A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations

Abstract

We investigate the use of discrete and continuous versions of physics-informed neural network methods for learning unknown dynamics or constitutive relations of a dynamical system. For the case of unknown dynamics, we represent all the dynamics with a deep neural network (DNN). When the dynamics of the system are known up to the specification of constitutive relations (that can depend on the state of the system), we represent these constitutive relations with a DNN. The discrete versions combine classical multistep discretization methods for dynamical systems with neural network based machine learning methods. On the other hand, the continuous versions utilize deep neural networks to minimize the residual function for the continuous governing equations. We use the case of a fedbatch bioreactor system to study the effectiveness of these approaches and discuss conditions for their applicability. Our results indicate that the accuracy of the trained neural network models is much higher for the cases where we only have to learn a constitutive relation instead of the whole dynamics. This finding corroborates the well-known fact from scientific computing that building as much structural information is available into an algorithm can enhance its efficiency and/or accuracy.

References in corpus (1)

• Nonparametric forecasting of low-dimensional dynamical systems

Cited by in corpus (5)

• Physics-informed deep learning for flow and deformation in poroelastic media
• HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
• Tensorized Transformer for Dynamical Systems Modeling
• Parameter identification for a damage model using a physics informed neural network
• Statistical Learning for Fluid Flows: Sparse Fourier divergence-free approximations