Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
146 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On Learning the Dynamical Response of Nonlinear Control Systems with Deep Operator Networks (2206.06536v2)

Published 14 Jun 2022 in math.DS, cs.NA, and math.NA

Abstract: We propose a Deep Operator Network~(DeepONet) framework to learn the dynamic response of continuous-time nonlinear control systems from data. To this end, we first construct and train a DeepONet that approximates the control system's local solution operator. Then, we design a numerical scheme that recursively uses the trained DeepONet to simulate the control system's long/medium-term dynamic response for given control inputs and initial conditions. We accompany the proposed scheme with an estimate for the error bound of the associated cumulative error. Furthermore, we design a data-driven Runge-Kutta~(RK) explicit scheme that uses the DeepONet forward pass and automatic differentiation to better approximate the system's response when the numerical scheme's step size is sufficiently small. Numerical experiments on the predator-prey, pendulum, and cart pole systems confirm that our DeepONet framework learns to approximate the dynamic response of nonlinear control systems effectively.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. JAX: composable transformations of Python+NumPy programs. URL: http://github.com/google/jax.
  2. Openai gym. arXiv preprint arXiv:1606.01540 .
  3. Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proceedings of the national academy of sciences 113, 3932–3937.
  4. Sparse identification of nonlinear dynamics with control (sindyc). IFAC-PapersOnLine 49, 710–715.
  5. Deepm&mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks. Journal of Computational Physics 436, 110296.
  6. Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Transactions on Neural Networks 6, 911–917.
  7. Multi-input cnn based vibro-acoustic fusion for accurate fault diagnosis of induction motor. Engineering Applications of Artificial Intelligence 120, 105872.
  8. Power system toolbox. Cherry Tree Scientific Software 48, 53.
  9. A multi-stage deep learning based algorithm for multiscale model reduction. Journal of Computational and Applied Mathematics 394, 113506.
  10. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems 2, 303–314.
  11. Gaussian processes for data-efficient learning in robotics and control. IEEE transactions on pattern analysis and machine intelligence 37, 408–423.
  12. Model-based reinforcement learning for semi-markov decision processes with neural odes. Advances in Neural Information Processing Systems 33, 19805–19816.
  13. Hei: hybrid explicit-implicit learning for multiscale problems. arXiv preprint arXiv:2109.02147 .
  14. Reinforcement learning for bluff body active flow control in experiments and simulations. Proceedings of the National Academy of Sciences 117, 26091–26098.
  15. Correct equations for the dynamics of the cart-pole system. Center for Cognitive and Neural Studies (Coneural), Romania .
  16. Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 .
  17. A first course in the numerical analysis of differential equations. 44, Cambridge university press.
  18. Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 .
  19. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  20. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895 .
  21. B-deeponet: An enhanced bayesian deeponet for solving noisy parametric pdes using accelerated replica exchange sgld. Journal of Computational Physics 473, 111713.
  22. Multi-variance replica exchange stochastic gradient mcmc for inverse and forward bayesian physics-informed neural network. arXiv preprint arXiv:2107.06330 .
  23. Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators. arXiv preprint arXiv:1910.03193 .
  24. Learning nonlinear operators via deeponet based on the universal approximation theorem of operators. Nature Machine Intelligence 3, 218–229.
  25. A fault diagnosis approach based on 2d-vibration imaging for bearing faults. Journal of Vibration Engineering & Technologies , 1–14.
  26. A self-adaptive multiple-fault diagnosis system for rolling element bearings. Measurement Science and Technology 33, 125018.
  27. Dae-pinn: a physics-informed neural network model for simulating differential algebraic equations with application to power networks. Neural Computing and Applications 35, 3789–3804.
  28. Deeponet-grid-uq: A trustworthy deep operator framework for predicting the power grid’s post-fault trajectories. Neurocomputing 535, 166–182.
  29. Deep dynamics models for learning dexterous manipulation, in: Conference on Robot Learning, PMLR. pp. 1101–1112.
  30. Generalizing koopman theory to allow for inputs and control. SIAM Journal on Applied Dynamical Systems 17, 909–930.
  31. Data-driven learning of nonautonomous systems. SIAM Journal on Scientific Computing 43, A1607–A1624.
  32. Data driven governing equations approximation using deep neural networks. Journal of Computational Physics 395, 620–635.
  33. Multistep neural networks for data-driven discovery of nonlinear dynamical systems. arXiv preprint arXiv:1801.01236 .
  34. Generalized joint probability density function formulation inturbulent combustion using deeponet. arXiv preprint arXiv:2104.01996 .
  35. Learning partial differential equations via data discovery and sparse optimization. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 473, 20160446.
  36. Neupde: Neural network based ordinary and partial differential equations for modeling time-dependent data, in: Mathematical and Scientific Machine Learning, PMLR. pp. 352–372.
  37. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming, in: Machine learning proceedings 1990. Elsevier, pp. 216–224.
  38. Reinforcement learning: An introduction. MIT press.
  39. Understanding and mitigating gradient flow pathologies in physics-informed neural networks. SIAM Journal on Scientific Computing 43, A3055–A3081.
  40. Learning the solution operator of parametric partial differential equations with physics-informed deeponets. Science advances 7, eabi8605.
  41. Benchmarking model-based reinforcement learning. arXiv preprint arXiv:1907.02057 .
  42. Computer control: An overview. IFAC Professional Brief 1, 2.
  43. Belnet: Basis enhanced learning, a mesh-free neural operator. arXiv preprint arXiv:2212.07336 .
Citations (17)
View on Semantic Scholar

Summary

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

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