Thursday , August 16 2018

Vol.23-Issue1-2014-ZAMOUM BOUSHAKI

Artificial Neural Network Control of the
Recycle Compression System

Razika ZAMOUM BOUSHAKI1, Boukhemis CHETATE2, Yasmine ZAMOUM2
1 Institut de Génie Electrique et Electronique,
Université M’hamad Bougara de Boumerdes,
Avenue de l’indépendance, Boumerdes 35000, Algeria,
boushakiraz@yahoo.fr
2 Laboratoire de Recherche sur l’Electrification des Entreprises Industrielles,
Université M’hamad Bougara de Boumerdes,
Avenue de l’indépendance, Boumerdes 35000, Algeria
boukhemis.chetate@gmail.com

Abstract: This paper presents results from an investigation on a nonlinear compressor control. The useful range of operation of turbo compressors is limited by choking at high rate flows and by the onset of instability known as surge at low rate flows. Traditionally, this instability has been avoided by using control systems that prevent the operating point of the compressor to enter in the unstable region. It is not efficient to apply classical controllers, such as simple P, PI and PID when the parameters of compression system change frequently. The aim of our work is to design and simulate an intelligent controller. A simulation part is clearly presented with the advantages of the intelligent system.

Keywords: Compression system, PID controller, Fuzzy logic control, Neural predictive controller, NARMA L2 Control.

>Full text
CITE THIS PAPER AS:
Razika ZAMOUM BOUSHAKI, Boukhemis CHETATE, Yasmine ZAMOUM, Artificial Neural Network Control of the Recycle Compression System, Studies in Informatics and Control, ISSN 1220-1766, vol. 23 (1), pp. 65-76, 2014.

  1. Introduction

This work is motivated by the fact that the compressors are used in a wide variety of applications such as: power generation using industrial gas turbines, pressurization of gas in the process industry, transport of fluids in pipelines, and the fundamental instability problem known as surge limits the operation range for compressors at low mass flows. This instability problem has been studied and a surge avoidance solution is established. This solution is based on keeping the operating point at the right side of the surge line. There is a potential for increasing the efficiency of compressor by allowing the operation point closer to the surge line, which is the case in industrial current systems. The increase in efficiency range is possible with compressor designs where the design is done with such controllers. However, this raises the need for control techniques, which stabilize the compressor when disturbances occur or set point is changed, otherwise, the operating point may cause a crossing of the surge line. This approach is known as artificial intelligent active surge control. In recent years intelligent active surge control has been an active area of research as in [1,2,3,4] have been focused on modelling and control. Active surge control has showed the ability to extend the operating range significantly [3,4].

This study presents a solution to this problem based on intelligent neural network controller.

REFERENCES

  1. HOLLOWAY, A., L. E. HOLLOWAY, Automated Control, Observation, and Diagnosis of Multi-layer Condition Systems, Studies in Informatics and Control Journal, vol. 16(1), 2007, pp. 97-114.
  2. AYHAN MARABA, A. EMIN KUZUCUOGLU, Speed Control of an Asynchronous Motor Using PID Neural Network, Studies in Informatics and Control, ICI Publishing House, vol. 20(3), 2011, pp. 199-208.
  3. HAFAIFA, A., F. LAAOUAD, K. LAROUSSI, Fuzzy Approach Applied in Fault Detection and Isolation to the Compression System Control, Studies in Informatics and Control, ICI Publishing House, ISSN 1220-1766, vol. 19(1), 2010, pp. 17-26.
  4. HAFAIFA, A., A. DAOUDI, K. LAROUSSI, Modelling and Control of Surge in Centrifugal Compression Based on Fuzzy Rule System, Studies in Informatics and Control, ICI Publishing House, ISSN 1220-1766, vol. 19(4), 2010, pp. 347-356.
  5. ANDREASSEN, A., Stabiliserende regulering av kompressor, NTNU, 2001.
  6. BØHAGEN, B., J. T. GRAVDAHL, On Active Surge Control of Compressors using a Mass Flow Observer, the 41th IEEE Conference, December 10-13, 2002.
  7. GREITZER, Surge and Rotating Stall in Axial Flow Compressors: Theoretical Compression System Model, Journal of Engineering for Power, vol. 98, 1976, pp. 190-198.
  8. GRAVDAHL, J. T., O. EGELAND, Compressor Surge and Rotating Stall: Modeling and Control, Springer-Verlag, 1999.
  9. BJØRN, O. B., J. T. GRAVDAHL, The Recycle Compression System, NTNU, 2010.
  10. EGELAND, O., J. T. GRAVDAHL, Modeling and Simulation for Automatic Control, Norway, 2002.
  11. CHETATE, B., R. ZAMOUM, A. FEGRICHE, M. BOUMDIN, PID and Novel Approach of PI Fuzzy Logic Controllers for Active Surge in Centrifugal Compressor, Ajse, Springer, vol. 38, 2013, pp.1405-1414.
  12. JONSON, L. G., Surge Testing of Natural Gas Pipeline Centrifugal Compressors, Mechanical engineering, Calgary, 1998.
  13. http://www.mathworks.com, Neural Network Toolbox, 2011.
  14. Ben OMRANE, I., A. CHATTI, P. BORNE, Evolutionary Method for Designing and Learning Control Structure of a Wheelchair, Studies in Informatics and Control, ICI Publishing House, ISSN 1220-1766, vol. 21(2), 2012, pp. 155-164.
  15. LUNGU, R., C. ROTARU, M. LUNGU, New Systems for Identification, Estimation and Adaptive Control of the Aircrafts Movement, Studies in Informatics and Control, ICI Publishing House, ISSN 1220-1766, vol. 20(3), 2011, pp. 273-284.

 

https://doi.org/10.24846/v23i1y201407