An electronic expansion valve modeling framework development using artificial neural network: A case study on VRF systems. (November 2019)

• Record Type: Journal Article
• Authors: Wan, Hanlong; Cao, Tao; Hwang, Yunho; Oh, Saikee
• Is Part Of: International journal of refrigeration. Volume 107(2019)
• Page Start: 114
• Page End: 127
• Publication Date: 2019-11
• Subjects: Electronic expansion valve -- Artificial neuron network -- Principal component analysis -- Variable refrigerant flow; Détendeur électronique -- Réseau neuronal artificiel -- Analyse du composant principal -- Débit de frigorigène variable; Refrigeration and refrigerating machinery -- Periodicals; 621.56
• DOI: 10.1016/j.ijrefrig.2019.08.018
• Languages: English
• ISSNs: 0140-7007

Abstract

Highlights: An ANN model was used to predict mass flow rate through EEV. We optimized input parameter number, hidden neuron number and transfer function pairs. By optimizing ANN model parameters, ANN model accuracy was improved. Based on field test data, ANN model had a better performance than power-law model. Abstract: Electronic expansion valves (EEV) are widely used in variable refrigerant flow systems (VRF) to control the mass flow rate of each indoor unit. EEV model is used to predict the mass flow rate through an EEV. While the power-law correlation method has been used to build the EEV model so far, Artificial Neural Network (ANN) methods have been adapted to model the EEV with a fixed speed compressor thanks to its higher accuracy. However, the EEV is typically working with the variable speed compressor in a VRF system. In addition, the parameters used in ANN modeling could be further optimized. The objective of this study is to develop an EEV modeling framework and optimize the input parameter number and hidden neuron number. We presented the framework through an EEV model development for a VRF system. For these, we used the field test data, applied a principal components analysis approach in optimizing the ANN input parameter number, and investigated the proper number of hidden neurons and appropriate transfer function pairs. We found the performance of the ANN model would not improve much as the number of input parameters and the number of hidden neurons reached a threshold. Only three transfer function pairs are suitable for this case in total nine groups we studied. Our ANN model has the average absolute deviation of 2.2%. The framework can be easily applied to EEV modeling in other VRF and air condition systems with necessary data support.