Online Forecasting and Calculating of Steam Turbine Exhaust Enthalpy Based on RBF Process Neural Network with Two Hidden Layers

Abstract:

In order to diagnose the economic performance of unit online, a new algorithm to forecast the exhaust enthalpy in the steam turbine online based on RBF process neural network with to hidden layers neural network is introduced in this paper. This online forecasting method establishes the complicated relation model between the steam turbine exhaust enthalpy and the relative operating parameters. The enthalpy of the last stage extraction steam and that of the exhaust are online calculated for a 300MW set in this paper. The example result shows that this method can accurately forecast the steam turbine exhaust enthalpy and the model is simple, accurate and convergence. This is an effective and feasible predicting method.

• Periodical: Advanced Materials Research (Volume 1037)
• Pages: 349-352
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1037.349
• Online since: October 2014
• Authors: Huan Chun Gong*
• Keywords: Exhaust Enthalpy, Online Forecasting, RBF Process Neural Network with Two Hidden Layers, Steam Turbine

References

[1] Wang Gang, Zhang Guang. A study on two problems of thermodynamic calculation Matrix Method[J]. Modern Electric Power, 2000, 17(1): 12-15.

[2] Cao zuqing. Steam turbine characteristics[M]. Beijing: China Water & Power Press, (1989).

[3] Wenxin, Zhoulu, Lixiang. Simulation and application of MATLAB neural network[M]. Beijing: Science Press, (2003).

[4] Cai Jiejin, Ma Xiaoqian. Application of support vector machine in the steam turbine exhaust steamenthalpy online prediction[J]. Automation of Electric Power Systems, 2006, 30(18): 77-82.

[5] GAO Jun-ru, DING Guang-bin, MENG Xin, Etc. Hierarchical radial basis neural network using steam turbine exhaust steam enthalpy calculation[J]. Power Engineering. 2005, 25(4): 466-468.