Intelligent Manufacturing Lab starts at University of Michigan-Dearborn

The Intelligent Manufacturing Lab (IML) at the University of Michigan-Dearborn is an innovative research space dedicated to advancing AI-driven engineering solutions. Our lab brings together students and faculty to tackle complex challenges at the intersection of artificial intelligence, manufacturing, and energy systems.

Our Research Focus

We integrate cutting-edge AI methodologies with physics-based modeling to develop next-generation solutions across multiple domains:

AI for Manufacturing

Our manufacturing research revolutionizes next-generation production systems through:

Additive Manufacturing: AI-driven 3D printing algorithm development, material development, and process optimization using digital light processing (DLP) techniques
Battery Manufacturing: Advanced manufacturing processes for solid-state and lithium-ion batteries with reliability-based design optimization
Semiconductor Manufacturing: Intelligent systems for process control, quality assurance, and yield optimization to enhance device reliability

AI for Energy Storage

Our energy storage research focuses on design, optimization, and lifecycle assessment:

Battery Thermal Management Systems: Generative design and physics-informed machine learning for advanced thermal management
Battery Manufacturing: Probabilistic frameworks ensuring robust battery performance and safety
Battery Recycling: Life cycle assessments and techno-economic analyses for sustainable recycling solutions

AI for Data Center HVAC

We develop intelligent cooling systems through:

HVAC System Optimization: AI-driven control strategies for energy-efficient data center operations
Chip Cooling: Physics-based modeling and machine learning for optimal thermal management of semiconductor devices

AI Methodologies

We develop fundamental AI techniques for engineering applications:

Physics-Informed Machine Learning: Integrating physical laws with neural networks for accurate predictions
Generative Design: AI and diffusion models for novel design exploration and optimization
Uncertainty Quantification: Statistical frameworks for design under uncertainty and multi-fidelity approaches
Surrogate Modeling: Efficient machine learning approximations for rapid design exploration
Engineering Design Optimization: Reliability-based and control co-design optimization frameworks

Our Approach

The lab combines experimental testing, finite element modeling, machine learning-based surrogate modeling, generative design, and process optimization to enable breakthrough solutions. We serve as a hub for hands-on learning, industry partnerships, and collaborative research, preparing students for careers in advanced manufacturing, energy systems, and AI-driven engineering.

We welcome collaboration opportunities to solve real-world engineering problems across diverse domains. If you have a challenging engineering problem that could benefit from our expertise, we encourage you to reach out.

Welcome 👋

Authors

Zheng Liu

Assistant Professor

Zheng Liu joined the University of Michigan-Dearborn Industrial and Manufacturing Systems Engineering Department as an Assistant Professor. His research bridges theoretical and applied aspects of AI in manufacturing and energy systems. He focused on physics-based modeling, physics-informed machine learning, and generative design for manufacturing and energy storage applications. He also evaluated the manufacturing processes through life cycle assessment and techno-economic analysis, helping the team win $1M Department of Energy’s (DOE) inaugural American-Made Geothermal Lithium Extraction Prize. He has collaborated on multiple projects funded by the National Science Foundation (NSF) through the Future Manufacturing Research Grant (FMRG) program, as well as the Office of Naval Research (ONR). In addition, he served as a graduate fellow and STEM outreach coordinator at the NSF Engineering Research Center for Power Optimization for Electro-Thermal Systems (POETS). Zheng has received the Sharp Outstanding Graduate Student Award and the Tau Beta Pi Outstanding Graduate Student Award in recognition of his research contributions. He has published more than 15 peer-reviewed journal articles and 15 conference proceedings, and has served as a track chair for the IEEE Transportation Electrification Conference. Through his work, he continues to push the frontiers of AI-driven innovation in manufacturing and energy systems.