Constrained Neural Ordinary Differential Equations with Stability Guarantees

Abstract

Differential equations are frequently used in engineering domains, such as modeling and control of industrial systems, where safety and performance guarantees are of paramount importance. Traditional physics-based modeling approaches require domain expertise and are often difficult to tune or adapt to new systems. In this paper, we show how to model discrete ordinary differential equations (ODE) with algebraic nonlinearities as deep neural networks with varying degrees of prior knowledge. We derive the stability guarantees of the network layers based on the implicit constraints imposed on the weight's eigenvalues. Moreover, we show how to use barrier methods to generically handle additional inequality constraints. We demonstrate the prediction accuracy of learned neural ODEs evaluated on open-loop simulations compared to ground truth dynamics with bi-linear terms.

4 pages, Appendix

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Decoupled Weight Decay Regularization
• Deep Residual Learning for Image Recognition
• Neural Jump Stochastic Differential Equations
• IMEXnet: A Forward Stable Deep Neural Network

Cited by in corpus (5)

• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systems
• Learning Dynamics Models with Stable Invariant Sets
• Physics-Informed Neural State Space Models via Learning and Evolution
• A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks