Accurate modeling of vapor–liquid equilibria of binary mixtures of refrigerants using intelligent models. (September 2018)

• Record Type: Journal Article
• Authors: Najafi-Marghmaleki, Adel; Barati-Harooni, Ali; Khosravi-Nikou, Mohammad Reza
• Is Part Of: International journal of refrigeration. Volume 93(2018)
• Page Start: 65
• Page End: 78
• Publication Date: 2018-09
• Subjects: Low GWP refrigerants -- Vapor–liquid equilibrium -- Equation of State (EoS) -- Intelligent Model; Frigorigènes à faible GWP -- Équilibre vapeur-liquide -- Équation d'état -- Modèle intelligent; Refrigeration and refrigerating machinery -- Periodicals; 621.56
• DOI: 10.1016/j.ijrefrig.2018.05.027
• Languages: English
• ISSNs: 0140-7007

Abstract

Highlights: Four models were developed for prediction of phase behavior of binary refrigerant systems. The four computer based models are RBF-NN, MLP-NN, CSA-LSSVM and Hybrid-ANFIS. The performance of the developed models is evaluated by using statistical quality measure approaches. The outcomes of the developed models are compared with PR-EoS and SRK-EoS. The performance of the developed models is better than the studied thermodynamic models. Abstract: Developing simple, accurate and general models for prediction of different properties of hydrofluorocarbons (HFCs) and hydrocarbons (HCs) with hydrofluoro-olefins (HFOs) mixtures is of crucial importance in the design of new refrigeration system. In this communication, four computer based models namely Radial Basis Function Neural Network, Multilayer Perceptron Neural Network, Least Square Support Vector Machine optimized by Coupled Simulated Annealing and Adaptive Neuro Fuzzy Inference System trained by Hybrid method were used for prediction of vapor–liquid equilibrium (VLE) for binary mixtures of different HFC and HC compounds with HFO refrigerants. Results reveal that the developed models are accurate and effective for prediction of experimental VLE data for different systems. However, the RBF-NN model provides better predictions compared to other models. Moreover, the predictions of the developed models were better than the Peng-Robinson (PR) and Soave–Redlich–Kwong (SRK) equations of state (EoSs).