Based on Vari Combination Forecasting Model for Power Plant Flue Gas Oxygen Contentance-Covariance Method

Abstract:

Focusing on the problem which power plant flue gas oxygen content is hard to predict efficiently, an intelligent hybrid prediction method is proposed. First, the RBF neural network and principal component analysis method are utilized to reduce the dimension of the input variables. Second, the case-based reasoning method is carried on to predict the flue gas oxygen content based on the above analysis results. Then, in order to reflect the cumulative effect of the flue gas oxygen content with time, the GM (1, 1) grey prediction method is used to predict the current flue gas oxygen content value. Finally, the final flue gas oxygen content is obtained by the variance-covariance method of weight combination forecasting. Simulations and industrial results show that the proposed intelligent hybrid prediction model has high accuracy and robustness, and can solve the problem of predicting the flue gas oxygen content effectively.

• Periodical: Applied Mechanics and Materials (Volume 525)
• Pages: 665-670
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.525.665
• Online since: February 2014
• Authors: Teng Xi Zhan*, Jiao Li Peng, Bing Tu
• Keywords: Case-Based Reasoning (CBR), Flue Gas Oxygen Content, GM ( 1, 1) Grey Prediction Method, Intelligent Hybrid Prediction Method, Principal Component Analysis (PCA)

References

[1] Zhao Zheng. Based on information fusion of boiler combustion state parameter detection technology research [ D]. Baoding: North China Electric Power University, (2007).

[2] Wang Hongzhi, Chen Shuai, Shi Hongbo. Based on least squares support vector machine and PSO algorithm of soft measurement of oxygen content in flue gas [J ]. Thermal power generation, 2008, 37 ( 3): p.35-p.38.

[3] Fu Zhongguang, Jin Tao, Zhou Lijun, Ge Zhihua, Zheng Ling, Yang Yongping. The complex system reverse modeling method and partial least squares modelling application research [J ]. China Journal of geotechnical engineering, 2009, 29 ( 2): 25-29.

[4] Yang Guangjun, Liu Jizhen, Liu Xiang Jay, Tan Wen. Coal-fired power plant flue gas oxygen content soft measurement of gray box modeling [ A]. Sixth World Congress on intelligent control and automation [C]. Dalian University of Technology press, 2006: 4904-4908.

DOI: 10.1109/wcica.2006.1713317

[5] LIU Jizhen, ZHAO Zheng, ZENG Deliang, CHEN Yanqiao. Soft-sensing model of oxygen control based on data fusion[A]. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics[C]/Guangzhou: IEEE Press, 2005: 3991-3995.

DOI: 10.1109/icmlc.2005.1527635

[6] CHENEY E W. Introduction to approximation theory [M]. New York: Mcgraw-Hill, (1966).

[7] Li Yonghua, Fu Song, Chen Hongwei, upward, Yu Xia. Mixed coal thermogravimetric test [J ]. Boiler technology, 2003, 34 ( 1): 8-11.

[8] Fu Zhongguang, Wang Liping, Ge Zhihua, Jin Tao, Zhang Guang. Using principal component analysis method in comprehensive evaluation of operation state of the power unit [J ]. Power engineering, 2008, 28 ( 4): 548-551.

[9] SCHANK R. Dynamic memory: a theory of learning in computers and people[M]. Cambridge: Cambridge University Press, (1982).

[10] Gao Xinbo, Li Jie, Ji Hongbing. Based on the weighted fuzzy C means clustering and statistical test of multi-threshold image segmentation algorithm [J ]. Chinese Journal of electronics, 2004, 32 ( 4): 661-664.