Data-Driven Prediction and Uncertainty Quantification of PWR Crud-Induced Power Shift Using Convolutional Neural Networks

2024-06-27

Energy

AI Summary

Predicting Crud-Induced Power Shift (CIPS) in pressurized water reactors remains challenging due to the complex interplay between fuel assembly geometry, coolant chemistry, and operational history. Method: This paper proposes a lightweight 3D convolutional neural network (3D-CNN) surrogate model for end-to-end, assembly-level prediction of CIPS occurrence and onset time. It is the first work to apply 3D-CNNs to assembly-scale CIPS modeling, integrating core physics simulation outputs with plant-specific operational measurements. To enhance reliability, we introduce a reactor-specific calibration mechanism and Monte Carlo Dropout for interpretable uncertainty quantification. Results: Validated on multi-cycle data—including both clean and crud-affected reload cycles—from Catawba Unit 1, the model achieves high prediction accuracy while reducing computational cost by orders of magnitude compared to high-fidelity physics-based simulations. It demonstrates strong engineering practicality, robustness across diverse operational conditions, and quantifiable predictive uncertainty—enabling informed decision-making for CIPS mitigation.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

The development of Crud-Induced Power Shift (CIPS) is an operational challenge in Pressurized Water Reactors that is due to the development of crud on the fuel rod cladding. The available predictive tools developed previously, usually based on fundamental physics, are computationally expensive and have shown differing degrees of accuracy. This work proposes a completely top-down approach to predict CIPS instances on an assembly level with reactor-specific calibration built-in. Built using artificial neural networks, this work uses a three-dimensional convolutional approach to leverage the image-like layout of the input data. As a classifier, the convolutional neural network model predicts whether a given assembly will experience CIPS as well as the time of occurrence during a given cycle. This surrogate model is both trained and tested using a combination of calculated core model parameters and measured plant data from Unit 1 of the Catawba Nuclear Station. After the evaluation of its performance using various metrics, Monte Carlo dropout is employed for extensive uncertainty quantification of the model predictions. The results indicate that this methodology could be a viable approach in predicting CIPS with an assembly-level resolution across both clean and afflicted cycles, while using limited computational resources.

Problem

• Power Shift Prediction
• Crud Formation
• Computational Efficiency

Innovation

• Convolutional Neural Network
• Power Shift Prediction
• Monte Carlo Dropout