A distinguishing focus is translating AI from lab prototypes into robust shop-floor systems through MLOps, edge AI, and trustworthy AI practices. The cluster builds repeatable pipelines for data governance, model monitoring/drift detection, and safe deployment with human-in-the-loop workflows. We also advance explainable and risk-aware AI to support operator trust, compliance, and auditability in safety- and quality-critical operations. These capabilities position the cluster to partner with industry on scalable, secure, and maintainable Industrial AI solutions.
Representative Research Topics
-
Predictive maintenance and remaining useful life (RUL) modeling for critical manufacturing assets
-
Machine vision quality inspection: defect detection/segmentation, metrology, and inline QA automation
-
Anomaly detection and fault diagnosis using multimodal time-series (vibration, acoustics, current, thermal, etc.)
-
Process optimization and control with hybrid models (physics-informed ML, digital-twin-assisted optimization)
-
Edge AI + MLOps for manufacturing: deployment, monitoring, drift management, and trustworthy/explainable AI
Group Members
-
Nelson Granda, Assistant Professor, Applied Engineering Technology - nagranda@ncat.edu
- Letu Qingge, Assistant Professor, Computer Science - lqingge@ncat.edu
- Renzun Zhao, Associate Professor, Civil, Architectural and Environmental Engineering - rzhao@ncat.edu