Data-driven reduced-order models via regularized operator inference for a single-injector combustion process

Abstract

This paper derives predictive reduced-order models for rocket engine combustion dynamics via Operator Inference, a scientific machine learning approach that blends data-driven learning with physics-based modeling. The non-intrusive nature of the approach enables variable transformations that expose system structure. The specific contribution of this paper is to advance the formulation robustness and algorithmic scalability of the Operator Inference approach. Regularization is introduced to the formulation to avoid over-fitting. The task of determining an optimal regularization is posed as an optimization problem that balances training error and stability of long-time integration dynamics. A scalable algorithm and open-source implementation are presented, then demonstrated for a single-injector rocket combustion example. This example exhibits rich dynamics that are difficult to capture with state-of-the-art reduced models. With appropriate regularization and an informed selection of learning variables, the reduced-order models exhibit high accuracy in re-predicting the training regime and acceptable accuracy in predicting future dynamics, while achieving close to a million times speedup in computational cost. When compared to a state-of-the-art model reduction method, the Operator Inference models provide the same or better accuracy at approximately one thousandth of the computational cost.

To appear in the Journal of the Royal Society of New Zealand. See https://github.com/Willcox-Research-Group/ROM-OpInf-Combustion-2D for code and additional results

References in corpus (1)

• The NumPy array: a structure for efficient numerical computation

Cited by in corpus (32)

• Improving aircraft performance using machine learning: a review
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Quadratic Approximation Manifold for Mitigating the Kolmogorov Barrier in Nonlinear Projection-Based Model Order Reduction
• LaSDI: Parametric Latent Space Dynamics Identification
• Bayesian operator inference for data-driven reduced-order modeling
• Non-intrusive reduced-order models for parametric partial differential equations via data-driven operator inference
• gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identification
• Predictive Reduced Order Modeling of Chaotic Multi-scale Problems Using Adaptively Sampled Projections
• Predicting Solar Wind Streams from the Inner-Heliosphere to Earth via Shifted Operator Inference
• Scientific Machine Learning Based Reduced-Order Models for Plasma Turbulence Simulations
• Domain decomposition for data-driven reduced modeling of large-scale systems
• Data-driven Discovery of Delay Differential Equations with Discrete Delays
• Data-driven modeling of hypersonic reentry flow with heat and mass transfer
• Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine
• Non-intrusive reduced-order modeling for dynamical systems with spatially localized features
• Adjacency-based, non-intrusive model reduction for Vortex-Induced Vibrations
• Energy preserving reduced-order modelling of thermal shallow water equation
• Non-intrusive Balancing Transformation of Highly Stiff Systems with Lightly-damped Impulse Response
• Energy-Preserving Reduced Operator Inference for Efficient Design and Control
• Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems
• Physically consistent predictive reduced-order modeling by enhancing Operator Inference with state constraints
• Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces
• Mixed interpolatory and inference non-intrusive reduced order modeling with application to pollutants dispersion
• A parallel implementation of reduced-order modeling of large-scale systems
• Block-structured Operator Inference for coupled multiphysics model reduction
• A Differentiable Solver Approach to Operator Inference
• Projection-based model-order reduction via graph autoencoders suited for unstructured meshes
• Toward real-time optimization through model reduction and model discrepancy sensitivities
• VIVALDy: A Hybrid Generative Reduced-Order Model for Turbulent Flows, Applied to Vortex-Induced Vibrations
• Hyper-reduction-free reduced-order Newton solvers for projection-based model-order reduction of nonlinear dynamical systems
• Randomized Projection Learning Method forDynamic Mode Decomposition