A Differentiable Solver Approach to Operator Inference

Abstract

Model Order Reduction is a key technology for industrial applications in the context of digital twins. Key requirements are non-intrusiveness, physics-awareness, as well as robustness and usability. Operator inference based on least-squares minimization combined with the Discrete Empirical Interpolation Method captures most of these requirements, though the required regularization limits usability. Within this contribution we reformulate the problem of operator inference as a constrained optimization problem allowing to relax on the required regularization. The result is a robust model order reduction approach for real-world industrial applications, which is validated along a dynamics complex 3D cooling process of a multi-tubular reactor using a commercial software package.

References in corpus (5)

• Neural Ordinary Differential Equations
• Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
• 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
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

Cited by in corpus (1)

• $\text{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications