Fast evaluation of refrigerant thermophysical properties using neural networks for transient simulations.

Accurate and efficient evaluations of refrigerant thermophysical properties and their partial derivatives are essential for transient simulations of thermal systems where several computations need to be executed at each integration time step. Since the utilization of an equation of state for retrieving properties based on a pair of independent inputs typically involves numerical iterations in solution procedures, when the input variables differ from the refrigerant state variables employed in dynamic models, a variety of approaches have been developed to explicitly approximate these properties based on the state variables including table lookup interpolation and curve fittings. This paper presents an alternative method that exploits physics-informed neural networks to model refrigerant properties explicitly from pressure and enthalpy and then to generate consistent partial derivatives by differentiating the neural networks. Computational speed and accuracy of the proposed approach are demonstrated using transient heat exchanger simulations in Modelica and compared against other approaches.