Neural network based prediction method for preventing condensation in chilled ceiling systems

被引：43

作者：

Ge, Gaoming ^{[1
]}

Xiao, Fu ^{[1
]}

Wang, Shengwei ^{[1
]}

机构：

[1] Hong Kong Polytech Univ, Dept Bldg Serv Engn, Kowloon, Hong Kong, Peoples R China

来源：

ENERGY AND BUILDINGS | 2012年 / 45卷

关键词：

Dedicated outdoor air system; Chilled ceiling; Condensation prevention; Neural network; LOAD PREDICTION; BUILDINGS; PERFORMANCE; PANELS; MODEL; HEAT; TIME;

D O I：

10.1016/j.enbuild.2011.11.017

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

Condensation is prone to occur at the startup moment in chilled ceiling systems, due to the infiltration and accumulation of moisture during system-off. To prevent condensation, an effective method is to operate the dedicated outdoor air system (DOAS) to dehumidify indoor air before operating chilled ceiling system. The pre-dehumidification time is critical. However, there is little experience in determining the pre-dehumidification time in both research and practice. In this study, neural network (NN) is used to predict condensation risk and the optimal pre-dehumidification time in chilled ceiling systems. Two NN models are developed to predict the temperature on the surface of chilled ceiling and indoor air dew-point temperature at the startup moment so as to evaluate the risk of condensation. The third NN model is developed to predict the optimal pre-humidification time for condensation prevention. Both training data and validation data are obtained from simulation tests in TRNSYS. The results show that 30 min pre-dehumidification is sufficient for the simulated building in Hong Kong. The influence of infiltration rate on the pre-dehumidification time is also investigated. This study also shows that NN-based method can be used for predictive control for condensation prevention in chilled ceiling systems. (c) 2011 Elsevier B.V. All rights reserved.

引用

页码：290 / 298

页数：9

共 26 条

[1] Energy conservation in buildings through efficient A/C control using neural networks [J].

Ben-Nakhi, AE ;

Mahmoud, MA .

APPLIED ENERGY, 2002, 73 (01) :5-23

[2] Cooling load prediction for buildings using general regression neural networks [J].

Ben-Nakhi, AE ;

Mahmoud, MA .

ENERGY CONVERSION AND MANAGEMENT, 2004, 45 (13-14) :2127-2141

[3]

Conroy C.L., 2001, ASHRAE T, V107, P578

[4] Radiant ceiling systems coupled to its environment part 1: Experimental analysis [J].

Fonseca, Nestor ;

Cuevas, Cristian ;

Lemort, Vincent .

APPLIED THERMAL ENGINEERING, 2010, 30 (14-15) :2187-2195

[5] Radiant ceiling systems coupled to its environment part 2: Dynamic modeling and validation [J].

Fonseca, Nestor ;

Bertagnolio, Stephane ;

Cuevas, Cristian .

APPLIED THERMAL ENGINEERING, 2010, 30 (14-15) :2196-2203

[6]

Ge G.M., 2010, P 8 INT C SYST SIM B

[7] Model-based optimal control of a dedicated outdoor air-chilled ceiling system using liquid desiccant and membrane-based total heat recovery [J].

Ge, Gaoming ;

Xiao, Fu ;

Xu, Xinhua .

APPLIED ENERGY, 2011, 88 (11) :4180-4190

[8] Control strategies for a liquid desiccant air-conditioning system [J].

Ge, Gaoming ;

Xiao, Fu ;

Niu, Xiaofeng .

ENERGY AND BUILDINGS, 2011, 43 (06) :1499-1507

[9] Performance of chilled ceiling panels using phase change material slurries as the heat transport medium [J].

Griffiths, P. W. ;

Eames, P. C. .

APPLIED THERMAL ENGINEERING, 2007, 27 (10) :1756-1760

[10] Thermal comfort and energy consumption of the radiant ceiling panel system. Comparison with the conventional all-air system [J].

Imanari, T ;

Omori, T ;

Bogaki, K .

ENERGY AND BUILDINGS, 1999, 30 (02) :167-175

← 1 2 3 →