Bian He-Ying
College of Electrical and Information Engineering, Pingdingshan University, Henan, 467000, Pingdingshan, China
Li Zeng-Quan
Henan Quality Polytechnic, Henan, 467000, Pingdingshan, China
Fang Yan-Jun
Department of Automation, Wuhan University, Hubei, 430072, Wuhan, China
ABSTRACT
A novel soft-sensing model of the carbon content in fly ash is established by applying support vector regression and article swarm algorithm about the problem that the carbon content in fly ash is difficult to measure accurately. The carbon content in fly ash is an important index to judge the quality of boiler operation and coal utilization rate and affects directly the efficiency of the boiler. In this work, carried on data preprocessing, the various variables correlation analysis and dapted article swarm algorithm to optimize the parameters C and g of the model according to the real time data of a Power Plant 1000MW ultra-supercritical unit. Moreover, the models accuracy and generalization capability were dentified by using the test data. The simulation results show that soft-sensing model built has a higher prediction accuracy and better generalization ability than the previous measurement methods which provides an effective way for measurement of carbon content in fly ash in power plant.
PDF References Citation
How to cite this article
Bian He-Ying, Li Zeng-Quan and Fang Yan-Jun, 2013. Study on Soft-sensing Model of Carbon Content in Fly Ash Based on Support
Vector Regression. Information Technology Journal, 12: 3122-3127.
DOI: 10.3923/itj.2013.3122.3127
URL: https://scialert.net/abstract/?doi=itj.2013.3122.3127
DOI: 10.3923/itj.2013.3122.3127
URL: https://scialert.net/abstract/?doi=itj.2013.3122.3127
REFERENCES
- Chen, M.S. and D.P. Liu, 2005. Optimized control of carbon content in utility boilers fly ash. Power Eng., 25: 545-549.
Direct Link - Deng, S., S.Y. Lin and W.L. Chang, 2011. Application of multiclass support vector machines for fault diagnosis of field air defense gun. Expert Syst. Appl., 38: 6007-6013.
CrossRef - Han, P., H. Qiao, D.F. Wang and Y. Zhai, 2007. Development and current status of thermal parameter soft-sensing technique in power plant. Chin. J. Sci. Instr., 28: 1139-1146.
Direct Link - Li, R., H.N. Wang, H. He, Y.M. Cui and Z.L. Du, 2007. Support vector machine combined with K-nearest neighbors for solar flare forecasting. Chin. J. Astronomy Astrophys., Vol. 7.
CrossRef - Mohandes, M.A., T.O. Halawani, S. Rehman and A.A. Hussain, 2004. Support vector machines for wind speed prediction. Renewable Energy, 29: 939-947.
CrossRef - Ren, B. and Z.P. Feng, 2002. Improved genetic algorithm and particle swarm optimization as well as comparison between them. J. Nanjing Normal Univ. (Eng. Technol.), 2: 14-20.
Direct Link - Shen, Y., B. Guo and T.X. Gu, 2005. Particle swarm optimization algorithm and comparison with genetic algorithm. J. Univ. Electr. Sci. Technol. China, 34: 696-699.
Direct Link - Wang, C.L., H. Zhou, Z.H. Zhou, Z.Q. Ling, G.N. Li and K.F. Cen, 2005. Support vector machine modeling on the unburned carbon in fly ash. Proc. Chin. Soc. Electr. Eng., 25: 72-76.
Direct Link - Zhang, G. and L. Bao, 2009. Soft-sensing modeling of the carbon content in fly ash based on information fusion for thermal power plant. Proceedings of the International Conference on Mechatronics and Automation, August 9-12, 2009, Changchun, China, pp: 3860-3865.
CrossRef