scholarly journals Predictive Modeling of a Paradigm Mechanical Cooling Tower Model: II. Optimal Best-Estimate Results with Reduced Predicted Uncertainties

Energies ◽  
2016 ◽  
Vol 9 (9) ◽  
pp. 747 ◽  
Author(s):  
Ruixian Fang ◽  
Dan Cacuci ◽  
Madalina Badea
Keyword(s):  
Predictive Modeling ◽  
Cooling Tower ◽  
Best Estimate ◽  
Tower Model

scholarly journals Operational cooling tower model (CTTOOL V1.0)

2015 ◽  
Author(s):  
S. Aleman ◽  
L. LocalDomainServers ◽  
A. Garrett
Keyword(s):  
Cooling Tower ◽  
Tower Model

Application of Artificial Neural Network for Modeling of Mechanical Cooling Tower

2011 ◽  
Vol 383-390 ◽  
pp. 7746-7749 ◽  
Author(s):  
Wei Shun Huang ◽  
Ching Wei Chen ◽  
Cheng Wen Lee ◽  
Ching Liang Chen ◽  
Tien Shuen Jan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Flow ◽  
Cooling Tower ◽  
Air Flow ◽  
Cooling Water ◽  
Computation Method ◽  
Cooling Load ◽  
Artificial Neural ◽  
Tower Model

The objective of the study is to focus on the application of the artificial neural network to configure a heat-radiating model for cooling towers within the parameters of fluctuating in air flow or cooling water flow. To achieve the objective, a cooling tower heat balancing equation have been used to instill the correlations between a cooling tower cooling load to the four predefined parameters. Based on the premise established, the parameters of a cooling tower’s air flow and cooling water flow in a modulated process are utilized in an experimental system for collecting relevant operating data. Lastly, the artificial neural network tool derived from the Matlab software is utilized to define the input parameters being – the cooling water temperature, ambient web-bulb temperature, cooling tower air flow, and cooling water flow, with an objective set to instilling a cooling tower model for defining a cooling tower cooling load. In addition, the tested figures are compared to the simulated figures for verifying the cooling tower model. By utilizing the method derived from the model, the mean error of between 0.72 and 2.13% is obtained, with R2 value rated at between 0.97 and 0.99. The experiment findings show a relatively high reliability that can be achieved for configuring a model by using the artificial neural network. With the support of an optimized computation method, the model can be applied as an optimization operating strategy for an air-conditioning system’s cooling water loop.

Sign in / Sign up

Export Citation Format

Share Document