Data-Enabled Physics-Informed Machine Learning for Reduced-Order Modeling Digital Twin: Application to Nuclear Reactor Physics

Abstract

This paper proposes an approach that combines reduced-order models with machine learning in order to create physics-informed digital twins to predict high-dimensional output quantities of interest, such as neutron flux and power distributions in nuclear reactor cores. The digital twin is designed to solve forward problems given input parameters, as well as to solve inverse problems given some extra measurements. Offline, we use reduced-order modeling, namely, the proper orthogonal decomposition (POD) to assemble physics-based computational models that are accurate enough for fast predictive digital twin. The machine learning techniques, namely, k-nearest-neighbors (KNN) and decision trees (DT) are used to formulate the input-parameterdependent coefficients of the reduced basis, whereafter the high-fidelity fields are able to be reconstructed. Online, we use the real time input parameters to rapidly reconstruct the neutron field in the core based on the adapted physics-based digital twin. The effectiveness of the framework is illustrated through a real engineering problem in nuclear reactor physics -reactor core simulation in the life cycle of HPR1000 governed by the two-group neutron diffusion equations affected by input parameters, i.e., burnup, control rod inserting step, power level and temperature of the coolant, which shows potential applications for on-line monitoring purpose.

Data-driven surrogate model with latent data assimilation: Application to wildfire forecasting

“…Being widely adopted in CFD simulations and industrial applications, the proper orthogonal decomposition (POD) [72] is a classical method of model order reduction using snapshots of dynamical systems, widely applied in engineering problems [6,22,38]. Here we remind the principle and some of the most important properties of POD for reduced-order modelling.…”

Reduced Order Surrogate Modelling and Latent Assimilation for Dynamical Systems

“…This approach has been widely applied in dynamical systems [38] with snapshots at different time steps. Applications can be found in a large range of engineering problems, including numerical weather prediction [22], hydrology [10] or nuclear engineering [16]. More precisely, a set of n u simulated or observed fields {u t0,t1,..tn u −1 } at different time are flattened and combined vertically to a matrix,…”

An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physics

“…In this regard, the objective of a digital twin in nuclear reactor domain can generally be taken as gains in economical efficiency and safety goals in nuclear power applications, particularly in reactor operations. The early application in reactor physics [36] proposes a prototype of reactor physics operational digital twin (RPODT) to predict neutron flux and power distributions in nuclear reactor cores for on-line monitoring purpose. The effectiveness of the proposed digital twin was illustrated through a real engineering problem based on HPR1000 reactor core.…”

“…The work in [36] suggested a non-intrusive reduced order model with machine learning methods to realize the first goal.…”