Constrained Hamiltonian Systems and Physics-Informed Neural Networks: Hamilton-Dirac Neural Networks

Abstract

The effectiveness of the Physics Informed Neural Networks (PINNs) for learning the dynamics of constrained Hamiltonian systems is demonstrated using the Dirac theory of constraints for regular systems with holonomic constraints and systems with non-standard Lagrangians. By utilizing Dirac brackets, we derive the Hamilton-Dirac equations and minimize their residuals, incorporating also energy conservation and the Dirac constraints, using appropriate regularization terms in the loss function. The resulting PINNs, referred to as Hamilton-Dirac Neural Networks (HDNNs), successfully learn constrained dynamics without deviating from the constraint manifold. Two examples with holonomic constraints are presented: the nonlinear pendulum in Cartesian coordinates and a two-dimensional, elliptically restricted harmonic oscillator. In both cases, HDNNs exhibit superior performance in preserving energy and constraints compared to traditional explicit solvers. To demonstrate applicability in systems with singular Lagrangians, we computed the guiding center motion in a strong magnetic field starting from the guiding center Lagrangian. The imposition of energy conservation during the neural network training proved essential for accurately determining the orbits of the guiding center. The HDNN architecture enables the learning of parametric dependencies in constrained dynamics by incorporating a problem-specific parameter as an input, in addition to the time variable. Additionally, an example of semi-supervised, data-driven learning of guiding center dynamics with parameter inference is presented.

References in corpus (11)

• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Inferring solutions of differential equations using noisy multi-fidelity data
• Structure and structure-preserving algorithms for plasma physics
• Hamiltonian neural networks for solving equations of motion
• On Learning Hamiltonian Systems from Data
• Physics enhanced neural networks predict order and chaos
• Symplectic Learning for Hamiltonian Neural Networks
• Degenerate Variational Integrators for Magnetic Field Line Flow and Guiding Center Trajectories
• Neural network tokamak equilibria with incompressible flows