Abstract
In this study, we develop physics-informed neural networks (PINNs) to solve an isothermal fixed-bed (IFB) model for catalytic CO2 methanation. The PINN includes a feed-forward artificial neural network (FF-ANN) and physics-informed constraints, such as governing equations, boundary conditions, and reaction kinetics. The most effective PINN structure consists of 5–7 hidden layers, 256 neurons per layer, and a hyperbolic tangent (tanh) activation function. The forward PINN model solves the plug-flow reactor model of the IFB, whereas the inverse PINN model reveals an unknown effectiveness factor involved in the reaction kinetics. The forward PINN shows excellent extrapolation performance with an accuracy of 88.1% when concentrations outside the training domain are predicted using only one-sixth of the entire domain. The inverse PINN model identifies an unknown effectiveness factor with an error of 0.3%, even for a small number of observation datasets (e.g., 20 sets). These results suggest that forward and inverse PINNs can be used in the solution and system identification of fixed-bed models with chemical reaction kinetics.
Highlights
Power-to-gas technology using intermittent surplus renewable electricity has gained attention for mitigating CO2 emissions to the atmosphere [1,2]
As the CO2 methanation reaction is thermodynamically favored at low temperatures and high pressures [9], an isothermal fixed-bed reactor (IFB)
This study demonstrates that the forward and inverse physics-informed neural networks (PINNs) can solve fixed-bed models with highly nonlinear chemical reaction kinetics and identify unknown model parameters
Summary
Power-to-gas technology using intermittent surplus renewable electricity has gained attention for mitigating CO2 emissions to the atmosphere [1,2]. As the CO2 methanation reaction is thermodynamically favored at low temperatures and high pressures [9], an isothermal fixed-bed reactor (IFB). To develop advanced CO2 methanation technologies, researchers have explored the use of modeling and simulations in the optimization of reactor designs. Unknown physical model parameters are identified using both the well-trained forward PINN and external input/output datasets. Forward and inverse PINNs coupled with AD were developed for the solution and parameter identification of a highly nonlinear reaction rate model for catalytic. This study demonstrates that the forward and inverse PINNs can solve fixed-bed models with highly nonlinear chemical reaction kinetics and identify unknown model parameters
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have