Modelling of Two Continuous Stirred Tank Heat Exchangers in Series Using Neural Network

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    This paper presents the application of artificial neural networks (ANN) in modeling of two continuous stirred tank heat echangers in series (2CSTHEs), which is a complex non-linear process. Non-linear models of the 2CSTHEs system were developed using ANN because of  ANN ability to model complex non-linear processes without requiring any explicit knowledge about input-output relationship. The ANN architecture  is based on the multilayer feed forward network and it is trained using the back-propagation algorithms. Three types of back-propagation algorithms are used in the study, namely, Levenberg-Marquardt, BFGS quasi-Newton, and conjugate gradient with Polak-Ribiére updates. Two dynamic models of the system are developed: ANN model for CSTHE 1and 2. Results from the study showed that the 2CSTHEs model trained using Levenberg-Marquardt algorithm produced the best predictive performance of the system behaviour. The results confirmed that ANN can be used in the modeling of the heat exchanger 2CSTHEs, and the model obtained can predict the outputs of the system process with very high accuracy. This proves that ANN modelling method can produce accurate system models that can simulate and predict the behaviour of complex non-linear processes.

     


  • Keywords


    CSTHE; data generation; heat exchanger; modelling; neural network

  • References


      [1] Mohanraj M, Jayaraj S, and Muraleedharan C (2015), Application of Artificial Neural Networks for Thermal Analysis of Heat Exchangers. International Journal of Thermal Sciences. 90,150-172.

      [2] Diaz G, Sen M, Yang KT, and McClain RL (2001), Dynamic prediction and control of heat exchangers using artificial neural networks. International Journal of Heat and Mass Transfer, 44,1671-1679.

      [3] Lazrak A, Boudehem F, Bannot S, Fraisse G, Leconte A, Papillon & Souyri B (2016), Development of a dynamic artificial neural network model of an absorption chiller and its experimental validation. Renewable Energy, 86, 1009-1022.

      [4] Mikulandric R, Loncar D, Bohning D, Bohme R & Beckmann M (2014), Artificial neural network modelling approach for biomass gasification. Energy Conversion and Management, 87, 1210-1223.

      [5] Al-Dawery SK, Alrahawi AM, and Al-Zobai KM (2001), Dynamic modelling and control of plate heat exchanger. International Journal of Heat and Mass Transfer, 55, 6873-6880.

      [6] Bakosova M, Oravec J (2014), Applied Thermal Engineering. Robust model predictive control for heat exchanger network. Applied Thermal Engineering, 73, 924-930.

      [7] Lazrak, A, Boudehem F, Bannot S, Fraisse G, Leconte A, Papillon P & Souyri B (2016), Development of a dynamic artificial neural network model of an absorption chiller and its experimental validation. Renewable Energy, 86, 1009-1022.

      [8] Kiu MY, Thesis: Optimal control design of two continuous stirred tank heaters is Series. Bangi: National University of Malaysia (UKM), (20120).

      [9] Alvarez EM, Hernandez JA & Bourous, M (2016), Modelling the performance parameters of a horizontal falling film absorber with aqueous (lithium, potassium, sodium) nitrate solution using artificial neural networks. Energy, 102, 313-323.

      [10] Morales LI, Conde-Gutierrez R A, Hernandez JA, Huicochea A, Juares-Romero D, Siqueiros J (2015), Optimisation of an absorption heat transformer with two-duplex components using inverse neural network and solved by genetic algorithm. Applied Thermal Engineering. 85, 322-333.

      [11] Morales LI, Conde-Gutierrez R A, Hernandez JA, Huicochea A, Juares-Romero D, Siqueiros J (2015), Optimisation of an absorption heat transformer with two-duplex components using inverse neural network and solved by genetic algorithm. Applied Thermal Engineering, 85:322-333.

      [12] Annuar MH. Thesis: Modelling of two heaters in series using neural networks. Bangi, National University of Malaysia (UKM), (2015) Malaysia.

      [13] Ahmad ZAG, Norliza AR & Faezah Esa*.2014. Pembangunan Kawalan Logik Kabur dalam Reaktor Lapisan Terpadat. Jurnal Kejuruteraan, 26(2014): 55-61.


 

View

Download

Article ID: 24910
 
DOI: 10.14419/ijet.v8i1.2.24910




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.