Project # 88
Edge AI and LLM-empowered Monitoring and Process Optimization of Additive Manufacturing

Team Lead:	Amogh Modgekar Desai
Other Team Members:	Armaan Nalli \| Tyler Nguyen
Faculty Advisor(s):	Dr. Chen Kan
Department:	IMSE
Project Type:	REU
Title:	Edge AI and LLM-empowered Monitoring and Process Optimization of Additive Manufacturing
Abstract:	Although widely adopted, additive manufacturing (AM) remains prone to process uncertainties that lead to defects and compromise product quality. In the literature, sensor-based monitoring has been developed to detect uncertainty-induced anomalies, with subsequent optimization strategies to adjust process parameters for defect mitigation. However, existing approaches face two key limitations: 1) most are implemented on centralized servers or cloud platforms, requiring extensive data transmission that introduces latency and cybersecurity risks; and 2) most operate as black-box systems, yielding results with limited interpretability and offering little support for human-in-the-loop decision-making. To fill the gaps, this project develops a new framework that integrates edge AI for real-time AM anomaly detection with large language models (LLM) for interpretable guidance to human operators for process optimization. The framework has been implemented on a wire-arc additive manufacturing (WAAM) system.
Poster:	View Poster #88 (PDF)
Judges Scoring:	Submit Evaluation (judges only)

Project # 88Edge AI and LLM-empowered Monitoring and Process Optimization of Additive Manufacturing