In this paper constrain model predictive control is studied. The discrete time neural network for solving quadratic programming problem is stated. To solve the issue of continuous time neural network, simplified dual neural network is implemented in discrete time neural network. The convergence of discrete time neural network is analyse with the help of a software platform. The system response is obtained from air separation unit.

 

Published In : IJCSN Journal Volume 4, Issue 4

Date of Publication : August 2015

Pages : 668 - 673

Figures :05

Tables : --

Publication Link : A Comparison of Constrain Model Predictive Control and Neural Network for Implementation

 

 

 

Sudhir Sawarkar : receives Ph.D. in computer engineering from Amravati University in 2007.Currently he is principal of Datta Meghe College of Engineering. He has 27 years of teaching experience. He has published 37 and 47 papers in international conference and journals .he has published 8 papers in national conferences. He is member of IndianSociety for Technical Education, Institute of technical engineering, Computer society of India and Board of studies of Computer engineering.

Sonali Deshmukh : receives B.E in electronics engineering from Mumbai University in 2012. She currently pursuing M.E in electronics engineering from Mumbai University. She has 1 year of teaching experience. She has published a paper in International conference.

 

 

 

 

 

 

 

Model predictive control (MPC)

neural network

discrete time neural network

simplified dual neural network (SDNN)

From the results we got we can conclude that model predictive control with neural network is one of the best option if response time is major factor of measurement. This method is widely implemented in automation industries. The neural network is used to classify various signals to respond accurately.

 

 

 

 

 

 

 

 

 

[1] W. Greenwell and A. Vahidi, “Predictive control of voltage and current in a fuel cell-ultracapacitor hybrid,” IEEE Trans. Ind. Electron. vol. 57, no. 6, pp. 1954–1963, Jun. 2010. [2] C. Lim, N. A. Rahim, W. Hew, and E. Levi, “Model predictive control of a two-motor drive with five-leginverter supply,” IEEE Trans. Ind. Electron., vol. 60, no. 1, pp. 54–65, Jan. 2013 [3] A. Gupta, S. Bhartiya, and P. S. V. Nataraj, “A novel approach to multiparametric quadratic programming,” Automatica, vol. 47, no. 9, pp. 2112– 2117, Sep. 2011. [4] L. G. Bleris, P. D. Vouzis, M. G. Arnold, and M. V. Kothare, “A coprocessor FPGA platform for the implementation of real-time model predictive control,” in Proc. Amer. Control Conf., 2006, pp. 1912–1917. [5] D. Li, N. Yang, R. Niu, H. Qiu, and Y. Xi, “FPGA based QDMC control for reverse-osmosis water desalination system,” Desalination, vol. 285, pp. 83– 90, Jan. 2012. [6] N. Yang, D. Li, J. Zhang, and Y. Xi, “Model predictive controller design and implementation on FPGA with application to motor servo system,” Control Eng. Pract., vol. 20, no. 11, pp. 1229–1235, Nov. 2012. [7] M. S. K. Lau, S. P. Yue, K. V. Ling, and J.M.Maciejowski, “A comparison of interior point and active set methods for FPGA implementation of model predictive control,” in Proc. Eur. Control Conf., 2009, pp. 156–161. [8] S. Zhang and A. G. Constantinides, “Lagrange programming neural networks,” IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process., Vol 39, no.7, pp 441-452, July 1992 [9] M. Yashtini and A. Malek, “A discrete-time neural network for solving nonlinear convex problems with hybrid constraints,” Appl. Math. Computevol. 195, no. 2, pp. 576–584, Feb. 2008. [10] Y. Pan and J. Wang, “Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks,” IEEE Trans. Ind. Electron., vol. 59, no. 8, pp. 3089–3101, Aug. 2012 [11] J. B. Rawlings and K. R. Muske, “The stability of constrained receding horizon control,” IEEE Trans. Autom. Control, vol. 38, no. 10, pp. 1512– 1516, Oct. 1993. [12] Z. Xu et al., “Automatic load change system of cryogenic air separation process,” Sep. Purif. Technol., vol. 81, no. 3, pp. 451–465, Oct. 2011. [13] D. Q. Mayne, J. B. Rawlings, C. V. Rao, and P. O. M. Scokaert, “Constrained model predictive control: Stability and optimality,” Automatica, vol. 36, no. 6, pp. 789–814, Jun. 2000. [14] D. Kinderlehrer and G. Stampacchia, an Introduction to Variational Inequalities and Their Applications. New York, NY, USA: Academic, 1980.TMS320C6678 Multicore Fixed and Floating-Point Digital Signal Processor Data Manual, Texas Instruments Incorporated, Dallas, TX, USA, 2011. [15] AllgoK wer, F., & Zheng, A. (1999). Model predictive control: Assessment and future directions. Proceedings of international workshop onmodel predictive control, Ascona, 1998, Berlin: Springer.23(2), 149}160. [16] Badgwell, T. A. (1997). Robust model predictive control ofstable linearsystems. International Journal of Control, 68(4), 797},818. [17] Bemporad,A,Casavola A and Mosca.E(1997).Nonlinear control of constrained linear system via predictive reference management,IEEE Transactions on Automatic Control,42(3),340]349. [18] Clarke.D.W,Mohtadi.C and Tus.P.S(1987b).Generalize predictive control.Part 2:Extansions and interpretations.Automatic. [19] Chisci, L., Lombardi, A., & Mosca, E. (1996). Dual receding horizon control of constrained discrete-time systems. European Journal ofControl, 2, 278}285. [20] Chen, C. C., & Shaw, L. (1982). On receding horizon feedback control. Automatica, 18, 349}352. [21] GarcmHa,C.E&Morshedi,A.M(1986).Quadratic programming solution of dynamic matrix control(QDMC).Chemical Engineering communications,46,73}87.