Enhancing nuclear power plants’ autonomous control capabilities
Majdi Radaideh will support Idaho National Lab-led effort to revolutionize nuclear reactor control systems
A new initiative led by Idaho National Laboratory (INL) that includes Majdi Radaideh, U-M assistant professor of nuclear engineering and radiological sciences, aims to revolutionize nuclear reactor control systems using advanced AI and digital twins. The project focuses on developing autonomous control systems that optimize reactor performance while maintaining safety and security.
Nuclear energy:
fission and fusion
Advancing nuclear energy
from discovery to deployment
Radaideh’s expertise is central to quantifying and mitigating uncertainties in machine learning, especially reinforcement learning used for digital twins—virtual models that mimic real reactor operations and enable proactive, automated control. The team’s novel uncertainty quantification (UQ) approach combines new probability methods to address a range of risks, from cyber-attacks to low-quality sensor data, offering a comprehensive framework for safe digital twin implementation.
“This project provides a unique opportunity to assess machine learning models robustness in building real-time digital twins,” said Radaideh. “With INL, we are going to address two key challenges in model calibration in real-time and build an interpretable physics-based reinforcement learning control policy. “
This is an AI-generated, human-verified summary of the article Advancing Nuclear Reactor Control and Digital Twins with Idaho National Laboratory by Sara Norman.