Parameter identification and state estimation for nuclear reactor operation digital twin

Gong, Hang; Zhu, Tao; Chen, Zhang; Wan, Yaping; Li, Qing

doi:10.1016/j.anucene.2022.109497

Cited by 11 publications

(3 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, for the interface problem, a suitable sampling algorithm can facilitate the training process and provide a better approximation. The next study could also involve the implementation of the proposed networks in emerging reactor digital twins [75][76][77] as core solvers.…”

Section: Discussionmentioning

confidence: 99%

Physics-constrained neural network for solving discontinuous interface K-eigenvalue problem with application to reactor physics

Yang,

Deng

et al. 2023

NUCL SCI TECH

View full text Add to dashboard Cite

Machine learning-based modeling of reactor physics problems has attracted increasing interest in recent years. Despite some progress in one-dimensional problems, there is still a paucity of benchmark studies that are easy to solve using traditional numerical methods albeit still challenging using neural networks for a wide range of practical problems. We present two networks, namely the Generalized Inverse Power Method Neural Network (GIPMNN) and Physics-Constrained GIPMNN (PC-GIPIMNN) to solve K-eigenvalue problems in neutron diffusion theory. GIPMNN follows the main idea of the inverse power method and determines the lowest eigenvalue using an iterative method. The PC-GIPMNN additionally enforces conservative interface conditions for the neutron flux. Meanwhile, Deep Ritz Method (DRM) directly solves the smallest eigenvalue by minimizing the eigenvalue in Rayleigh quotient form. A comprehensive study was conducted using GIPMNN, PC-GIPMNN, and DRM to solve problems of complex spatial geometry with variant material domains from the field of nuclear reactor physics. The methods were compared with the standard finite element method. The applicability and accuracy of the methods are reported and indicate that PC-GIPMNN outperforms GIPMNN and DRM.

show abstract

Section: Discussionmentioning

confidence: 99%

Physics-constrained neural network for solving discontinuous interface K-eigenvalue problem with application to reactor physics

Yang,

Deng

et al. 2023

NUCL SCI TECH

View full text Add to dashboard Cite

show abstract

“…The DT is constructed and calibrated autonomously for the NPPs core (Li et al, 2023d). It is also employed in nuclear reactors for parameter identification and state estimation (Gong et al, 2023), and anomaly detection (Cancemi et al, 2023).…”

Section: Big Data and Ai Applications In Nppsmentioning

confidence: 99%

Application of artificial intelligence technologies and big data computing for nuclear power plants control: a review

Ejigu,

Tuo,

Liu

2024

Front. Nucl. Eng.

View full text Add to dashboard Cite

Nuclear power plants produce a massive amount of clean energy and necessitate safe operation through intelligence technologies. Recently, the rapid advancements in communication infrastructures including artificial intelligence, big data computing, and Internet of Things devices moving the nuclear industries towards digitalization and intelligence to improve safety. The integration of these technologies into the nuclear sector offers effective tactics in addressing several challenges in the control and safe operation of nuclear power plants. This can be achieved through the insights generated from massive amounts of data. This paper comprehensively reviews the literature on artificial intelligence technologies and big data, seeking to provide a holistic perspective on their relations and how they can be integrated with nuclear power plants. The utilization of computing platforms boosts the deployment of artificial intelligence and big data analytics effectively in nuclear power plants. Further, this review also points out the future opportunities as well as challenges for applying artificial intelligence and big data computing in the nuclear industry.

show abstract

“…Notably, in the emerging research area, Gong et al . proposed a digital twin technique for nuclear reactor operations, which also presents an urgent need for nuclear power plant accident datasets 24 – 26 .…”

Section: Background and Summarymentioning

confidence: 99%

An open time-series simulated dataset covering various accidents for nuclear power plants

Xiao

Liang

et al. 2022

Sci Data

View full text Add to dashboard Cite

Nuclear energy plays an important role in global energy supply, especially as a key low-carbon source of power. However, safe operation is very critical in nuclear power plants (NPPs). Given the significant impact of human-caused errors on three serious nuclear accidents in history, artificial intelligence (AI) has increasingly been used in assisting operators with regard to making various decisions. In particular, data-driven AI algorithms have been used to identify the presence of accidents and their root causes. However, there is a lack of an open NPP accident dataset for measuring the performance of various algorithms, which is very challenging. This paper presents a first-of-its-kind open dataset created using PCTRAN, a pre-developed and widely used simulator for NPPs. The dataset, namely nuclear power plant accident data (NPPAD), basically covers the common types of accidents in typical pressurised water reactor NPPs, and it contains time-series data on the status or actions of various subsystems, accident types, and severity information. Moreover, the dataset incorporates other simulation data (e.g., radionuclide data) for conducting research beyond accident diagnosis.

show abstract

Parameter identification and state estimation for nuclear reactor operation digital twin

Cited by 11 publications

References 81 publications

Physics-constrained neural network for solving discontinuous interface K-eigenvalue problem with application to reactor physics

Physics-constrained neural network for solving discontinuous interface K-eigenvalue problem with application to reactor physics

Application of artificial intelligence technologies and big data computing for nuclear power plants control: a review

An open time-series simulated dataset covering various accidents for nuclear power plants

Contact Info

Product

Resources

About