Combining Grey Relationship Analysis and Neural Network to Develop Attractive Automobile Booth Design

Area of Science:

• Design Engineering
• Artificial Intelligence
• Human-Computer Interaction

Background:

• Traditional Miryoku engineering struggles to accurately represent customer importance and can omit key information.
• Existing methods for linking customer preferences to design elements are statistically limited.

Purpose of the Study:

• To develop an AI-driven approach to enhance Miryoku engineering for improved product design.
• To address limitations in current methods for evaluating Kansei factors and mapping them to design elements.

Main Methods:

• Grey relationship analysis for prioritizing Kansei words.
• Morphological deconstruction and orthogonal design for screening design elements.
• Neural networks for mapping Kansei factors to product design elements.

Main Results:

• A novel three-level evaluation grid diagram platform was established.
• AI effectively identified key Kansei factors and representative design combinations.
• The method successfully discovered perceptually attractive product designs, validated in an automotive booth case study.

Conclusions:

• The proposed AI-integrated Miryoku engineering method significantly improves design decision-making.
• This approach enhances exhibitor design and increases attendee satisfaction.
• It offers a more accurate and efficient way to create customer-centric products.