototype are calculated by combining empirical equations and MAP diagrams of the engine losses. The heat transfer process of the engine is investigated, including the heat transfer process within and between the components of the prototype in contact with each other, and the convective heat transfer process between the prototype and the fluid contact surface. Based on the CFD (Computational Fluid Dynamics) method, the flow and temperature fields of the physical air-cooled prototype are calculated using the existing CFD mathematical model, and the influence of the flow field of the prototype heat exchanger ventilation duct on the engine temperature rise is analysed. A forced air cooling solution for the prototype was proposed to determine the structure of the vents, the location of the ventilation holes and the size of the cooling fan. The effect of forced air cooling on the temperature rise of the prototype is compared with the effect of natural air cooling. A parallel water jacket should be designed and its structure optimised in order to compare the effect of the water jacket on the temperature rise of the prototype before and after optimisation. Finally, all studies are combined to provide reference recommendations for the design of the prototype cooling structure.

show abstract

“…Cheng et al 19 proposed a prediction model based on BP neural network, it effectively solves the matching problem between modeling features and perceptual images in modeling image research, assist designers to quickly identify key modeling features and perceptual image targets, which improves the scientificity of design decision-making. Chen and Cheng 20 developed a product pattern design system by combining Kansei engineering theory with BP neural network. At present the neural network algorithm has been used to realize the intelligent and personalized recommendation of product design, but the BP neural network model has not been optimized.…”

Section: Introductionmentioning

confidence: 99%

A perceptual image prediction model of professional dress style based on PSO-BP neural network

Chen

Cheng

2023

Journal of Engineered Fibers and Fabrics

Self Cite

View full text Add to dashboard Cite

In order to understand consumers’ cognition of clothing style and design clothing products more in line with people’s emotional needs, a garment style perceptual image prediction model based on PSO-BP neural network was constructed by taking professional dress as an example. Firstly, the professional dress samples were screened and the style design elements were deconstructed and coded. The Kansei engineering theory and factor analysis method were used to determine the representative adjectives, so as to reduce the cognitive dimension of the target users for the style characteristics and perceptual image of the dress. Then, using the sample style design element code as the input layer and the user’s perceptual image evaluation score as the output layer, the PSO-BP neural network’s perceptual image prediction model for professional dress styles is constructed. Finally, the sample data were input into the PSO-BP model, BP neural network and GA-BP model for simulation and calculation, and the error analysis of the results proved that the PSO-BP prediction model is effective and advanced. Designers can use this model to quickly transform customers’ perceptual needs with dress style design elements, so as to improve the scientificity of design decision-making and better meet customer needs.

show abstract

Development of design system for product pattern design based on Kansei engineering and BP neural network

Cited by 27 publications

References 24 publications

Applying Kansei engineering to the design of headwear pieces with traditional shape features

Applying Kansei engineering to the design of headwear pieces with traditional shape features

Design of an All-electric Bus Cooling System Incorporating Computational Fluid Dynamics

A perceptual image prediction model of professional dress style based on PSO-BP neural network

Contact Info

Product

Resources

About