Physically Consistent Neural ODEs for Learning Multi-Physics Systems
This addresses the unreliability of physics-agnostic models for practitioners in fields like engineering and physics, though it is incremental by building on existing Neural ODE and IPHS frameworks.
The paper tackles the problem of neural networks making physically inconsistent predictions in multi-physics systems by proposing Physically Consistent Neural ODEs (PC-NODEs), which leverage Irreversible port-Hamiltonian Systems to ensure thermodynamic consistency and demonstrate effectiveness on real-world building thermodynamics and simulated gas-piston systems.
Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, they might consequently make physically inconsistent predictions, which makes them unreliable in practice. In this paper, we leverage the framework of Irreversible port-Hamiltonian Systems (IPHS), which can describe most multi-physics systems, and rely on Neural Ordinary Differential Equations (NODEs) to learn their parameters from data. Since IPHS models are consistent with the first and second principles of thermodynamics by design, so are the proposed Physically Consistent NODEs (PC-NODEs). Furthermore, the NODE training procedure allows us to seamlessly incorporate prior knowledge of the system properties in the learned dynamics. We demonstrate the effectiveness of the proposed method by learning the thermodynamics of a building from the real-world measurements and the dynamics of a simulated gas-piston system. Thanks to the modularity and flexibility of the IPHS framework, PC-NODEs can be extended to learn physically consistent models of multi-physics distributed systems.