vault backup: 2025-08-11 16:54:01

Zettelkasten/Permanent Notes/thesis-ideas.md

@@ -258,15 +258,16 @@ ___________________________________________________________
 ### Goals:
 
 The goal of this research is to develop a high-assurance,
-digital twin–based methodology for runtime fault detection
+digital twin–based fault detection and mitigation framework
-in a reactor control system. A physics-based digital twin
+for a reactor control system. A physics-based digital twin
-will be continuously compared with live plant measurements
+will be run in parallel with plant measurements to detect
-to detect anomalies such as coolant losses, sensor and
+anomalies such as coolant losses, sensor and actuator
-actuator faults, and abnormal component degradation. Discrepancies
+faults, and abnormal component degradation. Discrepancies
 between the digital twin and plant data will be analyzed
-using physics-informed machine learning models to diagnose
+using residual0based and physics-informed machine learning
-the underlying fault and trigger appropriate autonomous
+models to diagnose the underlying fault and trigger
-control actions.
+appropriate graded autonomous control actions ranging from
+control adjustments to safe shutdown.
 
 ### Outcomes:
 
@@ -274,19 +275,19 @@ For this research to be successful, I will accomplish the
 following:
 
 1. Create a simulation suite for the Small Modular Advanced
-   High Temperature Reactor (SmAHTR) to simulate fault
+   High Temperature Reactor (SmAHTR) to simulate high-impact
-conditions including sensor and actuator failures, and
+fault types such as secondary loop coolant losses, heat
-component degradation.
+exchanger fouling, and sensor drifting.
 
-2. Implement a physics-informed neural network (PINN)
+2. Implement a residual-based physics-informed neural
-   framework to estimate key plant parameters, detect
+   network (PINN) to estimate key plant parameters, detect
 discrepancies between predicted and measured signals, and
-identify probable fault conditions.
+identify probable fault condition and severity.
 
 3. Integrate the fault detection developed with a
    proof-of-concept autonomous supervisory controller
-capable of implementing graded responses to fault
+capable of implementing graded responses to fault conditions
-conditions.
+aligned with NRC safety protocols.
 
 ### Impact: