Modeling of Distributed Parameter Processes with Neural Networks

Abstract:

In this paper an original solution for the modeling of distributed parameter processes using neural networks is presented. The proposed method represents a particular alternative to a very accurate modeling-simulation method for this kind of processes, the method based on the matrix of partial derivatives of the state vector (Mpdx), associated with Taylor series. In order to compare the performances generated by the two methods, a distributed parameter thermal process associated to a rotary hearth furnace (R.H.F) from the technological flow of producing seamless steel pipes is considered. The main similarities and differences between the two methods are highlighted in the paper. The treated solution represents a premise for the usage of the neural networks in the automatic control of the distributed parameter processes domain.

• Periodical: Applied Mechanics and Materials (Volume 555)
• Pages: 530-540
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.555.530
• Online since: June 2014
• Authors: Honoriu Vălean, Mihail Abrudean, Mihaela Ligia Ungureşan, Iulia Clitan, Vlad Mureşan*
• Keywords: Distributed Parameter Process, Matrix of Partial Derivatives of the State Vector (Mpdx), Neural Network (NN), Numerical Simulation, Partial Differential Equation, Serial-Parallel Structure

References

[1] V. Mureşan and M. Abrudean: Temperature Modelling and Simulation in the Furnace with Rotary Hearth, Proceedings of 2010 IEEE AQTR 2010–17th edition, Cluj-Napoca, Romania, May 28-30, 2010, pp.147-152.

DOI: 10.1109/aqtr.2010.5520900

[2] H. -X. Li and C. Qi: Spatio-Temporal Modeling of Nonlinear Distributed Parameter Systems: A Time/Space Separation Based Approach, 1st Edition, edited by Springer Publishing House, 2011, pg. 194.

[3] M. Krstic: Systematization of approaches to adaptive boundary control of PDEs, Int. Journal of Robust and Nonlinear Control, vol. 16 (2006), pp.801-818.

DOI: 10.1002/rnc.1098

[4] R.F. Curtain and K.A. Morris: Transfer Functions of Distributed Parameter Systems, Automatica, 45, 5 (2009), pp.1101-1116.

DOI: 10.1016/j.automatica.2009.01.008

[5] T. Coloşi, M. Abrudean, M. -L. Ungureşan and V. Mureşan: Numerical Simulation Method for Distributed Parameters Processes, edited by Springer Publishing House, 2013, pg. 343.

DOI: 10.3182/20130522-3-ro-4035.00004

[6] S. Haykin: Neural Networks and Learning Machines, Third Edition, edited by Pearson International Edition, 2009, pg. 934.

[7] H. Valean: Neural Network for System Identification and Modelling, Proc. of A'96-Theta 10 Automatic Control and Testing Conference, Cluj-Napoca, Romania, 23-24 May, 1996, pp.263-268.

[8] R.V. Borges: Learning and Representing Temporal Knowledge in Recurrent Networks, IEEE Transactions on Neural Networks, Vol. 22, Issue 12 (2011), p.2409 – 2421.

DOI: 10.1109/tnn.2011.2170180

[9] H. Valean, A. Astilean and T. Letia: Neural Supervisory for an Electrocorundum Furnace, Proc. of the 7th International Conference on Optimization of Electrical and Electronic Equipment OPTIM 2000, vol. III, Brasov, Romania, May 11-12, 2000, pp.645-650.

[10] User Guide, Matlab 7. 5. 0 (R2007b).

[11] F. Golnaraghi and B. C. Kuo: Automatic Control Systems, 9th edition, edited by Wiley Publishing House, 2009, pg. 800.

[12] J. Love: Process Automation Handbook, 1 edition, edited by Springer Publishing House, 2007, pg. 1200.