Electronic expansion valve mass flow rate prediction based on dimensionless correlation and ANN model. (September 2015)

• Record Type: Journal Article
• Authors: Tian, Zhen; Gu, Bo; Qian, Cheng; Yang, Lin; Liu, Fen
• Is Part Of: International journal of refrigeration. Volume 57(2015:Sep.)
• Page Start: 1
• Page End: 10
• Publication Date: 2015-09
• Subjects: Artificial neural network -- Buckingham π-theorem -- Dimensionless correlation -- Electronic expansion valve -- Mass flow rate prediction -- R134a; Réseau neuronal artificiel -- Théorème de Buckingham p -- Corrélation adimensionnellle -- Détendeur électronique -- Prévision du debit massique -- R134a; Refrigeration and refrigerating machinery -- Periodicals; 621.56
• DOI: 10.1016/j.ijrefrig.2015.04.016
• Languages: English
• ISSNs: 0140-7007

Abstract

Abstract: Refrigerant mass flow rate through electronic expansion valve (EEV) makes significant sense for refrigeration system intelligent control and energy conservation. Objectives of this study were to present experimental data of R134a mass flow rate through EEV and to develop models for EEV mass flow rate prediction via two approaches: dimensionless correlation based on Buckingham π -theorem and artificial neural network (ANN) model based on dimensionless parameters. The database utilized for model training and test was comprised of our experimental data and data available in open literatures including R22, R407C, R410A and R134a. Compared with three existing dimensionless correlations, the proposed dimensionless correlation and ANN model demonstrated higher accuracy. The proposed dimensionless correlation gave mean relative error (MRE) of 6.60%, relative mean square error of (RMSE) 12.05 kg h −1 and correlation coefficient (R 2 ) of 0.9810. The ANN model with the configuration of 8-6-1 showed MRE, RMSE and R 2 of 3.97%, 7.59 kg h −1 and 0.9924, respectively. Highlights: Experimental data of R134a mass flow rate through EEV were presented. A dimensionless correlation and an ANN model were proposed for EEV mass flow rate prediction. The established models could be applied for 4 refrigerants with a wide operating range. Dimensionless parameters were utilized as ANN inputs. ANN with the configuration of 8-6-1 showed MRE, RMSE and R 2 of 3.97%, 7.59 kg h −1 and 0.9924, respectively.