A comparison between the modeling of a reciprocating compressor using artificial neural network and physical model

• This paper presents the development of two models, a physical model and an ANN model of a reciprocating compressor.
• Both models were compared at different development stages to emphasize the discrepancies among them.
• Both models are validated with experimental data for the refrigerants R1234yf and R134a.
• The quality of the predicted behavior of the ANN model was better than the quality of the physical model.

This article presents the development, validation, and comparison of two methods for modeling a reciprocating compressor. Initially, the physical mode is based on eight internal sub-processes that incorporate infinitesimal displacements according to the piston movement. Next, the analysis and modeling of the compressor through the application of artificial neural networks are presented. The input variables are: suction pressure, suction temperature, discharge pressure, and compressor rotation speed. The output parameters are: refrigerant mass flow rate, discharge temperature, and energy consumption. Both models are validated with experimental data for the refrigerants R1234yf and R134a; computer simulations show that mean relative errors are below ±10% with the physical model, and below ±1% when artificial neural networks are used. Additionally, the performance of the models is evaluated through the computation of the squared absolute error. Finally, these models are used to compute an energy comparison between both refrigerants.