A Deterministic Assurance Framework for Licensable Explainable AI Grid-Interactive Nuclear Control
Open Access
Abstract
Deploying deep reinforcement learning (DRL) in safety-critical nuclear control is limited less by raw performance than by the absence of licensable, audit-ready evidence. We introduce a Deterministic Assurance Framework (DTAF) that converts controller behavior into licensing-grade proof by combining the following: (i) deterministic licensing gates tied to formal safety and performance limits (e.g., Total Time Unsafe (TTU) = 0; bounded Transient Severity Score (TSS); and minimum Grid Load-Following Index (GLFI)); (ii) a portfolio of adversarial stress tests representative of off-nominal operation; and (iii) a traceability and explainability package that renders every evaluated action auditable. The DTAF is demonstrated on a high-fidelity pressurized-water-reactor (PWR) simulation model used as a software-in-the-loop testbed. Three governor architectures are evaluated under identical, fixed scenarios: a curriculum-trained Soft Actor–Critic (SAC) agent, and Differential-Evolution-optimized Proportional–Integral–Derivative (PID-DE) and Fuzzy-Logic (FLC-DE) Controllers. Performance is assessed deterministically via gate-aligned metrics—TTU, TSS, GLFI, cumulative control effort (CE_sum), valve-reversal count (V_rev), and speed overshoot (OS_ω). Across the adversarial portfolio, the SAC controller meets the predeclared licensing gates in single-run evaluations, whereas the strong conventional baselines violate gates in specific high-severity cases; where all methods remain within the safe envelope, the SAC delivers a higher GLFI and lower CE_sum, with fewer reversals and reduced overshoot. All licensing conclusions derive from deterministic single-run tests; a small, fixed-seed check (three seeds with descriptive intervals) is reported separately as non-licensing supplementary analysis. By producing transparent, reproducible artifacts, the DTAF offers a regulator-oriented pathway for qualifying DRL controllers in grid-interactive nuclear operations.Keywords
Funding Information
- 2025 Research Fund of the KEPCO International Nuclear Graduate School (KINGS), Republic of Korea
This publication has 21 references indexed in Scilit:
- A digital twin framework for generation-IV reactors with reinforcement learning-enabled health-aware supervisory controlProgress in Nuclear Energy, 2025
- Novel multiagent reinforcement learning framework using twin delayed deep deterministic policy gradient for adaptive PID control in boiler turbine systemsScientific Reports, 2025
- Explainable AI Models for Enhancing Operator Reliability During Reactor Design-Based Accidents Using Radionuclide DataNuclear Technology, 2025
- A safe reinforcement learning algorithm for supervisory control of power plantsKnowledge-Based Systems, 2024
- Possibilities of reinforcement learning for nuclear power plants: Evidence on current applications and beyondNuclear Engineering and Technology, 2024
- Dense reinforcement learning for safety validation of autonomous vehiclesNature, 2023
- Particle Swarm Optimization or Differential Evolution—A comparisonEngineering Applications of Artificial Intelligence, 2023
- Frequency control of nuclear-renewable hybrid energy systems using optimal PID and FOPID controllersHeliyon, 2022
- Taking the Human Out of the Loop: A Review of Bayesian OptimizationProceedings of the IEEE, 2015
- Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous SpacesJournal of Global Optimization, 1997