Physics-Informed Gas Lifting Oil Well Modelling using Neural Ordinary Differential Equations

Abstract

Modelling of oil well systems is important for a wide range of petroleum scientific and oil industrial processes. Considering the uncertainty of the measurements and the demand for empirical knowledge, a purely first-principle model and a black-box model based on data are not sufficient for accurately describing an oil well system. Thus, there is a growing body of literature that recognizes the importance of data-driven methods combined with physical knowledge. However, the application of combination methods for dynamic nonlinear systems is still challenging. In this work, we demonstrate the application of a physics-informed neural network to a gas lifting oil well system. The neural ordinary differential equation is the main tool for the modeling and the simulation is examined in Julia programming language. The advantage and drawbacks of the physics-informed data-driven method are analyzed.