Understanding the Impact of Applying Large Language Model in Engineering Design Education

Abstract In the contemporary era of engineering education, the integration of Large Language Models (LLMs), offers a novel perspective on enhancing the design process. This study investigates the impact of ChatGPT-3.5 on mechanical engineering design education, focusing on concept generation and detailed modeling. By comparing outcomes from AI-assisted groups to those without AI assistance, our research reveals that AI significantly broadens concept generation diversity but also introduces bias for existing popular designs. Additionally, while AI aids in suggesting functions for CAD modeling, its textual nature and the occurrence of unreliable responses limit its usefulness in detailed CAD modeling tasks, highlighting the irreplaceable value of traditional learning materials and hands-on practice. The study concludes that AI should serve as a complement to, rather than a replacement for, traditional design education. Additionally, it highlights the necessity for further specialization within AI to enhance its effectiveness.