ANN-Based Modeling for Load and Main Steam Pressure Characteristics of a 600MW Supercritical Power Generating Unit

Abstract:

A supercritical coal-fired power generating unit is a typical multivariable system with large inertia and non-linear, slow time-variant, time-delay characteristics, which often makes the coordinated control quality deteriorate under wide-range load-changing conditions, and can't well satisfy the unit load and main steam pressure control requirements. Thus, it is of vital significance to study the supercritical boiler units operation characteristic by means of modeling method, and to improve the control quality with model-based advanced control strategies. In this paper, artificial neural network (ANN) method was used to build a nonlinear mathematical model of the load and main steam pressure characteristics for a 600MW supercritical boiler unit. Operation data over wide-range load-changing conditions were used for model training. Simulation tests showed that the model can fit the complex non-linear, dynamic characteristics between the units load, main steam pressure and fuel, feedwater flow and turbine governing valve opening with high precision and strong generalization ability. The model can be used as a prediction model to construct an intelligent controller for supercritical boiler unit coordinated control to meet the engineering application demand.

• Periodical: Advanced Materials Research (Volumes 760-762)
• Pages: 1381-1386
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.760-762.1381
• Online since: September 2013
• Authors: Liang Yu Ma, Zhi Yuan Gao
• Keywords: Artificial Neural Network (ANN), Coordinated Control System, Nonlinear Mathematical Model, Supercritical Power Unit

References

[1] Z.J. Li, Thermal Automatic Control System, Beijing: China Electric Power Press, (1997).

[2] Y. Liang and J. J. Gu, Parameter identification for the model of supercritical unit based on genetic algorithm, Electric Power Science and Engineering, Vol. 26, No. 7, pp.38-41, Jul. (2010).

[3] J. Ding, G.Y. Li, and N. Wang, Research on simplified model for the control of 660MW supercritical unit, Electric Power Science and Engineering, Vol. 27, No. 5, pp.29-34, May. (2011).

[4] L. Tian, D.L. Zeng, X.P. Liu, and J.Z. Liu, A simplified non-linear dynamic model of 500MW unit, Power Engineering, Vol. 24, No. 4, pp.522-525, Aug. (2004).

[5] S. Yan, D.L. Zeng, J.Z. Liu, and Q.J. Liang, A simplified non-linear model of a once-through boiler-turbine unit and its application, Proceedings of the CSEE, Vol. 32, No. 11, pp.126-134, Apr. (2012).

[6] X.S. Tian, Z.X. Han, L.J. Chen, and J. Cai, Parameter estimation and equilibrium points analysis on non-linear model of the supercritical unit, Computer Simulation, Vol. 28, No. 1, pp.20-23, Jan. (2011).

[7] Z.X. Han, C.X. Zhou, W. Zhang, H.J. Ma, C.J. Zhang, and D. Li, New design method of coordinated control system of supercritical pressure power unit and its application, Proceedings of the CSEE, Vol. 29, No. 8, pp.75-81, (2009).

[8] S.Q. Liu, S.F. Yu, and L. Zhou, Mathematic model and simulation of 900MW supercritical once-through boiler, Computer Simulation, Vol. 22, No. 10, pp.215-218, Oct. (2005).

[9] Q.J. Liang, J.Z. Liu, Y.G. Xue, and D.L. Zeng, A non-linear model for ultra-supercritical power unit and the dynamic characteristic study, Journal of Power Engineering, Vol. 32, No. 2, pp.118-123, Feb. (2012).

[10] X. Wang and W.H. Wang, Artificial Neural Network Principle and Application. Shenyang: Northeast University Press, (2000).

[11] H. Demuth, M. Beale, and M. Hagan, Neural Network ToolboxTM 6 User's Guide, The Math Works, Inc. (2008).