Research
Focus Area 1: Physics-informed data-driven modeling and optimization for processes and operations
Developing novel statistical models, machine learning methods, and optimization algorithms with emphasis on both generalizability and interpretability.
Integrating physics principles and domain knowledge of complex processes into data-driven modeling to improve prediction, diagnosis, and optimization.
Publication examples
Nondestructive fatigue life prediction for additively manufactured metal parts through a multimodal transfer learning framework
IISE Transactions
Dirichlet process Gaussian mixture models for real-time monitoring and their application to chemical mechanical planarization
IEEE TASE
A Machine Learning Framework with Shapley’s Additive Explanations to Assess Solder Joint Reliability for Electronic Packaging
Journal of Electronic MaterialsFocus Area 2: Heterogeneous sensing and data-driven modeling for process monitoring, quality prediction, and operation optimization in additive manufacturing
Investigating materials-process-structure-property-performance relationships in different additive manufacturing processes using advanced sensing and machine learning.
Understanding the fatigue performance of parts made from the laser powder bed fusion (L-PBF) process in terms of process conditions, defects, and surface roughness, and improving the accuracy of fatigue life prediction for L-PBF parts in critical applications.
Publication examples
Defect criticality analysis on fatigue life of L-PBF 17-4 PH stainless steel via machine learning
International Journal of Fatigue
Determining critical surface features affecting fatigue behavior of additively manufactured Ti-6Al-4V
International Journal of Fatigue
A review of machine learning techniques for process and performance optimization in laser beam powder bed fusion additive manufacturing
Journal of Intelligent Manufacturing
Nonparametric Bayesian framework for material and process optimization with nanocomposite fused filament fabrication
Additive Manufacturing
Online real-time quality monitoring in additive manufacturing processes using heterogeneous sensors
Journal of Manufacturing Science and EngineeringFocus Area 3: AI in distributed smart manufacturing to advance critical fabrication capabilities and resilient supply chains
Adapting cutting-edge AI technologies, such as LLM, multimodal learning, and federated learning, into distributed manufacturing paradigms equipped with I4.0 infrastructure.
Investigating AI methods and technologies for materials design, in-situ process monitoring and quality prediction for semiconductor manufacturing and electronic packaging.
Publication examples
Wafer quality monitoring using spatial Dirichlet process based mixed-effect profile modeling scheme
Journal of Manufacturing Systems
FedCOT: Personalized Federated Transfer Learning with Conditional Optimal Transport for Manufacturing Predictive Modeling
