Zeng-hui ZHU（朱增辉）, Hui-ying SUN（孙慧影）
College of Information and Electrical Engineering, Shandong Unive rsity of Science and Technology, Qingdao 266510, China
Abstract-By combining the Back-Propagation (BP) neural netwo rk with conventional proportional Integral Derivative (PID) controller, a new te mperature control strategy of the export steam in supercritical electric power p lant is put forward. This scheme can effectively overcome the large time delay, inertia of the export steam and the influence of object in varying operational p arameters. Thus excellent control quality is obtained. The present paper describ es the development and application of neural network based controller to control the temperature of the boiler′s export steam. Through simulation in various si tuations, it validates that the control quality of this control system is appare ntly superior to the conventional PID control system.
Key words-PID controller based on BP neural network; su percritical power unit; export steam temperature; large time delay
Manuscript Number: 1674-8042(2011)01-0084-04
dio: 10.3969/j.issn.1674-8042.2011.01.22
References
[1]K.J.De, J.S.Brown, 1984. A qualitative physics based on confluence. Artificial Intelligence, 24: 7-83.
[2]C.M.Ufret, T.J. Williams, 1981. Mathematical Model of the Blast Furn ace Process. D.B. Spalding, N.H. Afgan (Eds.), Heat and Mass Transfer in Metallu rgical Systems, Hemisphere Pub Co, Washington, p.3-27.
[3]J, Chen, D. Xu. 1998. An Improved Back Propagation Algorithm. Gu, J. (Ed.), Proceedings of Systems Science and Systems Engineering. Scientific and T echnical Documents Publishing House, Beijing, p.408-411.
[4]A. Meghlaoui, J. Thibault, R.T. Bui, L. Tikasz, R. Santerre, 1998. Neural networks for the identification of the aluminum electrolysis process. Com., and Chem. Eng., 22(10): 1419-1428.
[5]T.E. Quatrile, Y.A. Liu, 1991. Artificial Intelligence in Chemical E ngineering. Academic Press, San Diego, CA, p.248-256.
[6]L.C. Hamilton, 1990. Modern Data Analysis-A First Course in Applie d Statistics, Brooke Cole Pub., Co., Pacific Grove, CA, p.107-109.
[7]D.C. Hoaglin, F. Mosteller, J.W. Tukey, 1983. Understanding Robustan d Exploratory Data analysis. Wiley, New York.
[8] A.S. Venkatadri, S.K. Gupta, 1985. A Relook on Desulphurization in Indian Blast Furnaces. S.P. Mehrotra, T.R. Ramachandran (Eds.) Proc. Intl. Conf . on ‘Progress in Metallurgical Research’, IIT Kanpur, p.186-194.
[9]B. Kuipers, 1986. Qualitative simulation. Artificial Intel ligence, 29: 289-338.
[10]H. Walker, 1977. Blast Furnace Practices II. W.K. Lu (Ed.), Blast F urnace Iron Making, Mc Master University, Canadap.17-29.
[11]O.Iida, 1989. Blast Furnace Control by Artificial iItelligence. Rodd, M.G. Suski, G.J. (Eds.), Artificial Intelligence in Real-Time Control. S wansea, UK, p.73-78.
[12]G.Jin, 1986. A mathematic model for predicting the Si-content and temperature of pig iron. Iron Smelting, 5(2): 8-16.
[13]J. Wang, C. Fang, 1992. Computer Systems for Process Control. Tsing hua University Press, Beijing, p.37.
[14]Y. Wang, J. A. Chen, 1995. Framework of Decision Analyst is Integra ting Qualitative Reasoning and Quantitative Models. Proc. IEEE International Conference on Systems, Man and Cybernetics, Vancouver, p.346-450.
[full text view]
