Data mining techniques for thermophysical properties of refrigerants

被引：22

作者：

Kuecueksille, Ecir Ugur ^{[1
]}

Selbas, Resat ^{[1
]}

Sencan, Arzu ^{[1
]}

机构：

[1] Suleyman Demirel Univ, Dept Mech Educ, Tech Educ Fac, TR-32260 Isparta, Turkey

来源：

ENERGY CONVERSION AND MANAGEMENT | 2009年 / 50卷 / 02期

关键词：

Refrigerant; Thermophysical properties; Data mining; Linear regression; Multi layer perception; Pace regression; Simple linear regression; Sequential minimal optimization; KStar; Additive regression; M5 model tree; Decision table; M5 ' Rules; THERMODYNAMIC PROPERTIES; NEURAL-NETWORKS; SOFTWARE; DESIGN;

D O I：

10.1016/j.enconman.2008.09.002

中图分类号：

O414.1 [热力学];

学科分类号：

摘要：

This study presents ten modeling techniques within data mining process for the prediction of thermophysical properties of refrigerants (R134a, R404a, R407c and R410a). These are linear regression (LR), multi layer perception (MLP), pace regression (PR), simple linear regression (SLR), sequential minimal optimization (SMO), I(Star, additive regression (AR), M5 model tree, decision table (DT), M5'Rules models. Relations depending on temperature and pressure were carried out for the determination of thermophysical properties as the specific heat capacity, viscosity, heat conduction coefficient, density of the refrigerants. Obtained model results for every refrigerant were compared and the best model was investigated. Results indicate that use of derived formulations from these techniques will facilitate design and optimize of heat exchangers which is component of especially vapor compression refrigeration system. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：399 / 412

页数：14

共 50 条

[21] Thermophysical Properties for Environmental-Friendly Refrigerants of Trifluoroiodomethane and Difluoromethane
DuanYuanyuan Zhu Mingshan Shi Lin HanLizhong(Department of Thermal Engineering
Science Foundation in China, 2002, (01) : 32 - 36
[22] CALCULATION OF THE THERMOPHYSICAL PROPERTIES OF THE TWO-PHASE FLUID REFRIGERANTS
Ionescu, Constantin
Necula, Horia
UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2009, 71 (03): : 3 - 14
[23] Predicting thermophysical properties of alkanes and refrigerants using machine learning algorithms
Rathod, Kiran
Ravula, Sai Charan
Kommireddi, Prasanna Sai Chandra
Thangeda, Rahul
Kikugawa, Gota
Chilukoti, Hari Krishna
FLUID PHASE EQUILIBRIA, 2024, 578
[24] Use of universal correlations to predict some thermophysical properties of alternative refrigerants
Fialho, PS
de Castro, CAN
HIGH TEMPERATURES-HIGH PRESSURES, 2001, 33 (05) : 611 - 625
[25] Prediction of thermophysical properties of mixed refrigerants using artificial neural network
Sencan, Arzu
Kose, Ismail Ilke
Selbas, Resat
ENERGY CONVERSION AND MANAGEMENT, 2011, 52 (02) : 958 - 974
[26] DATA MINING DATA MINING CONCEPTS AND TECHNIQUES
Agarwal, Shivam
2013 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE AND RESEARCH ADVANCEMENT (ICMIRA 2013), 2013, : 203 - 207
[27] Estimation of thermophysical properties of lubricating oils and their solutions with refrigerants: An appraisal of existing methods
Conde, MR
APPLIED THERMAL ENGINEERING, 1996, 16 (01) : 51 - 61
[28] Estimation of thermophysical properties of lubricating oils and their solutions with refrigerants: an appraisal of existing methods
M. Conde Engineering, Zurich, Switzerland
Appl Therm Eng, 1 (51-61):
[29] Data mining techniques in index techniques
Teh, YW
Zaitun, AB
INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, 2003, : 331 - 339
[30] Prediction of the thermophysical properties and phase behavior of alternative refrigerants via computational chemistry.
Fermeglia, M
Pricl, S
ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2002, 224 : U616 - U616

← 1 2 3 4 5 →