Using Deep Learning to Explore Local Physical Similarity for Global-scale Bridging in Thermal-hydraulic Simulation

TL;DR

This paper introduces a data-driven method using deep learning to analyze local physical patterns, aiming to improve the accuracy of thermal-hydraulic simulations across different scales and conditions.

Contribution

It presents a novel feature similarity measurement approach that leverages machine learning to connect local physical features with simulation errors, enhancing model reliability.

Findings

Deep learning effectively models the relationship between physical features and simulation errors.

The method improves the credibility of thermal-hydraulic simulations beyond test conditions.

Case studies demonstrate successful bridging of global scale gaps in mixed convection scenarios.

Abstract

Current system thermal-hydraulic codes have limited credibility in simulating real plant conditions, especially when the geometry and boundary conditions are extrapolated beyond the range of test facilities. This paper proposes a data-driven approach, Feature Similarity Measurement FFSM), to establish a technical basis to overcome these difficulties by exploring local patterns using machine learning. The underlying local patterns in multiscale data are represented by a set of physical features that embody the information from a physical system of interest, empirical correlations, and the effect of mesh size. After performing a limited number of high-fidelity numerical simulations and a sufficient amount of fast-running coarse-mesh simulations, an error database is built, and deep learning is applied to construct and explore the relationship between the local physical features and simulation errors. Case studies based on mixed convection have been designed for demonstrating the capability of data-driven models in bridging global scale gaps.