Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems (2312.06256v1)
Abstract: This work concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems. We investigate the integration of neural autoencoders in model order reduction, while at the same time preserving Hamiltonian or Lagrangian structures. We focus on extensively evaluating the considered methodology by performing simulation and control experiments on large mass-spring-damper networks, with hundreds of states. The empirical findings reveal that compressed latent dynamics with less than 5 degrees of freedom can accurately reconstruct the original systems' transient and steady-state behavior with a relative total error of around 4\%, while simultaneously accurately reconstructing the total energy. Leveraging this system compression technique, we introduce a model-based controller that exploits the mathematical structure of the compressed model to regulate the configuration of heavily underactuated mechanical systems.
- A. Agrachev and A. Sarychev, “Navier–stokes equations: Controllability by means of low modes forcing,” Journal of Dynamical and Control Systems, March 2005.
- C. Della Santina et al., “Model-based control of soft robots: A survey of the state of the art and open challenges,” IEEE Control Systems Magazine, vol. 43, no. 3, pp. 30–65, 2023.
- A. Kaptanoglu et al., “Physics-constrained, low-dimensional models for magnetohydrodynamics: First-principles and data-driven approaches,” Physical Review E, April 2020.
- S. Greydanus et al., “Hamiltonian neural networks,” in Advances in Neural Information Processing Systems, vol. 32, 2019.
- M. Cranmer et al., “Lagrangian neural networks,” In ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations, 2020.
- T. Beckers et al., “Gaussian process port-hamiltonian systems: Bayesian learning with physics prior,” in 2022 IEEE 61st Conference on Decision and Control (CDC). IEEE, 2022, pp. 1447–1453.
- G. Evangelisti and S. Hirche, “Physically consistent learning of conservative lagrangian systems with gaussian processes,” in 2022 IEEE 61st Conference on Decision and Control (CDC). IEEE, 2022, pp. 4078–4085.
- J. Liu et al., “Physics-informed neural networks to model and control robots: a theoretical and experimental investigation,” arXiv preprint arXiv:2305.05375, 2023.
- M. Lutter and J. Peters, “Combining physics and deep learning to learn continuous-time dynamics models,” The International Journal of Robotics Research, vol. 42, no. 3, pp. 83–107, 2023.
- M. T. Gillespie et al., “Learning nonlinear dynamic models of soft robots for model predictive control with neural networks,” in 2018 IEEE International Conference on Soft Robotics (RoboSoft). IEEE, 2018, pp. 39–45.
- S. L. Brunton et al., “Applying machine learning to study fluid mechanics,” Acta Mechanica Sinica, pp. 1–9, 2022.
- R. Perera et al., “Graph neural networks for simulating crack coalescence and propagation in brittle materials,” Computer Methods in Applied Mechanics and Engineering, 2022.
- F. Mahlknecht et al., “Using spectral submanifolds for nonlinear periodic control,” in 2022 IEEE 61st Conference on Decision and Control (CDC). IEEE, 2022, pp. 6548–6555.
- R. Swischuk et al., “Projection-based model reduction: Formulations for physics-based machine learning,” Computers & Fluids, vol. 179, pp. 704–717, 2019.
- K. Willcox and J. Peraire, “Balanced model reduction via the proper orthogonal decomposition,” AIAA Journal, vol. 40, no. 11, pp. 2323–2330, 2002.
- L. Fulton et al., “Latent-space dynamics for reduced deformable simulation,” Computer Graphics Forum, 2019.
- S. Shen et al., “High-order differentiable autoencoder for nonlinear model reduction,” ACM Transactions on Graphics, vol. 40, no. 4, 2021.
- B. Karasözen et al., “Structure preserving model order reduction of shallow water equations,” Mathematical Methods in the Applied Sciences, vol. 44, no. 1, pp. 476–492, 2021.
- J. S. Hesthaven et al., “Structure-preserving model order reduction of hamiltonian systems,” arXiv preprint arXiv:2109.12367, 2021.
- D. Bacciu et al., “A gentle introduction to deep learning for graphs,” Neural Networks, vol. 129, pp. 203–221, 2020.
- C. Armanini et al., “Soft robots modeling: A structured overview,” IEEE Transactions on Robotics, 2023.
- J. Zhu et al., “Challenges and outlook in robotic manipulation of deformable objects,” IEEE Robotics & Automation Magazine, vol. 29, no. 3, pp. 67–77, 2022.
- J. Gilmer et al., “Neural message passing for quantum chemistry,” in 34th International Conference on Machine Learning, vol. 3, 2017, pp. 2053–2070.
- W. Hamilton et al., “Inductive representation learning on large graphs,” Advances in Neural Information Processing Systems, pp. 1024–1034, 2017.
- R. Maulik et al., “Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders,” Physics of Fluids, vol. 33, no. 3, 2021.
- H. Gabbard et al., “Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy,” Nature Physics, vol. 18, no. 1, pp. 112–117, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
