Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning

Abstract

In this work, we introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To improve prediction accuracy while reducing network size, Dissipative SymODEN encodes the port-Hamiltonian dynamics with energy dissipation and external input into the design of its computation graph and learns the dynamics in a structured way. The learned model, by revealing key aspects of the system, such as the inertia, dissipation, and potential energy, paves the way for energy-based controllers.

arXiv commentPublished at ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations (DeepDiffEq)

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Continuous control with deep reinforcement learning
• Hamiltonian Neural Networks
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
• Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
• Learning Dynamical Systems from Partial Observations
• A General Framework for Structured Learning of Mechanical Systems

Cited by in corpus (20)

• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• Machine-Learning Non-Conservative Dynamics for New-Physics Detection
• Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
• Structure-preserving Sparse Identification of Nonlinear Dynamics for Data-driven Modeling
• Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling
• Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
• Learning Potentials of Quantum Systems using Deep Neural Networks
• One-Shot Transfer Learning of Physics-Informed Neural Networks
• Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
• Learning Dissipative Neural Dynamical Systems
• Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data
• Learning Dynamics Models with Stable Invariant Sets
• Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control
• SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
• Reversible and irreversible bracket-based dynamics for deep graph neural networks
• Identifying Physical Law of Hamiltonian Systems via Meta-Learning
• Learning dissipative Hamiltonian dynamics with reproducing kernel Hilbert spaces and random Fourier features
• Can we learn gradients by Hamiltonian Neural Networks?