Nuclear Engineering

Nuclear engineering research increasingly leverages advanced machine learning techniques, particularly deep neural networks (DNNs) and their variants, to improve the efficiency and accuracy of simulations and predictions for complex reactor systems. Current efforts focus on developing robust surrogate models, such as DeepONets, for real-time inference in digital twin applications and on rigorously quantifying uncertainties in these models using methods like Monte Carlo Dropout and Bayesian Neural Networks. This work is crucial for enhancing the safety, reliability, and efficiency of nuclear power generation and for advancing the verification and validation of existing computational models.

Papers

November 12, 2024

Research on fault diagnosis of nuclear power first-second circuit based on hierarchical multi-granularity classification network
Jiangwen Chen, Siwei Li, Guo Jiang, Cheng Dongzhen, Lin Hua, Wang Wei
DH Research Multi Granularity Fault Diagnosis First Attempt Nuclear Reactor Nuclear Engineering

October 24, 2024

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
Farah Alsafadi, Mahmoud Yaseen, Xu Wu
Data Augmentation Bayesian Neural Network Comprehensive Investigation Generative Deep Learning Nuclear Engineering

August 15, 2023

Deep Neural Operator Driven Real Time Inference for Nuclear Systems to Enable Digital Twin Solutions
Kazuma Kobayashi, Syed Bahauddin Alam
Digital Twin Surrogate Modeling Deep Operator Network VI DeepONet Nuclear Reactor Nuclear Engineering

November 16, 2022

Prediction and Uncertainty Quantification of SAFARI-1 Axial Neutron Flux Profiles with Neural Networks
Lesego E. Moloko, Pavel M. Bokov, Xu Wu, Kostadin N. Ivanov
Neural Network Human Prediction Uncertainty Quantification Nuclear Reactor Experimental Verification Nuclear Engineering

June 27, 2022

Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models
Mahmoud Yaseen, Xu Wu
Machine Learning Model Uncertainty Quantification Deep Learning Model Uncertainty Fission Gas Nuclear Engineering

Nuclear Engineering

Papers

Research on fault diagnosis of nuclear power first-second circuit based on hierarchical multi-granularity classification network

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation

Deep Neural Operator Driven Real Time Inference for Nuclear Systems to Enable Digital Twin Solutions

Prediction and Uncertainty Quantification of SAFARI-1 Axial Neutron Flux Profiles with Neural Networks

Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models