Optimising AI-driven solutions without trade-offs: predicting and preventing potential failures in sustainable innovation

The application of Generative Artificial Intelligence (AI) in early-stage design processes has emerged as a promising method for generating innovative solution concepts. However, AI-driven concepts may introduce secondary problems when implemented practically. This study proposes a systematic framework integrating Generative AI (GPT-4o), patent analysis using Retrieval-Augmented Generation (RAG), and Failure Mode and Effects Analysis (FMEA) to predict, evaluate, and mitigate potential risks. Applied to a case study on nickel recovery through froth flotation, the framework significantly enhanced the feasibility, usefulness, and sustainability of solution concepts. The research highlights the scientific contribution and practical benefits of combining Generative AI with structured risk-analysis methods for sustainable innovation.