mlsanityData to 14 Oct 2026

Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison

arXiv 2506.12819 ↗First posted 15 Jun 2025eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Computationally cheap yet accurate dynamical models are a key requirement for real-time capable nonlinear optimization and model-based control. When given a computationally expensive high-order prediction model, a reduction to a lower-order simplified model can enable such real-time applications. Herein, we review nonlinear model order reduction methods and provide a comparison of method characteristics. Additionally, we discuss both general-purpose methods and tailored approaches for chemical process systems and we identify similarities and differences between these methods. As machine learning manifold-Galerkin approaches currently do not account for inputs in the construction of the reduced state subspace, we extend these methods to dynamical systems with inputs. In a comparative case study, we apply eight established model order reduction methods to an air separation process model: POD-Galerkin, nonlinear-POD-Galerkin, manifold-Galerkin, dynamic mode decomposition, Koopman theory, manifold learning with latent predictor, compartment modeling, and model aggregation. Herein, we do not investigate hyperreduction, i.e., reduction of floating point operations. Based on our findings, we discuss strengths and weaknesses of the model order reduction methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 311 references that are in the map. First posted on arXiv 15 Jun 2025.

Builds on

49 of 311 references.

References · 49

  1. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
  2. 2019Machine Learning for Fluid Mechanicscited by 385
  3. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  4. 2017Linearly-Recurrent Autoencoder Networks for Learning Dynamicscited by 145
  5. 2017Sobolev Training for Neural Networkscited by 143
  6. 2016Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive controlcited by 140
  7. 2014Dynamic mode decomposition with controlcited by 129
  8. 2020A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEscited by 105
  9. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  10. 2019Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systemscited by 96
  11. 2021POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decompositioncited by 79
  12. 2018Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systemscited by 54
37 more
  1. 2018Optimal construction of Koopman eigenfunctions for prediction and controlcited by 35
  2. 2018Global Deterministic Optimization with Artificial Neural Networks Embeddedcited by 33
  3. 2020Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear termscited by 32
  4. 2017Koopman operator-based model reduction for switched-system control of PDEscited by 31
  5. 2022Quadratic Approximation Manifold for Mitigating the Kolmogorov Barrier in Nonlinear Projection-Based Model Order Reductioncited by 30
  6. 2022Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutionscited by 29
  7. 2015Learning to Linearize Under Uncertaintycited by 25
  8. 2023Geometric Autoencoders -- What You See is What You Decodecited by 23
  9. 2020An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusioncited by 19
  10. 2020Data-Driven Model Predictive Control using Interpolated Koopman Generatorscited by 17
  11. 2023Learning Nonlinear Projections for Reduced-Order Modeling of Dynamical Systems using Constrained Autoencoderscited by 16
  12. 2023Canonical and Noncanonical Hamiltonian Operator Inferencecited by 15
  13. 2018Nonlinear Model Order Reduction via Lifting Transformations and Proper Orthogonal Decompositioncited by 14
  14. 2022Koopman Form of Nonlinear Systems with Inputscited by 11
  15. 2022Deep Koopman Learning of Nonlinear Time-Varying Systemscited by 11
  16. 2014Preserving Lagrangian structure in nonlinear model reduction with application to structural dynamicscited by 10
  17. 2022Generalized Quadratic Embeddings for Nonlinear Dynamics using Deep Learningcited by 9
  18. 2021How to Compute Invariant Manifolds and their Reduced Dynamics in High-Dimensional Finite-Element Modelscited by 8
  19. 2022Data-driven reduced order models using invariant foliations, manifolds and autoencoderscited by 8
  20. 2023Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systemscited by 7
  21. 2024A Riemannian Framework for Learning Reduced-order Lagrangian Dynamicscited by 7
  22. 2015Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Modelscited by 6
  23. 2020Direct computation of nonlinear mapping via normal form for reduced-order models of finite element nonlinear structurescited by 6
  24. 2021Optimizing Oblique Projections for Nonlinear Systems using Trajectoriescited by 6
  25. 2022Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learningcited by 6
  26. 2019Integrating production scheduling and process control using latent variable dynamic modelscited by 3
  27. 2020The p-AAA algorithm for data driven modeling of parametric dynamical systemscited by 3
  28. 2020Image-Based Model Predictive Control via Dynamic Mode Decompositioncited by 3
  29. 2023Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theorycited by 3
  30. 2023A modified AAA algorithm for learning stable reduced-order models from datacited by 2
  31. 2013Cross-Gramian-Based Combined State and Parameter Reduction for Large-Scale Control Systemscited by 1
  32. 2016Characterization of Exact Lumpability for Vector Fields on Smooth Manifoldscited by 1
  33. 2020Adaptive Learning of Hybrid Models for Nonlinear Model Predictive Control of Distillation Columnscited by 1
  34. 2022Virtual twins of nonlinear vibrating multiphysics microstructures: physics-based versus deep learning-based approachescited by 1
  35. 2022Demand Response for Flat Nonlinear MIMO Processes using Dynamic Ramping Constraintscited by 1
  36. 2023Optimal Design and Flexible Operation of a Fully Electrified Biodiesel Production Processcited by 1
  37. 2024Data-driven Nonlinear Model Reduction using Koopman Theory: Integrated Control Form and NMPC Case Studycited by 1

Built on by

Not cited yet.