Skip to main content
Department of Industrial and Systems Engineering College of Engineering

Research

Degradation modeling, diagnosis, and prognosis

How to accurately model and predict a system’s health state and remaining lifetime based on real-time multi-sensor and covariate data? (Application examples: turbofan engines, Li-ion batteries)

Selected Publications:

  • Zihan Li, Mostafa Reisi and Minhee Kim (2026), “Federated Conformal Approach for Trustworthy Uncertainty Quantification in Distributed Fleet Prognostics,” Technometrics.
  • Minhee Kim, Changyue Song, and Kaibo Liu (2022), “Individualized Degradation Modeling and Prognostics in a Heterogeneous Group via Incorporating Static Covariate Information,” IEEE Transactions on Automation Science and Engineering, 19 (3), 2074-2094.
  • Minhee Kim and Kaibo Liu (2020), “A Bayesian Deep Learning Framework for Interval Estimation of Remaining Useful Life in Complex Systems by Incorporating General Degradation Characteristics,” IISE Transactions,53(3), 326-340.

Funded projects:

  • Model-Agnostic Strategies to Align AI with Real-World Operational Goals in Predictive Maintenance
    • PI, National Science Foundation, 09/01/2025 – 8/31/2028
  • Exploiting Spatiotemporal Energy Arbitrage for Electric Vehicle Battery Swap Stations with Faithful Battery Degradation Modeling
    • Co-PI, ISE-HWCOE Research Thrust Pilot Program, University of Florida, 01/01/2023 – 12/31/2023

Uncertainty Quantification and Trustworthy AI in High-Stakes Applications

How much should we trust a model’s prediction, and when should we not trust it at all? (Application examples: nuclear power plants, semiconductor wafers)

Selected Publications:

  • Zihan Li, Mostafa Reisi and Minhee Kim (2026), “Federated Conformal Approach for Trustworthy Uncertainty Quantification in Distributed Fleet Prognostics,” Technometrics.
  • Kani Fu, Zihan Li, Akash Deep, Jaesung Lee and Minhee Kim (2026), “Examining and Mitigating Underspecification in Neural Network-based Wafer Defect Pattern Classification,” Journal of Intelligent Manufacturing.
  • Minhee Kim and Yong Yang (2027), “Quantifying Uncertainty in Void Swelling Prediction: A Conformal Prediction Framework for Reactor Safety Margins,” Annals of Nuclear Energy, 240, 112751.

Funded projects:

  • AI-Driven Failure Analysis and Physical Assurance for Advanced Semiconductor Packaging
    • Co-PI, Florida Semiconductor Engine, 08/01/2026 – 07/31/2029

Engineering-Informed Machine Learning

How to incorporate engineering domain knowledge to guide a model’s prediction and decision-making? (Application examples: additive manufacturing, product design)

Selected Publications:

  • Zihan Li, Kani Fu, Benjamin Bevans, Prahalada Rao, Rongxuan Wang, Antonio Carrington, Alexander Riensche, Christopher Barrett, Scott Halliday and Minhee Kim (2026), “Scalable Bayesian transfer learning for in-situ qualification in laser powder bed fusion additive manufacturing,” Journal of Quality Technology
  • Minhee Kim (2024), “Iterative Durability Design of Products via Degradation-Informed Bayesian Optimization,” IEEE Transactions on Automation Science and Engineering, 22, 18201-18216.
  • Zhan Ma, Shu Wang, Minhee Kim, Kaibo Liu, Chun-Long Chen, and Wenxiao Pan (2021), “Transfer learning of memory kernels for transferable coarse-graining of polymer dynamics,” Soft Matter, 17, 5864-5877.

Funded projects:

  • CAIG: ECHO: Environmental Context-aware geoHazard mOnitoring AI for Sinkhole Precursor Detection
    • Co-PI, National Science Foundation, 01/01/2025 – 12/31/2027
  • Investigate data science techniques for inspection optimization of reactor components
    • Co-PI, Electric Power Research Institute, 06/02/2026 – 12/31/2027
  • CLIMA: Collaborative Research: Multistable Organic Structural Systems (MOSS)
    • Co-PI, National Science Foundation, 01/01/2025 – 12/31/2027
  • Interpretable Dynamic Eye-tracking Analytics via Pattern Based Learning (IDEA-PBL)
    • PI, ISE-HWCOE Research Thrust Pilot Program, University of Florida, 01/01/2023 – 12/31/2023