Machine learning-based prediction of the coefficient of performance for low global warming potential refrigerants in a vapor compression system

This study addresses the energy significance of the coefficient of performance (COP) in vapor compression systems and the practical need to forecast COP quickly and reliably. Because COP directly reflects the amount of cooling delivered per unit of input power, accurate prediction supports energy savings, refrigerant selection, and early-stage design decisions, especially for low global warming potential (GWP) refrigerants. Authors develop data-driven models to estimate COP without full thermodynamic calculations. A synthetic dataset of 2,000 samples is generated in the Engineering Equation Solver (EES) for four refrigerants (R1234yf, R134a, R290, R600a) by using five inputs: refrigerant type, evaporation temperature, condensing temperature, subcooling, and superheat. Five supervised learning algorithms are trained and compared: linear regression, polynomial regression, random forests, decision trees, and support vector machines. The study evaluates model performance using the coefficient of determination (R²), root mean squared error (RMSE), and mean absolute error (MAE) based on an 80/20 train/test split. Results show Polynomial Regression (degree 3) delivers the highest accuracy (R² ≈ 0.9999; RMSE ≈ 0.0071; MAE ≈ 0.0053), with Random Forest as the next strongest baseline. The findings suggest that lightweight, well-tuned regressors can provide fast, precise COP predictions, reduce analysis time, and guide system design and parameter optimization. The approach offers an accessible tool for engineers seeking efficient, low-carbon refrigeration solutions.