Automation of Heat Exchanger using Neural Network

In this paper the development of a heat exchanger as a pilot plant for educational purpose is discussed and the use of neural network for controlling the process is being presented. The aim of the study is to highlight the need of a specific Pseudo Random Binary Sequence (PRBS) to excite a process under control. As the neural network is a data driven technique, the method for data generation plays an important role. In light of this a careful experimentation procedure for data generation was crucial task. Heat exchange is a complex process, which has a capacity and a time lag as process elements. The proposed system is a typical pipe-in- pipe type heat exchanger. The complexity of the system demands careful selection, proper installation and commissioning. The temperature, flow, and pressure sensors play a vital role in the control performance. The final control element used is a pneumatically operated control valve. While carrying out the experimentation on heat exchanger a welldrafted procedure is followed giving utmost attention towards safety of the system. The results obtained are encouraging and revealing the fact that if the process details are known completely as far as process parameters are concerned and utilities are well stabilized then feedback systems are suitable, whereas neural network control paradigm is useful for the processes with nonlinearity and less knowledge about process. The implementation of NN control reinforces the concepts of process control and NN control paradigm. The result also underlined the importance of excitation signal typically for that process. Data acquisition, processing, and presentation in a typical format are the most important parameters while validating the results.

Authors:

• Sudhir Agashe
• Ashok Ghatol
• Sujata Agashe

Keywords:

• Process identification
• neural network
• heat exchanger.

References:

[1] R.W.Miller and R.Roy, "Nonlinear Process Identification Using
Decision Theory," IEEE transactions on Automatic Control October
1964, pp538-540.
[2] Cesare Alippi and Vincenzo Piuri, " Experimental Neural Networks for
Prediction and Identification," IEEE transactions on Instrumentation
and Measurement, Vol. 45, No.2, April 1996, pp 670-676.
[3] E. H. Magali R.G. Meireles Paulo, E.M. Almeida and Marcelo Godoy, "
A Comprehensive Review for Industrial Applicability of Artificial
Neural Networks," IEEE Transactions on Industrial Electronics, Vol.
50. No. 3, June 2003, pp585-601.
[4] J. Wang, "O Dubois, J Nicolas, A Billat, " Adaptive Neural Network
control of the Temperature in Oven," LAM. UFR Sciences Exactes et
Naturelles, BP 347 Reims FRANCE, pp 8/1-8/3.
[5] F.G.Shinskey, "Process Control Systems, Application, Design, and
Tuning," Third Edition, McGraw-HILL 1988, pp 3-72.
[6] M.A. Abdelghani-Idrissi, F. Bagui, "Countercurrent Double-Pipe Heat
Exchanger subjected to Flow-Rate Step Change, Part-I: New steady state
Formulation," Journal of Heat Transfer Engineering, vol.23, No.5,
December 2002, pp 4-11.