Abstract
The automotive industry is undergoing rapid transformations driven by technological advancements, sustainability concerns, and evolving consumer preferences. Integrating Artificial Intelligence (AI) and optimization techniques in automotive styling design education is essential for modernizing teaching methodologies and enhancing student learning. This investigation presents a Refined Honey Badger Optimization (RHBO)-based framework to refine automotive design processes, providing students with an AI-driven approach to styling refinement. The examination begins with data pre-processing, which includes min-max normalization, and t-Distributed Stochastic Neighbour Embedding (t-SNE) was employed for feature extraction. The RHBO algorithm optimizes these features to enhance structural coherence, aerodynamic efficiency, and aesthetic appeal. The methodology allows students to interact with dynamically adjusted design parameters, improving their understanding of AI-driven styling. Experimental validation demonstrates an improvement in alignment with industry trends (88%), a reduction in iteration time (85%), and an increase in load distribution (87%) compared to the traditional manual technique. The results indicate that integrating RHBO-based design refinement significantly enhances both creativity and functionality, offering an effective learning tool for automotive design education. By incorporating bio-inspired optimization techniques into the curriculum, this investigation bridges the gap between conventional design practices and AI-driven methodologies, ensuring that students acquire industry-relevant skills. Future research will focus on real-time interactive AI-assisted platforms to further enhance engagement and adaptability in automotive styling education.
Get full access to this article
View all access options for this article.