Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Synthesis of Data-Driven Nonlinear State Observers using Lipschitz-Bounded Neural Networks (2310.03187v1)

Published 4 Oct 2023 in eess.SY, cs.SY, and math.OC

Abstract: This paper focuses on the model-free synthesis of state observers for nonlinear autonomous systems without knowing the governing equations. Specifically, the Kazantzis-Kravaris/Luenberger (KKL) observer structure is leveraged, where the outputs are fed into a linear time-invariant (LTI) system to obtain the observer states, which can be viewed as the states nonlinearly transformed by an immersion mapping, and a neural network is used to approximate the inverse of the nonlinear immersion and estimate the states. In view of the possible existence of noises in output measurements, this work proposes to impose an upper bound on the Lipschitz constant of the neural network for robust and safe observation. A relation that bounds the generalization loss of state observation according to the Lipschitz constant, as well as the $H_2$-norm of the LTI part in the KKL observer, is established, thus reducing the model-free observer synthesis problem to that of Lipschitz-bounded neural network training, for which a direct parameterization technique is used. The proposed approach is demonstrated on a chaotic Lorenz system.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. C. Kravaris and J. C. Kantor, “Geometric methods for nonlinear process control. 1. background,” Ind. Eng. Chem. Res., vol. 29, no. 12, pp. 2295–2310, 1990.
  2. S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems,” Proc. Natl. Acad. Sci. U.S.A., vol. 113, no. 15, pp. 3932–3937, 2016.
  3. J. Schoukens and L. Ljung, “Nonlinear system identification: A user-oriented road map,” IEEE Control Syst. Mag., vol. 39, no. 6, pp. 28–99, 2019.
  4. Y. M. Ren, M. S. Alhajeri, J. Luo, S. Chen, F. Abdullah, Z. Wu, and P. D. Christofides, “A tutorial review of neural network modeling approaches for model predictive control,” Comput. Chem. Eng., vol. 165, p. 107956, 2022.
  5. H. J. van Waarde, J. Eising, M. K. Camlibel, and H. L. Trentelman, “The informativity approach to data-driven analysis and control,” arXiv preprint arXiv:2302.10488, 2023.
  6. T. Martin, T. B. Schön, and F. Allgöwer, “Guarantees for data-driven control of nonlinear systems using semidefinite programming: A survey,” arXiv preprint arXiv:2306.16042, 2023.
  7. Z.-S. Hou and Z. Wang, “From model-based control to data-driven control: Survey, classification and perspective,” Inform. Sci., vol. 235, pp. 3–35, 2013.
  8. R. Nian, J. Liu, and B. Huang, “A review on reinforcement learning: Introduction and applications in industrial process control,” Comput. Chem. Eng., vol. 139, p. 106886, 2020.
  9. W. Tang and P. Daoutidis, “Data-driven control: Overview and perspectives,” in American Control Conference (ACC).   IEEE, 2022, pp. 1048–1064.
  10. C. Kravaris, J. Hahn, and Y. Chu, “Advances and selected recent developments in state and parameter estimation,” Comput. Chem. Eng., vol. 51, pp. 111–123, 2013.
  11. P. Bernard, V. Andrieu, and D. Astolfi, “Observer design for continuous-time dynamical systems,” Annu. Rev. Control, 2022.
  12. D. Luenberger, “Observers for multivariable systems,” IEEE Trans. Autom. Control, vol. 11, no. 2, pp. 190–197, 1966.
  13. N. Kazantzis and C. Kravaris, “Nonlinear observer design using Lyapunov’s auxiliary theorem,” Syst. Control Lett., vol. 34, no. 5, pp. 241–247, 1998.
  14. V. Andrieu and L. Praly, “On the existence of a Kazantzis-Kravaris/Luenberger observer,” SIAM J. Control Optim., vol. 45, no. 2, pp. 432–456, 2006.
  15. P. Bernard and V. Andrieu, “Luenberger observers for nonautonomous nonlinear systems,” IEEE Trans. Autom. Control, vol. 64, no. 1, pp. 270–281, 2018.
  16. L. C. Ramos, F. Di Meglio, V. Morgenthaler, L. F. F. da Silva, and P. Bernard, “Numerical design of Luenberger observers for nonlinear systems,” in 59th Conference on Decision and Control (CDC).   IEEE, 2020, pp. 5435–5442.
  17. M. Buisson-Fenet, L. Bahr, and F. Di Meglio, “Towards gain tuning for numerical KKL observers,” arXiv preprint, 2022, arXiv:2204.00318.
  18. M. U. B. Niazi, J. Cao, X. Sun, A. Das, and K. H. Johansson, “Learning-based design of Luenberger observers for autonomous nonlinear systems,” arXiv preprint, 2022, arXiv:2210.01476.
  19. K. Miao and K. Gatsis, “Learning robust state observers using neural ODEs,” arXiv preprint, 2022, arXiv:2212.00866.
  20. S. Huang, N. Papernot, I. Goodfellow, Y. Duan, and P. Abbeel, “Adversarial attacks on neural network policies,” arXiv preprint arXiv:1702.02284, 2017.
  21. H. Zhang, Y. Yu, J. Jiao, E. Xing, L. El Ghaoui, and M. Jordan, “Theoretically principled trade-off between robustness and accuracy,” in Int. Conf. Mach. Learn.   PMLR, 2019, pp. 7472–7482.
  22. M. Fazlyab, A. Robey, H. Hassani, M. Morari, and G. Pappas, “Efficient and accurate estimation of Lipschitz constants for deep neural networks,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  23. F. Latorre, P. Rolland, and V. Cevher, “Lipschitz constant estimation of neural networks via sparse polynomial optimization,” arXiv preprint arXiv:2004.08688, 2020.
  24. P. Pauli, A. Koch, J. Berberich, P. Kohler, and F. Allgöwer, “Training robust neural networks using lipschitz bounds,” IEEE Control Systems Lett., vol. 6, pp. 121–126, 2021.
  25. R. Wang and I. Manchester, “Direct parameterization of lipschitz-bounded deep networks,” in International Conference on Machine Learning.   PMLR, 2023, pp. 36 093–36 110.
  26. L. Brivadis, V. Andrieu, P. Bernard, and U. Serres, “Further remarks on KKL observers,” Syst. Control Lett., vol. 172, p. 105429, 2023.
  27. M. Revay, R. Wang, and I. R. Manchester, “Recurrent equilibrium networks: Flexible dynamic models with guaranteed stability and robustness,” IEEE Trans. Autom. Control, 2023, in press.
  28. Y. Zheng, L. Furieri, A. Papachristodoulou, N. Li, and M. Kamgarpour, “On the equivalence of youla, system-level, and input–output parameterizations,” IEEE Trans. Autom. Control, vol. 66, no. 1, pp. 413–420, 2020.
  29. W. Tang, “Data-driven state observation for nonlinear systems based on online learning,” AIChE J., vol. 69, no. (in press), p. e18224, 2023.
  30. W. Tang and P. Daoutidis, “Dissipativity learning control (DLC): A framework of input–output data-driven control,” Comput. Chem. Eng., vol. 130, p. 106576, 2019.
  31. ——, “Dissipativity learning control (DLC): Theoretical foundations of input–output data-driven model-free process control,” Syst. Control Lett., vol. 147, p. 104831, 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now