Using deep learning to explore local physical similarity for global-scale bridging in thermal-hydraulic simulation

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. Because mesh size is one of the model parameters for these coarse-mesh codes with simplified boundary-layer treatments, the mesh-induced error and model error are tightly connected, which makes it difficult to evaluate mesh effect or model scalability independently, as in classical scaling analysis. This paper proposes a data-driven approach, Feature-Similarity Measurement (FSM), 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. As a result, a data-driven model can be developed to provide an accurate estimate on the simulation error even when global-scale gaps exist. Case studies based on mixed convection have been designed for demonstrating the capability of data-driven models in bridging global-scale gaps.