Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine

Abstract

High-performance computing (HPC) has revolutionized our ability to perform detailed simulations of complex real-world processes. A prominent contemporary example is from aerospace propulsion, where HPC is used for rotating detonation rocket engine (RDRE) simulations in support of the design of next-generation rocket engines; however, these simulations take millions of core hours even on powerful supercomputers, which makes them impractical for engineering tasks like design exploration and risk assessment. Data-driven reduced-order models (ROMs) aim to address this limitation by constructing computationally cheap yet sufficiently accurate approximations that serve as surrogates for the high-fidelity model. This paper contributes a distributed memory algorithm that achieves fast and scalable construction of predictive physics-based ROMs trained from sparse datasets of extremely large state dimension. The algorithm learns structured physics-based ROMs that approximate the dynamical systems underlying those datasets.This enables model reduction for problems at a scale and complexity that exceeds the capabilities of standard, serial approaches. We demonstrate our algorithm's scalability using up to $2,048$ cores on the Frontera supercomputer at the Texas Advanced Computing Center. We focus on a real-world three-dimensional RDRE for which one millisecond of simulated physical time requires one million core hours on a supercomputer. Using a training dataset of $2,536$ snapshots each of state dimension $76$ million, our distributed algorithm enables the construction of a predictive data-driven reduced model in just $13$ seconds on $2,048$ cores on Frontera.

22 pages, 8 figures

References in corpus (16)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• On Dynamic Mode Decomposition: Theory and Applications
• Learning data driven discretizations for partial differential equations
• Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
• Data-Driven POD-Galerkin Reduced Order Model for Turbulent Flows
• Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifolds
• Data-driven reduced-order models via regularized operator inference for a single-injector combustion process
• Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Learning physics-based reduced-order models for a single-injector combustion process
• pyMOR - Generic Algorithms and Interfaces for Model Order Reduction
• The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations
• A Priori Estimation Of Memory Effects In Coarse-Grained Nonlinear Systems Using The Mori-Zwanzig Formalism
• VPIC 2.0: Next Generation Particle-in-Cell Simulations
• Domain decomposition for data-driven reduced modeling of large-scale systems
• A parallel implementation of reduced-order modeling of large-scale systems

Cited by in corpus (1)

• Fast prediction of plasma instabilities with sparse-grid-accelerated optimized dynamic mode decomposition