AutoMa
Autonomous Manufacturing
AutoMa
Autonomous Manufacturing
Advancing autonomous manufacturing through AI, automation, physics, and data.
Embedded Files
Autonomous Manufacturing
Our research explores how machines can perceive, learn, reason, and collaborate with other machines and humans to enable smarter design, autonomous production, and more resilient manufacturing systems. We combine computational intelligence with real-world experimentation, leveraging advanced manufacturing technologies as a platform for innovation.
Research Areas
Research Areas
Physics-informed AI
We develop AI methods that integrate physical principles, domain knowledge, and data-driven learning by incorporating physics through model architectures, constraints, optimization objectives, prior knowledge, and hybrid reasoning frameworks to improve prediction accuracy, interpretability, and reliability.
Federated Learning
We develop privacy-preserving and distributed AI methods that enable collaborative learning across heterogeneous, multimodal data sources, organizations, and intelligent systems without centralized data sharing.
Additive Manufacturing
We advance additive manufacturing through AI-driven design, process optimization, defect characterization, quality assurance, and customized manufacturing for next-generation engineering and healthcare applications.
Robotics & Autonomous Systems
We integrate robotics, sensing, computer vision, and AI to build autonomous systems for intelligent manufacturing, inspection, and human-centered automation.
Selected Research Projects
Selected Research Projects
Physics-Informed Multiple Instance Learning for Fatigue Assessment
Physics-Informed Multiple Instance Learning for Fatigue Assessment
Develops attention-based multiple instance learning with physics-informed constraints to identify critical defects and predict the fatigue performance of additively manufactured components under complex loading conditions.
Federated Learning for Collaborative Manufacturing Intelligence
Federated Learning for Collaborative Manufacturing Intelligence
Enables privacy-preserving machine learning across distributed manufacturers by collaboratively learning from heterogeneous multimodal data without sharing proprietary information.
Multimodal Transfer Learning for Fatigue Life Prediction
Multimodal Transfer Learning for Fatigue Life Prediction
Combines manufacturing process data, XCT-derived defect information, and engineering knowledge through transfer learning to improve predictive modeling with limited labeled data.
Physics-Informed Defect Characterization
Physics-Informed Defect Characterization
Extracts physically meaningful geometric descriptors from complex three-dimensional defects to enhance AI-driven understanding of material behavior, reliability, and manufacturing quality.
News
News
2026/7: I am excited to share that I have successfully defended my PhD dissertation, "Physics-informed Hierarchical Learning for Defect Characterization and Fatigue Life Prediction in Metal Additive Manufacturing."
2026/5: Our paper, "Curvature-based defect features for nondestructive fatigue life prediction in laser powder bed fusion", has been published in Progress in Additive Manufacturing.
2026/4: I am happy to share that I will be joining Rochester Institute of Technology (RIT) this fall as a tenure-track Assistant Professor in the Department of Industrial and Systems Engineering.
2026/3: Our paper, "FedCOT: Personalized federated transfer learning with conditional optimal transport for manufacturing predictive modeling", has been published in IEEE Transactions on Automation Science and Engineering.
2025/11: Received 1st place in Additive Manufacturing (AM) Bench 2025 Measurements and Challenge Problems: S-N Curve Prediction
2025/11: Received 1st place in AM Bench 2025 Measurements and Challenge Problems: Applied Stress Prediction
2025/10: Our paper, "FedCOT: Personalized Federated Transfer Learning with Conditional Optimal Transport for Manufacturing Predictive Modeling", has been preprinted in TechRxiv.
2025/10: Received the Magna Cum Laude Award for our INFORMS Student Chapter
2024/08: Our paper, "Nondestructive fatigue life prediction for additively manufactured metal parts through a multimodal transfer learning framework", has been published in IISE Transactions.
2024/07: Received the NSF Student Travel Award for the International Solid Freeform Fabrication (SFF) Symposium!
2023/12: Received the Institute for Printed Circuits (IPC) Scholarship & Award
2023/08: Our paper, "A data-driven process-quality-property analytical framework for conductive composites in additive manufacturing", has been published in Manufacturing Letters.
2022/10: Our paper, "Defect criticality analysis on fatigue life of L-PBF 17-4 PH stainless steel via machine learning", has been published in the International Journal of Fatigue.
2022/08: Our paper, "Defects Classification via Hierarchical Graph Convolutional Network in L-PBF Additive Manufacturing", has been published in Solid Freeform Fabrication 2022.
2022/06: Our paper, "Nonparametric Bayesian framework for material and process optimization with nanocomposite fused filament fabrication", has been published in Additive Manufacturing.
2022/05: Received the ALEPSCoR-Graduate Research Scholars Program (GRSP) Award! Selected for a competitive state-funded program supporting research excellence in Alabama.
Page updated
Google Sites
Report abuse