International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

An Adaptive Neural Network Based On Model Prediction Control

Author : Betty Elezebeth Samuel, ¹ Dr. Latha Parthiban ²

Date of Publication :7th March 2015

Abstract: Model Predictive Control (MPC) is a powerful model based control technique, which explicitly optimizes the overall performance of a system to be controlled. Also, it employs an explicit prediction model of the plant to optimize future plant behaviour. Artificial Neural Networks (ANNs), originally inspired by the ability of the human beings to perform many complicated tasks with ease, are used as an attractive tool to model complex relationships between inputs and outputs, and applied to various areas. More over neural networks (NNs) are effective models for identifying complex nonlinear and uncertain systems. Therefore neural network is suitable selection to identify complex nonlinear systems for MPC and design of training algorithm is an important task for neural network based model predictive control system. The primary intention of research is to design a model predictive control (MPC) using integration of Levenberg- Marquardt (LM) based back propagation (BP).

Reference :

1. Hong-Gui Han, Xiao-Long Wu, and Jun-Fei Qiao, , “Real-Time Model Predictive Control Using a SelfOrganizing neural Network”, IEEE Trans. Neural Netw. Learn. Syst.,vol. 24, no. 9, pp. 1425–1435, Sept. 2013. . Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68–73.
2. Ramdane Hedjar,”Adaptive neural network model predictive control”, Int. J. of Innovative Computing, Information and Control, Vol. 9, Number 3, pp. 1245-1257, March 2012
3. Stefan Richter, Colin N. Jones and Manfred Morari, “Real-Time Input-Constrained MPC Using Fast Gradient Methods”, in Proc. IEEE Decision and Control, Chinese Control Conf.,Dec. 2009, pp. 7387 - 7393.
4. Y. Wang and S. Boyd, “Fast model predictive control using online optimization,” IEEE Trans. Control Syst. Technol., vol. 18, no. 2,pp. 267–278, Mar. 2010.
5. Yunpeng Pan and Jun Wang,“Model Predictive Control of Unknown Nonlinear Dynamical Systems Based on Recurrent Neural Networks”, IEEE transactions on industrial electronics, vol.59, no.8, 2012.
6. P. Lezana, R. Aguilera and D. Quevedo, “Model predictive control of an asymmetric flying capacitor converter”, IEEE Trans. Ind. Electron., vol. 56, no. 6, pp. 1839–1846, 2009
7. Frauke Oldewurtel, Alessandra Parisio, Colin N. Jones, Dimitrios Gyalistras, Markus Gwerder , Vanessa Stauch, Beat Lehmann and Manfred Morari “Use of model predictive control and weather forecasts for energy efficient building climate control”, Energy and buildings,no.45,pp.15-27,2012.
8. Guang Li and Michael R.Belmont, “Model predictive control of sea wave energy converters e Part I: A convex approach for the case of a single device” Renewable Energy, vol.69, pp.453-463, 2014.
9. M. Maasoumya, M. Razmara, M. Shahbakhti and A. Sangiovanni Vincentelli,“Handling model uncertainty in model predictive control for energy efficient buildings”, Energy and building, vol.77, pp.377-392, 2014.
10. C. H. Lu and C. C. Tsai, “Adaptive predictive control with recurrent neural network for industrial processes: An application to temperature control of a variable-frequency oil-cooling machine,” IEEE Trans. Ind. Electron., vol. 55, no. 3, pp. 1366–1375, 2008.
11. F. J. Lin, T. S. Lee, and C. H. Lin, “Robust H∞ controller design with recurrent neural network for linear synchronous motor drive,” IEEE Trans.Ind. Electron., vol. 50, no. 3, pp. 456–470, Jun. 2003.
12. C. M. Lin and C. F. Hsu, “Recurrent-neural-networkbased adaptive back stepping control for induction servomotors,” IEEE Trans. Ind.Electron., vol. 52, no. 6, pp. 1677–1684, Dec. 2005
13. Min Han, Jianchao Fan, and Jun Wang, “A Dynamic Feedforward Neural Network Based on Gaussian Particle Swarm Optimization and its Application for Predictive Control” IEEE Transactions On Neural Networks, Vol. 22, No. 9,pp. 1457-1468, Sept. 2011.
14. Bobál, V., Böhm, J., Prokop, R., Fessl, J.: Practical Aspects of Self-Tuning Controllers,Algorithms and Implementation. Brno, VUTIUM 1999, in Czech
15. Švancara, K., PivoÅˆka, P.: Closed Loop On-Line Identification Based on Neural Networks in Adaptive Optimal Controller. In Proc. of Zittau Fuzzy Colloquium, Zittau,2002, pp. 218-223
16. Šíma, J., Neruda, R.: Theoretical issue of neural networks. MATFYZPRESS 1996, in Czech
17. Hristev, R.M.: The ANN Book, GNU Public Licence, 1998