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.

scholarly journals Experimental Investigation on Improvement of Wet Cooling Tower Efficiency with Diverse Packing Compaction Using ANN-PSO Algorithm

Energies ◽  
2020 ◽  
Vol 14 (1) ◽  
pp. 167
Author(s):  
Hasan Alimoradi ◽  
Madjid Soltani ◽  
Pooriya Shahali ◽  
Farshad Moradi Kashkooli ◽  
Razieh Larizadeh ◽  
...  
Keyword(s):  
Neural Network ◽  
Water Temperature ◽  
Water Flow ◽  
Flow Rate ◽  
Cooling Tower ◽  
Air Flow ◽  
Water Flow Rate ◽  
Pso Algorithm ◽  
Outlet Temperature ◽  
Air Flow Rate

In this study, a numerical and empirical scheme for increasing cooling tower performance is developed by combining the particle swarm optimization (PSO) algorithm with a neural network and considering the packing’s compaction as an effective factor for higher accuracies. An experimental setup is used to analyze the effects of packing compaction on the performance. The neural network is optimized by the PSO algorithm in order to predict the precise temperature difference, efficiency, and outlet temperature, which are functions of air flow rate, water flow rate, inlet water temperature, inlet air temperature, inlet air relative humidity, and packing compaction. The effects of water flow rate, air flow rate, inlet water temperature, and packing compaction on the performance are examined. A new empirical model for the cooling tower performance and efficiency is also developed. Finally, the optimized performance conditions of the cooling tower are obtained by the presented correlations. The results reveal that cooling tower efficiency is increased by increasing the air flow rate, water flow rate, and packing compaction.

scholarly journals A NILM method for cooling load disaggregation based on artificial neural network

2019 ◽  
Vol 111 ◽  
pp. 05020 ◽  
Author(s):  
Ziwei Xiao ◽  
Jiaqi Yuan ◽  
Wenjie Gang ◽  
Chong Zhang ◽  
Xinhua Xu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Energy Management ◽  
Residential Buildings ◽  
Building Energy ◽  
Cooling Load ◽  
Building Energy Management ◽  
Load Disaggregation ◽  
Artificial Neural ◽  
Cooling Loads

The demand of building energy management has increased due to high energy saving potentials. Load monitor and disaggregation can provide useful information for building energy management systems with detailed and individual loads of the building, so corresponding energy efficient measures can be taken to reduce the energy consumption of buildings. The technique is investigated widely in residential buildings known as Non-Intrusive Load Monitoring (NILM). However, relevant studies are not sufficient for non-residential buildings, especially for the cooling loads. This paper proposes a NILM method for cooling load disaggregation using artificial neural network. The cooling load is disaggregated into four categories: building envelope load, occupant load, equipment load and fresh air load. Two approaches are used to realize the load disaggregation: one is based on the Fourier transfer of the cooling loads, the other takes the cooling load, dry-bulb temperature and humidity of outdoor air, and time as inputs. By implementing the methods in a metro station, the performance of the proposed method can be obtained. Results show that both approaches can realize the load disaggregation accurately, with a RMSE less than 11.2. The second approach is recommended with a higher accuracy.

scholarly journals PENERAPAN MODEL BERBASIS ARTIFICIAL NEURAL NETWORK UNTUK MEMPREDIKSI KUALITAS AIR DI SUNGAI SUBAYANG KABUPATEN KAMPAR

2020 ◽  
Vol 14 (1) ◽  
pp. 18
Author(s):  
Endang Agus Damanhuri ◽  
Yusni Ikhwan Siregar ◽  
Elfizar Elfizar
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Water Flow ◽  
Mean Squared Error ◽  
Human Life ◽  
Water Quality Management ◽  
River Quality ◽  
Artificial Neural

Water quality management is very important to do, because water is an inseparable part of everyday human life. Monitoring water quality is a way to maintain the quality of waters, especially rivers. River quality monitoring that is usually done requires a lot of equipment, effort and expertise so that its application becomes expensive and complicated. Technology that is growing rapidly nowadays puts forward artificial intelligence as the backbone of the Industrial Revolution 4.0 which promises many conveniences for industry and government. One of artificial intelligence technology is machine learning with Artificial Neural Network algorithm which is commonly used to predict or forecast a future value. This artificial neural network can be used to help monitor river water quality. The objective of this research to develop Artificial Neural Networks (ANN) model to predict the paramater of river quality (DO, pH, turbidity, temperature, water flow, conductivity) in the Subayang River, Kampar Regency, using software Rapidminer. The performance of the ANN models was evaluated using root mean squared error (RMSE) and correlation squared (R2) as a second comparison, then the results of the testing implementation are compared with direct measurements in the field. With the RMSE values obtained in the test results of each parameter DO = 1.613, pH = 0.098, turbidity = 4.730, temperature = 0.493, water flow = 0.121 and conductivity = 0.909. The lower the RMSE level, the closer it is to Artificial Neural Network accuracy for value prediction.  

Sign in / Sign up

Export Citation Format

Share Document