Application of an Artificial Neural Network (ANN) for predicting low-GWP refrigerant boiling heat transfer inside Brazed Plate Heat Exchangers (BPHE)

•This paper presents an ANN model for refrigerant boiling inside BPHE.•The ANN model accounts for BPHE geometry, operating conditions and refrigerant properties.•A database of 1760 points on refrigerant boiling inside BPHE is presented.•The database includes 15 plate geometries and 14 refrigerants.•The ANN model predicts the database with a MAPE of 4.8%. This paper presents an Artificial Neural Network (ANN) model for predicting refrigerant boiling heat transfer coefficients inside Brazed Plate Heat Exchangers (BPHE). The model accounts for the effect of plate geometry, operating conditions and refrigerant properties. The model shows a fair agreement with a database of 1760 data points comprising 15 plate geometries and 16 refrigerants (including 4 natural refrigerants and 6 other low-GWP refrigerants). The Mean Absolute Percentage Error (MAPE) of the model predictions is 4.8%. The ANN model exhibits a better predictive capability than most of the state-of-the-art analytical-computational procedures for boiling inside BPHE available in the open literature. The characteristic parameters of the ANN model are fully reported in the paper.