Intelligent & Autonomous Manufacturing
Our research develops data-driven and physics-informed approaches to enable intelligent, adaptive, and autonomous manufacturing systems. By integrating multimodal sensing, artificial intelligence, machine learning, physics-based modeling, digital twins, and advanced data analytics, we transform manufacturing data into actionable insights for real-time process monitoring, anomaly detection, quality prediction, and autonomous decision-making. Through these efforts, we aim to develop self-aware, adaptive, resilient, and self-improving manufacturing systems capable of continuously learning from process data and autonomously optimizing manufacturing performance.
Our current work explores:
- Multimodal sensing and sensor fusion for intelligent manufacturing
- AI/ML-enabled real-time process monitoring, anomaly detection, and quality prediction
- Physics-informed AI and digital twins for process prediction and optimization
- Autonomous decision-making, adaptive control, and self-optimizing manufacturing systems
- FT. Zohora, J. Jeon, S. Akin, "Data-driven prediction of cold spray additive manufacturing via CFD-guided machine learning", Results in Engineering,, 2026. [Link]
- H. Lee, C. Han, T. Gabor, Y. Sim, S. Akin, MBG Jun, Y. Jeon, J. Lee, "Cold spray-based secure and unique product identification with neural encoding: A full-stack framework for scalable authentication in manufacturing", Journal of Intelligent Manufacturing, 2026. [Link]
- J. Lee, S. Akin, Y. Sim, H. Lee, E. Kim, J. Nam, K. Song, MBG Jun, "A stethoscope-guided interpretable deep learning framework for powder flow diagnosis in cold spray additive manufacturing", Manufacturing Letters, 2024. [Link]