IMS Laboratory

Projects

National Science Foundation (NSF), CMMI-Advanced manufacturing, MRI: Development of Metal 3D Printing Research Instrument with In-situ Characterization and Closed-loop Control Capability, (#2510152) PI lead, Current, 2025-2029
FUEL SEED subrecipient to LSU NSF-2315727, Advancing Metal Additive Manufacturing Technologies and Workforce Development for Sustainable Manufacturing and Energy Transition at Louisiana, PI, Current, 2025-2026.
Board of Regents Support Fund (BoRSF), Research Competitiveness Subprogram (RCS), Energy Driven In-situ Alloying and Multiphysics Control Pathways, PI, Current, 2024-2027.
Dixie Iron Works, Large Format Metal Additive Manufacturing via Robots, Co-PI, Current, 2024-2027.
Louisiana Transportation Research Center, TIRE: Using Metal 3D Printing to Increase Quality and Resource-efficiency of Construction Materials, PI, 2024-2025. (Completed)
Board of Regents Support Fund (BoRSF) for Cost Share NSF #OIA-1946231, LAMDA Seed Track 1: Binder Jetting Metal Additive Manufacturing of Stainless Steel - Physical Property Quantification and Machine Learning, PI, 2024-2025. (Completed)

Research Outline

[1] Advanced Manufacturing System

Robotic wire laser/arc additive manufacturing automated process - sensing - property relationships

• We have developed an in-process sensing system integrated with a Wire Laser Directed Energy Deposition (DED) to monitor the molten pool dimensional and temperature profiles

• It investigates interrelated process-sensing-geometry-microstructure relations based on learning from experiments that will enable improved quality control along with consistent overall surface, geometric and microstructural features of the part.

Operating Robot with Virtual Platform Training for Resilient Manufacturing Processes

It aims to create a virtual robotic AM platform with Unity and ROS2 real-time communication and RL of action policy for real manufacturing tasks and multi-robot collaboration. The key ideas are (1) developing the virtual platform at Unity and physical AM system with combinatorial in-process visual and thermal sensing; and (2) utilizing interface “AI environment” to describe the digital twin as a virtual environment for accelerated learning, as well as simulation of materials deposition, path planning, and multi-robot collaboration to increase efficiency and resilience of manufacturing

[2] AI & Materials Deposition

Physics-informed machine learning for shape memory alloy design and porosity analysis for the LPBF process

• The physics-informed feature engineering approach has been shown to enable ML to predict thermal hysteresis and mean martensitic transformation temperature in highly processed shape memory alloys.

• Experiments design based on ML can greatly reduce the number of physics-based experiments and calculations needed to discover and design optimized, new materials.

Machine Learning for Knowledge Transfer Across Multiple Metals Additive Manufacturing Printers

• Adopting new metals 3D printers introduces time and cost obstacles to printing parts with the same quality as was attained on existing printers.

• To enable the reuse of previously acquired knowledge, this study proposes a data-driven ML knowledge transfer framework for process - property relations modeling during laser AM. This framework is verified through 3 “industry-use” inspired scenarios for AM Ti-6Al-4V.

[3] In-situ Monitoring & Control

In-situ monitoring of laser-matter interaction multiphysics and process control

• A portable laser melting system has been developed and built. High-speed in-situ X-ray imaging and sensing diagnosis measurements are carried out to reveal the fundamental physics understanding of pore formation and fluid dynamics during laser melting. The effects of processing parameters and alloy constituted composition on the phase transition and defects formation are experimentally analyzed and interpreted with physical simulation.

• Multi-modality sensing data was monitored and modeled for in-situ part quality prediction and defect inspection, and in-process operation was suggested for defects prevention and property features adjustment.

In-situ high-speed X-ray characterization for laser powder bed fusion (LPBF) process

• We have developed an in-situ laser melting chamber system for high-speed in-situ X-ray characterization and in-situ sensor monitoring

• It uses a high-brilliance X-ray light source (synchrotron X-ray & X-ray free electron laser), high-speed camera and detector, the subsurface dynamics of laser-induced melt pool have been studied for pore defect formation and phase transformation at (nm-μm)-length and (ps-ms)-time scales.

Page updated

Google Sites

Report abuse