RESM
Submission & tracking
UPCOMING SPECIAL ISSUE
PARTNERS
Special issue
Special Issue Proposals:
The journal of RESM is open to proposals for special issues on emerging related topics. More info is here.
PUBLISHER
Research Article
Comparative analysis of fouling resistance prediction in shell and tube heat exchangers using advanced machine learning techniques
Kouidri Ikram1, Kaidameur Djilali1, Dahmani Abdennasser1, 2, Raheem Al-Sabur3, Benyekhlef Ahmed2, Abdel-Nasser Sharkawy4, 5
1Dept. of Mechanical Eng., GIDD Industrial Eng. and Sustainable Development Laboratory, Faculty of Science and Technology, University of Relizane, Algeria
2Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Medea, Algeria
3Dept. of Mechanical Eng., College of Eng., University of Basrah, Basrah 61001, Iraq
4Dept. of Mechanical Eng., Faculty of Eng., South Valley University, Qena 83523, Egypt
5Dept. of Mechanical Eng., College of Eng., Fahad Bin Sultan University, Tabuk 47721, Saudi Arabia
Keywords
Abstract
Fouling resistance;
Heat exchanger;
Machine learning;
FNN-MLP;
NARX;
SVM-RBF
Heat exchangers are utilized in a vast region of the process industry for heating and cooling. Long-term operation of heat exchangers results in decreased efficiency due to many problems, such as fouling. Therefore, the object of this research paper is to use three artificial intelligence techniques (feedforward neural networks-multilayer perceptron (FNN-MLP), nonlinear autoregressive networks with exogenous inputs (NARX), and support vector machines (SVM-RBF)) for predicting the fouling resistance in the tube and the shell heat exchanger in the preheating circuit of atmospheric distillation. The results summarize the high training as well as the predictive capacity of the "FFNN-MLP" model for predicting the fouling resistance in the heat exchanger with the highest coefficient of correlation (R = 0.99961) and the lowest root-mean-squared error (nRMSE = 1.0031%) for the testing phase, where the FNN-MLP network is superior to that provided using the SVM model (R = 0.9955 and nRMSE = 3.8652%). All the models of artificial networks and machine learning techniques used in the current work can be used to predict the fouling resistance in heat exchanger data with high accuracy. Despite this, the FNN-MLP model is the preferred model compared with the other proposed models, followed by the NARX model.
© 2023 MIM Research Group. All rights reserved.