Toward Developing Machine-Learning-Aided Tools for the Thermomechanical Monitoring of Nuclear Reactor Components

2025-07-12

AI Summary

Addressing the challenge of real-time monitoring of thermal–mechanical states in pressurized water reactor (PWR) fuel rods—which hinders predictive maintenance—this paper proposes a physics-informed, data-driven hybrid methodology. High-fidelity training data are generated via coupled BISON/MOOSE-THM simulations; a lightweight convolutional neural network (CNN) is then trained exclusively on sparse cladding surface temperature measurements to reconstruct the full-field temperature distribution with high accuracy (<1.5% error) and no overfitting after >1000 epochs. Subsequently, the inferred temperature field is coupled with thermo-mechanical constitutive models to enable online stress and strain inference. This approach achieves, for the first time, end-to-end reconstruction of the full-scale thermal–mechanical field from sparse surface thermometry. It establishes a novel, efficient, interpretable, and engineering-practical paradigm for online health monitoring of critical nuclear reactor components.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Proactive maintenance strategies, such as Predictive Maintenance (PdM), play an important role in the operation of Nuclear Power Plants (NPPs), particularly due to their capacity to reduce offline time by preventing unexpected shutdowns caused by component failures. In this work, we explore the use of a Convolutional Neural Network (CNN) architecture combined with a computational thermomechanical model to calculate the temperature, stress, and strain of a Pressurized Water Reactor (PWR) fuel rod during operation. This estimation relies on a limited number of temperature measurements from the cladding's outer surface. This methodology can potentially aid in developing PdM tools for nuclear reactors by enabling real-time monitoring of such systems. The training, validation, and testing datasets were generated through coupled simulations involving BISON, a finite element-based nuclear fuel performance code, and the MOOSE Thermal-Hydraulics Module (MOOSE-THM). We conducted eleven simulations, varying the peak linear heat generation rates. Of these, eight were used for training, two for validation, and one for testing. The CNN was trained for over 1,000 epochs without signs of overfitting, achieving highly accurate temperature distribution predictions. These were then used in a thermomechanical model to determine the stress and strain distribution within the fuel rod.

Problem

• Predict temperature, stress, strain in PWR fuel rods
• Enable real-time monitoring for nuclear reactor maintenance
• Use CNN and thermomechanical models with limited data

Innovation

• CNN combined with thermomechanical model
• Real-time monitoring using limited temperature data
• Training datasets generated via BISON and MOOSE-THM