The Potential of Generative AI for Systematic Engineering Innovation

Abstract

Generative AI offers a new path for engineering innovation by automating idea generation and evaluation. This study explores its effectiveness in addressing complex and inventive engineering challenges. Using automated multi-directional and systematic prompt generation, the paper investigates the ability of AI chatbots to autonomously generate and evaluate innovative solution ideas and concepts. Experiments with various LLMs revealed their potential to accelerate the innovation process but also highlighted limitations in generating feasible, ready-to-use solution concepts. To address these challenges, the paper proposes mixed AI innovation teams, where different generative chatbots can complement and monitor each other. This collaborative approach can improve the quality and feasibility of AI-generated solutions. Case studies demonstrate the practical application of these findings and strategies for effective human-AI collaboration in the innovation process. While generative AI holds significant promise, future research should focus on refining AI models and developing frameworks for effective human-AI interaction to ensure the practical feasibility of AI-generated engineering design solutions for inventive problems.