Neural network and polynomial model to improve the coefficient of performance prediction for solar intermittent refrigeration system

被引：12

作者：

Escobedo-Trujillo, B. A. ^{[1
]}

Colorado, D. ^{[2
]}

Rivera, W. ^{[3
]}

Alaffita-Hernandez, F. A. ^{[4
]}

机构：

[1] Univ Veracruzana, Fac Ingn, Campus Coatzacoalcos,Ave Univ Km 7-5, Coatzacoalcos 96535, Veracruz, Mexico

[2] Univ Veracruzana, Ctr Invest Recursos Energet & Sustentables, Ave Univ Km 7-5, Coatzacoalcos 96535, Veracruz, Mexico

[3] Univ Nacl Autonoma Mexico, Inst Energias Renovables, Privada Xochicalco S-N, Temixco 62580, Mor, Mexico

[4] Univ Veracruzana, Fac Matemat, Posgrad Matemat, Circuito Gonzalo Aguirre Beltran S-N, Xalapa 91090, Veracruz, Mexico

来源：

SOLAR ENERGY | 2016年 / 129卷

关键词：

Lithium bromide solution; Multivariable fitting; Residual analysis; Gaussian distribution; Correlation matrix; COP PREDICTION; HEAT TRANSFORMER; ICE PRODUCTION;

D O I：

10.1016/j.solener.2016.01.041

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

This study presents a novel hybrid methodology to estimate the coefficient of performance in an absorption intermittent cooling system; the system is for ice production and operates with an ammonia/lithium nitrate mixture. The hybrid model integrates a polynomial fitting method and an artificial neural network model to improve the network performance and the estimation of the COPs. The improvement uses fewer hidden neurons without sacrificing accuracy in the prediction. The proposed hybrid model has two neurons in the input and two in the hidden layers and shows better results than those obtained through polynomial fitting or artificial neural networks separately. The developed model presents an excellent agreement between experimental and simulated values of the coefficient of performance with a determination coefficient R-2 > 0.9978. (C) 2016 Elsevier Ltd. All rights reserved.

引用

页码：28 / 37

页数：10

共 15 条

[1]

[Anonymous], PROBABILIDAD APLICAC

[2]

[Anonymous], 2006, Introduction to Linear Regression Analysis

[3] Neural network and polynomial approximated thermal comfort models for HVAC systems [J].

Castilla, M. ;

Alvarez, J. D. ;

Ortega, M. G. ;

Arahal, M. R. .

BUILDING AND ENVIRONMENT, 2013, 59 :107-115

[4] Optimal operation conditions for a single-stage heat transformer by means of an artificial neural network inverse [J].

Colorado, D. ;

Hernandez, J. A. ;

Rivera, W. ;

Martinez, H. ;

Juarez, D. .

APPLIED ENERGY, 2011, 88 (04) :1281-1290

[5]

Demuth H., 2003, NEURAL NETWORK TOOLB

[6]

Devore JL., 2004, PROBABILITY STAT ENG

[7]

Escobedo-Trujillo BA, 2014, REV MEX ING QUIM, V13, P907

[8] Prediction of brightness and surface area kinetics during coffee roasting [J].

Hernandez, J. A. ;

Heyd, B. ;

Trystram, G. .

JOURNAL OF FOOD ENGINEERING, 2008, 89 (02) :156-163

[9] Uncertainty analysis of COP prediction in a water purification system integrated into a heat transformer using several artificial neural networks [J].

Hernandez, J. A. ;

Colorado, D. .

DESALINATION AND WATER TREATMENT, 2013, 51 (7-9) :1443-1456

[10] Optimal COP prediction of a solar intermittent refrigeration system for ice production by means of direct and inverse artificial neural networks [J].

Hernandez, J. A. ;

Rivera, W. ;

Colorado, D. ;

Moreno-Quintanar, G. .

SOLAR ENERGY, 2012, 86 (04) :1108-1117

← 1 2 →