Weaving Replicability, Predictability, and Renewability Into Color Design Knowledge Flow for Emotional Bionic Color Design

Abstract

Traditional color design often encounters problems such as extraction confusion, tangled choice, and empirical judgment, which restrict the replicability, predictability, and renewability of color knowledge. Bridging this gap, this study proposed an integrated bionic knowledge graph (BioKG), response surface methodology (RSM), and multi-objective firefly algorithm (MOFA) framework aiming to establish a systematic design knowledge flow for emotional bionic color design. Firstly, BioKG integrated semantic associations among natural colors, entities, and human emotions, ensuring the structuring and replicability of color knowledge. Secondly, the experimental color parameters were determined through Box–Behnken design, and predictive mapping between the color parameters and the emotional responses was achieved by using RSM. Furthermore, MOFA with a soft constraint was designed to optimize the color scheme of multi-emotion coupling. Subsequently, the proposed design knowledge flow was examined through a case study on the exterior color of new energy vehicles (NEVs). Results indicate that color knowledge is replicated in BioKG, predicted in RSM, and renewed in MOFA, thereby enabling the rapid generation of color schemes. User evaluation further suggested improved effectiveness and creative performance of each module compared with traditional processes in various task scenarios, such as product innovation, event marketing, and brand promotion. Ablation study also suggested that BioKG enabled replicable knowledge, RSM reduced design prediction costs, and MOFA supported scheme renewability under multi-objective optimization. Application insights based on NEVs exterior–interior color comparison suggest that the workflow is reusable across adjacent contexts under consistent constraints, while the evidence remains domain-bounded. Overall, this offers a systematic solution from the perspective of knowledge flow for emotion-driven color design within the NEVs application scope.