Domain-decoupled Physics-informed Neural Networks with Closed-form Gradients for Fast Model Learning of Dynamical Systems

• URL: http://arxiv.org/abs/2408.14951v2
• Date: Wed, 28 Aug 2024 09:08:11 GMT
• Title: Domain-decoupled Physics-informed Neural Networks with Closed-form Gradients for Fast Model Learning of Dynamical Systems
• Authors: Henrik Krauss, Tim-Lukas Habich, Max Bartholdt, Thomas Seel, Moritz Schappler,
• Abstract summary: Physics-informed neural networks (PINNs) are trained using physical equations and can incorporate unmodeled effects by learning from data. We introduce the domain-decoupled physics-informed neural network (DD-PINN) to address current limitations of PINC in handling large and complex nonlinear dynamical systems.
• Score: 2.8730926763860687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physics-informed neural networks (PINNs) are trained using physical equations and can also incorporate unmodeled effects by learning from data. PINNs for control (PINCs) of dynamical systems are gaining interest due to their prediction speed compared to classical numerical integration methods for nonlinear state-space models, making them suitable for real-time control applications. We introduce the domain-decoupled physics-informed neural network (DD-PINN) to address current limitations of PINC in handling large and complex nonlinear dynamical systems. The time domain is decoupled from the feed-forward neural network to construct an Ansatz function, allowing for calculation of gradients in closed form. This approach significantly reduces training times, especially for large dynamical systems, compared to PINC, which relies on graph-based automatic differentiation. Additionally, the DD-PINN inherently fulfills the initial condition and supports higher-order excitation inputs, simplifying the training process and enabling improved prediction accuracy. Validation on three systems - a nonlinear mass-spring-damper, a five-mass-chain, and a two-link robot - demonstrates that the DD-PINN achieves significantly shorter training times. In cases where the PINC's prediction diverges, the DD-PINN's prediction remains stable and accurate due to higher physics loss reduction or use of a higher-order excitation input. The DD-PINN allows for fast and accurate learning of large dynamical systems previously out of reach for the PINC.

Related papers

• GradINN: Gradient Informed Neural Network [2.287415292857564]
  We propose a methodology inspired by Physics Informed Neural Networks (PINNs) GradINNs leverage prior beliefs about a system's gradient to constrain the predicted function's gradient across all input dimensions. We demonstrate the advantages of GradINNs, particularly in low-data regimes, on diverse problems spanning non time-dependent systems.
  arXiv  Detail & Related papers  (2024-09-03T14:03:29Z)
• Improved physics-informed neural network in mitigating gradient related failures [11.356695216531328]
  Physics-informed neural networks (PINNs) integrate fundamental physical principles with advanced data-driven techniques. PINNs face persistent challenges with stiffness in gradient flow, which limits their predictive capabilities. This paper presents an improved PINN to mitigate gradient-related failures.
  arXiv  Detail & Related papers  (2024-07-28T07:58:10Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• Physics guided neural networks for modelling of non-linear dynamics [0.0]
  This work demonstrates that injection of partially known information at an intermediate layer in a deep neural network can improve model accuracy, reduce model uncertainty, and yield improved convergence during the training. The value of these physics-guided neural networks has been demonstrated by learning the dynamics of a wide variety of nonlinear dynamical systems represented by five well-known equations in nonlinear systems theory.
  arXiv  Detail & Related papers  (2022-05-13T19:06:36Z)
• Physics-informed Neural Networks-based Model Predictive Control for Multi-link Manipulators [0.0]
  We discuss nonlinear model predictive control (NMPC) for multi-body dynamics via physics-informed machine learning methods. We present the idea of enhancing PINNs by adding control actions and initial conditions as additional network inputs. We present our results using our PINN-based MPC to solve a tracking problem for a complex mechanical system.
  arXiv  Detail & Related papers  (2021-09-22T15:31:24Z)
• Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update [49.948082497688404]
  Training large-scale deep neural networks (DNNs) currently requires a significant amount of energy, leading to serious environmental impacts. One promising approach to reduce the energy costs is representing DNNs with low-precision numbers. We jointly design a lowprecision training framework involving a logarithmic number system (LNS) and a multiplicative weight update training method, termed LNS-Madam.
  arXiv  Detail & Related papers  (2021-06-26T00:32:17Z)
• Physics-Informed Neural Nets-based Control [5.252190504926357]
  This work presents a new framework called Physics-Informed Neural Nets-based Control (PINC) PINC is amenable to control problems and able to simulate for longer-range time horizons that are not fixed beforehand. We showcase our method in the control of two nonlinear dynamic systems.
  arXiv  Detail & Related papers  (2021-04-06T14:55:23Z)
• A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations [69.73803123972297]
  We propose a DNN-based OPF predictor that is trained using a meta-learning (MTL) approach. The developed OPF-predictor is validated through simulations using benchmark IEEE bus systems.
  arXiv  Detail & Related papers  (2020-12-21T17:39:51Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.