A Methodology for Thermal Limit Bias Predictability Through Artificial Intelligence

TL;DR

This paper introduces a deep learning methodology to predict and correct thermal limit bias in BWRs, significantly improving accuracy and operational efficiency, with successful deployment at multiple plants.

Contribution

A novel convolutional neural network architecture for predicting and correcting thermal limit bias in nuclear reactors, enhancing operational accuracy and economic performance.

Findings

Reduced mean nodal array error by 74%

Decreased maximum bias by 52%

Model deployed at multiple BWRs

Abstract

Nuclear power plant operators face significant challenges due to unpredictable deviations between offline and online thermal limits, a phenomenon known as thermal limit bias, which leads to conservative design margins, increased fuel costs, and operational inefficiencies. This work presents a deep learning based methodology to predict and correct this bias for Boiling Water Reactors (BWRs), focusing on the Maximum Fraction of Limiting Power Density (MFLPD) metric used to track the Linear Heat Generation Rate (LHGR) limit. The proposed model employs a fully convolutional encoder decoder architecture, incorporating a feature fusion network to predict corrected MFLPD values closer to online measurements. Evaluated across five independent fuel cycles, the model reduces the mean nodal array error by 74 percent, the mean absolute deviation in limiting values by 72 percent, and the maximum bias by 52 percent compared to offline methods. These results demonstrate the model's potential to meaningfully improve fuel cycle economics and operational planning, and a commercial variant has been deployed at multiple operating BWRs.