Classification of machine learning frameworks for data-driven thermal fluid models

Abstract

Thermal fluid processes are inherently multi-physics and multi-scale, involving mass-momentumenergy transport phenomena at multiple scales. Thermal fluid simulation (TFS) is based on solving conservative equations, for which -except for "first-principles" direct numerical simulationclosure relations (CRs) are required to provide microscopic interactions or so-called sub-grid-scale physics. In practice, TFS is realized through reduced-order modeling, and its CRs as low-fidelity models can be informed by observations and data from relevant and adequately evaluated experiments and high-fidelity simulations. This paper is focused on data-driven TFS models, specifically on their development using machine learning (ML). Five ML frameworks are introduced including physics-separated ML (PSML or Type I ML), physics-evaluated ML (PEML or Type II ML), physics-integrated ML (PIML or Type III ML), physics-recovered (PRML or Type IV ML), and physics-discovered ML (PDML or Type V ML). The frameworks vary in their performance for different applications depending on the level of knowledge of governing physics, source, type, amount and quality of available data for training. Notably, outlined for the first time in this paper, Type III models present stringent requirements on modeling, substantial computing resources for training, and high potential in extracting value from "big data" in thermal fluid research.The current paper demonstrates and investigates ML frameworks in three examples. First, we utilize the heat diffusion equation with a nonlinear conductivity model formulated by convolutional neural networks (CNNs) and feedforward neural networks (FNNs) to illustrate the applications of Type I, Type II, Type III, and Type V ML. The results indicate a preference for Type II ML under deficient data support. Type III ML can effectively utilize field data, potentially generating more robust predictions than Type I and Type II ML. CNN-based closures exhibit more predictability than FNN-based closures, but CNN-based closures require more training data to obtain accurate predictions. Second, we illustrate how to employ Type I ML and Type II ML frameworks for data-driven turbulence modeling using reference works. Third, we demonstrate Type I ML by building a deep FNN-based slip closure for two-phase flow modeling. The results show that deep FNN-based closures exhibit a bounded error in the prediction domain.to establish their relevance to the conditions and models under consideration, so that these data become useful information. Third, data are processed by various methods (including ML) to recognize underlying correlations behind the information. The so-developed intelligence (e.g., in the form of closure relations) is used to enable thermal fluid simulation in applications.Stemming from the preceding discussion, Fig. 2 depicts the DDM framework that includes the concept of (Data/Method/Platform) "as a Service (aaS)" [5]. The "aaS" notations are employed to denote components (modules) of work-flow in a "divide-and-conquer" strategy ...

Quantification of model uncertainty in RANS simulations: A review

“…Numerous other approaches have been proposed for augmenting and improving turbulence models based on machine learning [16]. Finally, data-driven, machine-learning based methods have also been used in improving CFD models of thermal fluids flow with focus on boiling flows in nuclear reactor thermo hydraulics [e.g., [147][148][149][150] and in high-Mach number flows [151].…”

Data-driven modeling for boiling heat transfer: Using deep neural networks and high-fidelity simulation results

“…Such premise cannot be guaranteed with flow features calculated from a MCFD solver. In this sense, to incorporate the deep network in a MCFD solver, the network should also be coupled with that solver in the training process, as is suggested in [5].…”

“…Moreover, A comprehensive review of the application of DNN in thermal fluid related problems is performed by Chang and Dinh [5]. It should be noted from the review that, in the current stage, there are still only limited applications of DNNs on physical problems and such applications are more focused on turbulence modeling.…”

A data-driven framework for error estimation and mesh-model optimization in system-level thermal-hydraulic simulation

“…and , = 1 ∑ � − � , � 2 =1 (23) where � and � , are the prediction from the mth tree respectively before and after permutation.…”