GOALI: Fostering Democratized Manufacturing with Artificial Intelligence (AI)-Assisted Product Design and Production Planning (AI-PDPP)

About This Grant

This research focuses on developing an artificial intelligence-assisted system to improve manufacturing product design and production planning efficiencies. Manufacturing is a critical driver of economic growth and technological advancement, yet traditional product design and production planning remain resource-intensive and significantly reliant on expert knowledge. Many small manufacturers struggle to compete due to the high costs and complexity of optimizing product designs and production schedules. The integration of artificial intelligence into manufacturing has the potential to simplify these over-demanding processes. By integrating deep learning into 1. product functional analysis, 2. component design integration, and 3. constraint-aware production planning, this research seeks to help small manufacturers leverage rapid advancement of intelligent automation for scalable and adaptable production. This research supports national interests by fostering small business innovation, increasing economic competitiveness, and expanding workforce development in US manufacturing. This research also contributes to the advancement of artificial intelligence in industrial settings, enhances supply chain resilience, and promotes collaboration between industry and academia through educational and workforce training initiatives. The goal of this research is to develop an artificial intelligence-assisted product design and production planning system that improves efficiencies in product design, manufacturability assessment, and production planning. To achieve this, this project focuses on three key objectives: (i) developing structured representation learning to accelerate the product design based on functional dependencies that artificial intelligence self-learned from large volumes of historical documents and customer demands; (ii) implementing a knowledge-augmented graph encoding framework to dynamically cluster modular product families and refine scheduling strategies with significantly reduced human intervention; (iii) creating a hybrid and artificial intelligence-assisted production scheduling system that allows refined Monte Carlo algorithms to search and identify the most effective production schedules. This project looks to address fundamental questions such as: (1) how can artificial intelligence enhance design automation while maintaining manufacturability constraints? (2) how can learned constraints be effectively integrated into adaptive production planning? (3) what are the trade-offs between scalability, generalizability, and computational efficiency in artificial intelligence-assisted manufacturing systems? Through validations with real-world manufacturing data and industry collaborations, this research seekd to enable practical and adaptable manufacturing design automation and production optimization. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.