Veerayut Lersbamrungsuk. Artificial neural network modeling for prediction of fouling in heat exchangers. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2021.
Artificial neural network modeling for prediction of fouling in heat exchangers
Abstract:
Fouling is one of the main problems that often arises during the operation of heat exchangers. The presence of fouling results in a reduction of heat transfer efficiency and can cause temperature control problems. To overcome this problem, it is necessary to understand the behavior of fouling. In this paper, an artificial neural network (ANN) model for the prediction of fouling in heat exchangers was proposed. In particular, a feed-forward neural network was used to predict the fouling factor. The datasets for ANN training were obtained from the simulation of heat exchangers integrated with the threshold fouling model under various sets of inlet temperatures and flow rates of hot and cold streams. The inputs of the ANN model included flow rates of hot and cold streams, outlet temperatures of hot and cold streams, and time, while the output of the ANN model was the fouling factor. Effects of the number of hidden neurons and training algorithms on the ANN topology were also studied. The statistical indices used to determine the best topology included mean square error, regression coefficient, and processing time. The proposed ANN model was also tested with a new dataset to assess its generalization.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2021
Modified:
2026-02-04
Issued:
2026-02-04
บทความ/Article
application/pdf
BibliograpyCitation :
In Thai Institute of Chemical Engineering and Applied Chemistry. The 30th Thai Institute of Chemical Engineering and Applied Chemistry Conference (TIChE 2021) (PSI02). Nakhon Ratchasima : Suranaree University of Technology