Speaker
Description
Current methods in product development and industrialization are rigid, resource-intensive, and reliant on expert intuition. Integrating Artificial Intelligence (AI), particularly Generative AI (GenAI), with combinatorial optimization presents significant potential to address these challenges. Such integration can enable data-driven, automated decision-making across the product lifecycle—from early-stage design and optimization to scale-up, transitioning a product or process from the development stage into full-scale manufacturing.
Despite this potential, effective application in engineering domains requires the incorporation of domain-specific knowledge, the handling of complex constraints, and the delivery of actionable outcomes. This work presents a preliminary analysis of how GenAI can be combined with optimization techniques to support complex engineering design and industrialization tasks. It includes a critical review of integration strategies, such as embedding engineering constraints, leveraging expert input to guide AI exploration, and translating AI-generated solutions into accessible and effective decisions. We conclude with a discussion on the role of these technologies in engineering workflows, evaluating their suitability for full automation versus their use as co-pilot systems in hybrid human–AI teams.
