AI for Engineering Systems

Monitoring, diagnostics, prognostics and decision-making for complex engineering systems.

Research focus

Our research establishes statistically principled and decision-oriented AI methods for complex engineering systems whose performance depends on evolving states, uncertain failure mechanisms, and operational decisions. We integrate domain knowledge with probabilistic modeling, Bayesian inference, Gaussian processes, survival analysis, reinforcement learning, and uncertainty quantification to monitor system behavior, diagnose abnormal operations, predict failure time and failure mode, and prescribe maintenance or operational actions. Applications include multi-component production systems, IoT-enabled smart and connected systems, multistage manufacturing systems, structural damage diagnosis, and service systems where reliable prediction must ultimately support better engineering decisions.

Overview of data science methods for engineering processes and systems View full-size figure

Selected publications

Publications

[J11] Jaesung Lee^*, Tatthapong Srikitrungruang (advisee), and Salman Jahani, “Knowledge-Guided Reinforcement Learning for Preventive Maintenance Planning in Economically Dependent Multi-Component Systems,” IISE Transactions, vol. 58, no. 11, pp. 1352–1369, 2026, Published online 2026-01-22, Assigned November 2026 issue, doi:10.1080/24725854.2025.2610967.
Publication record: [J11]
[J15] Sina Aghaee Dabaghan Fard (advisee), Minhee Kim, Akash Deep, and Jaesung Lee^*, “Bayesian Joint Model of Multi-Sensor and Failure Event Data for Multi-Mode Failure Prediction,” Technometrics, pp. 1–15, 2026, Published online 2026-05-13, doi:10.1080/00401706.2026.2653564.
Publication record: [J15]
[J2] Jaesung Lee, Junbo Son, Shiyu Zhou, and Yong Chen, “Variation source identification in manufacturing processes using Bayesian approach with sparse variance components prior,” IEEE Transactions on Automation Science and Engineering, vol. 17, no. 3, pp. 1469–1485, 2020, doi:10.1109/TASE.2019.2959605.
Publication record: [J2]
[J5] Congfang Huang, Jaesung Lee, Yang Zhang, Shiyu Zhou, and Jiong Tang, “Mixed-Input Bayesian Optimization Method for Structural Damage Diagnosis,” IEEE Transactions on Reliability, vol. 72, no. 2, pp. 678–691, 2023, doi:10.1109/TR.2022.3179602.
Publication record: [J5]

Complete publication record

Projects & applications

Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System)

Goal: Establishing a reinforcement learning method combined with a stochastic model to find the optimal preventive maintenance policy in a multi-components production system.

Methodologies: Deep Reinforcement learning, deep neural network, stochastic process modeling

Collaborators: This work is done with a Ph.D. student, T. Srikitrungruang and Collaborator, Dr. S. Jahani

Publications

[J11] Jaesung Lee^*, Tatthapong Srikitrungruang (advisee), and Salman Jahani, “Knowledge-Guided Reinforcement Learning for Preventive Maintenance Planning in Economically Dependent Multi-Component Systems,” IISE Transactions, vol. 58, no. 11, pp. 1352–1369, 2026, Published online 2026-01-22, Assigned November 2026 issue, doi:10.1080/24725854.2025.2610967.
Publication record: [J11]
- This work was selected as a finalist in the QSR Best Referred Paper Competition in 2025 INFORMS Conference.

Research diagram: Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System) — Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System) View full-size figure

Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification

Methodologies: Bayesian Hierarchical Modeling, Convolutional Gaussian Process, Variational Inference, Proportional Cox Hazard model

Collaborators: This work is done with a Ph.D. student, S. Aghaee

Publications

[J15] Sina Aghaee Dabaghan Fard (advisee), Minhee Kim, Akash Deep, and Jaesung Lee^*, “Bayesian Joint Model of Multi-Sensor and Failure Event Data for Multi-Mode Failure Prediction,” Technometrics, pp. 1–15, 2026, Published online 2026-05-13, doi:10.1080/00401706.2026.2653564.
Publication record: [J15]
- This work was selected as a finalist in the QCRE Best Student Paper Competition in 2025 IISE Conference .

Research diagram: Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification — Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification View full-size figure

Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System

IoT-enabled Smart and Connected System

Goal: Identifying faulty operations with excessive variation in a multistage manufacturing system; establishing a sparse-variance statistical model.

Methodologies: Random-effects model, hierarchical Bayesian prior modeling

Publications

[J2] Jaesung Lee, Junbo Son, Shiyu Zhou, and Yong Chen, “Variation source identification in manufacturing processes using Bayesian approach with sparse variance components prior,” IEEE Transactions on Automation Science and Engineering, vol. 17, no. 3, pp. 1469–1485, 2020, doi:10.1109/TASE.2019.2959605.
Publication record: [J2]

Research diagram: Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System — Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System View full-size figure

Other research directions

AI for Engineering Systems

Monitoring, diagnostics, prognostics and decision-making for complex engineering systems.

AI for Engineering Processes

Data-driven modeling, quality control and optimization for advanced engineering processes.

Physics-Informed AI

Physics-informed inference of heterogeneous physical properties from noisy observations.