[1] Yang Hongmin, Zhou Bo,. Neural network approach to predicting mercury emissionfrom utility boiler [J]. Journal of Southeast University (English Edition), 2008, 24 (1): 55-58. [doi:10.3969/j.issn.1003-7985.2008.01.013]

Copy

Neural network approach to predicting mercury emissionfrom utility boiler()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

24

Issue:

2008 1

Page:

55-58

Research Field:

Environmental Science and Engineering

Publishing date:

2008-03-30

Info

Title:

Neural network approach to predicting mercury emissionfrom utility boiler

Author(s):

Yang Hongmin¹;  2 ;  Zhou Bo¹

¹School of Power Engineering, Nanjing Normal University, Nanjing 210042, China
²Institute for Combustion Science and Environmental Technology, Western Kentucky University, Bowling Green, KY 42101, USA

Keywords:

mercury speciations;  electric utility boiler;  prediction;  artificial neural network

PACS:

X51

DOI:

10.3969/j.issn.1003-7985.2008.01.013

Abstract:

The feasibility of using an ANN method to predict the mercury emission and speciation in the flue gas of a power station under un-tested combustion/operational conditions is evaluated.Based on existing field testing datasets for the emissions of three utility boilers, a 3-layer back-propagation network is applied to predict the mercury speciation at the stack.The whole prediction procedure includes:collection of data, structuring an artificial neural network(ANN)model, training process and error evaluation.A total of 59 parameters of coal and ash analyses and power plant operating conditions are treated as input variables, and the actual mercury emissions and their speciation data are used to supervise the training process and verify the performance of prediction modeling.The precision of model prediction(root-mean-square error is 0.8 μg/Nm³ for elemental mercury and 0.9 μg/Nm³ for total mercury)is acceptable since the spikes of semi-mercury continuous emission monitor(SCEM)with wet conversion modules are taken into consideration.

References:

[1] US Environmental Protection Agency.Mercury study report to Congress, volume Ⅰ:executive summary, EPA-452/R-97-003 [R].Washington DC:Office of Air Quality Planning and Standards and Office of Research and Development, 1997.
[2] US Environmental Protection Agency.Clear skies legislation introduced in Congress proposal will improve air quality, prevent premature deaths, illnesses[M].Washington, DC:EPA Press, 2002.
[3] Galbreath K C, Zygarlicke C J.Mercury transformations in coal combustion flue gas[J].Fuel Processing Technology, 2000, 65(1):289-310.
[4] Livengood C D, Huang H S, Mendelsohn M H, et al.Development of mercury control technology for coal-fired systems[C]//Proceeding of the 210th ACS National Meeting.Chicago, IL, 1995:325-331.
[5] Müller B, Reinhardt J.Neural networks:an introduction[M].New York:Springer-Verlag, 1990.
[6] Gardner M W, Dorling S R.Artificial neural networks(the multiplayer perceptron)—a review of applications in the atmospheric sciences[J].Atmos Environ, 1998, 32(14/15):2627-2636.
[7] Luis E O, Beatriz M T.A method to estimate emission rates from industrial stacks based on neural networks [J].Chemosphere, 2004, 57(7):691-696.
[8] Jensen R R, Karki S, Salehfar H.Artificial neural network-based estimation of mercury speciation in combustion flue gases[J].Fuel Processing Technology, 2004, 85(6/7):451-462.
[9] Aleksander I, Morton H.An introduction to neural computing[M].2nd ed.London:Chapman and Hall, 1995.

Memo

Memo:

Biography: Yang Hongmin(1972—), male, doctor, professor, yanghongmin@njnu.edu.cn.
Foundation items: The National Basic Research Program of China(973 Program)(No.2006CB200302), the Natural Science Foundation of Jiangsu Province(No.BK2007224).
Citation: Yang Hongmin, Zhou Bo.Neural network approach to predicting mercury emission from utility boiler[J].Journal of Southeast University(English Edition), 2008, 24(1):55-58.

Common functions