Nuclear Engineering ETDs

Publication Date

Fall 12-11-2025

Abstract

This dissertation proposes and evaluates two approaches, with-in a Process Risk and Analysis (PRIA) framework, that advance data-driven hazard discovery in complex cyber-physical systems. First, a transferability-based clustering method groups subspace-identified segments into operational modes, prioritizing cross-predictive performance over raw feature proximity. Second, a Neural Switching Linear Dynamical System (NeuralSLDS) model anchors learning in identified state-space models with Bayesian residuals, calibrated predictive uncertainty, and context-aware operating mode transitions. Together, these methods generate physics-informed, probabilistic world models that can support model-in-the-loop analysis of hazardous trajectories. The approach is validated on a simulated point-kinetics reactor and a centrifugal chiller dataset, demonstrating coherent mode discovery across regimes, low short-horizon prediction error with well calibrated predictive uncertainty. Overall, PRIA works toward bridging the gap between high-fidelity physics-based models and reinforcement learning algorithms for the purpose of novel hazard discovery that contributes to enhanced safety and security of cyber physical systems.

Keywords

cyber-physical, process risk, bayesian, hybrid system identification

Document Type

Dissertation

Language

English

Degree Name

Nuclear Engineering

Level of Degree

Doctoral

Department Name

Nuclear Engineering

First Committee Member (Chair)

Christopher Perfetti

Second Committee Member

Eric Vugrin

Third Committee Member

Timothy Schriener

Fourth Committee Member

Meeko Oishi

Download

Share

COinS