Development of NOx Emission Model for a Tangentially Fired Acid Incinerator
This paper aims to develop a NOx emission model of
an acid gas incinerator using Nelder-Mead least squares support
vector regression (LS-SVR). Malaysia DOE is actively imposing the
Clean Air Regulation to mandate the installation of analytical
instrumentation known as Continuous Emission Monitoring System
(CEMS) to report emission level online to DOE . As a hardware
based analyzer, CEMS is expensive, maintenance intensive and often
unreliable. Therefore, software predictive technique is often
preferred and considered as a feasible alternative to replace the
CEMS for regulatory compliance. The LS-SVR model is built based
on the emissions from an acid gas incinerator that operates in a LNG
Complex. Simulated Annealing (SA) is first used to determine the
initial hyperparameters which are then further optimized based on the
performance of the model using Nelder-Mead simplex algorithm.
The LS-SVR model is shown to outperform a benchmark model
based on backpropagation neural networks (BPNN) in both training
and testing data.
[1] U.S Environmental Protection Agency. Clean Air Act as of 2008.
Chapter 85: Air Pollution Prevention and Control. s.l. : U.S Government
Printing Office, 2008.
[2] ENVIRONMENTAL QUALITY (CLEAN AIR) REGULATIONS 1978.
FEDERAL SUBSIDIARY LEGISLATION ENVIRONMENTAL QUALITY
ACT 1974 [ACT 127]. s.l. : Department of Environment, Malaysia,
2000.
[3] Design CEMS For Flue Gas From Thermal Power Plant. Fan Xiaoliang,
Zheng Haiming. Baoding, China : IEEE, 2009.
[4] Developing Data Acquisition and Handling System for Continous
Emission Monitoring System from Coal-Fired Power Plant. Haiming
Zheng, Guiji Tang. Baoding, China : IEEE, 2008.
[5] US Environmental Protection Agency. Climate Change - Health and
Environmental Effects. US EPA Home Page. [Online] [Cited: April 8,
2011.] http://www.epa.gov/climatechange/effects/index.html.
[6] Emission Monitoring Using Multivariate Soft Sensors. Dong, Dong and
McAvoy, Thomas J. Seattle, Washington : American Control
Conference, , 1995.
[7] Neural Networks for Boiler Emission Prediction. Baines, Glenn. s.l. :
Performance Consultant Fisher-Rosemount Solutions, 1999, pp. 435-
439.
[8] Predictive emission monitors (PEMS) for NOx generation in process
heaters. S. S. S. Chakravarthy, A. K. Vohra, B. S. Gill. Gurgaon, India :
Elsevier, 2000, Computers and Chemical Engineering 23 (2000), pp.
1649-1659.
[9] Combined Hybrid Clustering Techniques and Neural Fuzzy Networks to
Predict Diesel Engine Emissions. Jiamei Deng, Richard Stobart.
Brighton, UK : IEEE, 2007.
[10] Monitoring NOx Emissions from Coal-Fired Boilers using Generalized
Regression Neural Network. Ligang Zheng, Shuijun Yu, Minggao Yu.
Jiaozuo Henan, China : IEEE, 2008, pp. 1916-1919.
[11] Prediction of NOx Concentration from Coal Combustion Using LS-SVR.
Ligang Zheng, Hailin Jia, Shuijun Yu, Minggao Yu. Jiaozuo Henan,
China : IEEE, 2010, pp. 1-4.
[12] Modeling and optimization of the NOx emission characteristics of a
tangentially firedboiler with artificial neural networks. Hao Zhou, Kefa
Cen, Jianren Fan. Hangzhou, PR China : Science Direct, 2001, Energy
29 (2004) 167-183, pp. 167-183.
[13] S., Haykins.Neural networks: a comprehensive foundation, 2nd ed.
Englewood Cliffs, NJ : Prentice-Hall, 1999.
[14] Monitoring pollutant emissions in a 4.8 MW power plant through neural
network. Tronci, S., Baratti, R. and Servida, A. 2002, Neurocomputing,
Vol. 43, pp. 3 - 15.
[15] J.A.K Suykens, T.V. Gestel, J.D Brabenter, B.D Moor, J.
Vandewelle.Least Squares Support Vector Machines. NJ 07661 : World
Scientific Publishing , 2002.
[16] N, Cristianini and J, Shawe-Taylor.An introduction to support vector
machine and other kernel-based learning method. Cambridge :
Cambridge University Press, 2000.
[17] Chih-Wei Hsu, Chih-Chung Chang, and Chih-Jen Lin.A Practical Guide
to Support Vector Classi. Department of Computer Science, National
Taiwan University, Taipei 106, Taiwan. 2010.
[18] Teukolsky, Vetterling, Flannery.Numerical Recipes in C. 2nd Edition.
Cambridge University Press : s.n., 1998.
[19] Optimization by Simulated Annealing. S. Kirkpatrick, C. D. Gelatt and
M. P. Vecchi. 4598, s.l. : American Association for the Advancement of
Science, May 13, 1983, Science, New Series, Vol. 220, pp. 671-680.
[20] S.Jamaludin, S.Manaf, P.Oortwin.World Largest Tangentially Fired
Acid Gas Incinerator in LNG Plant: Startup and Operational
Experiences. Malaysia LNG Sdn. Bhd & Shell Global Solutions
International . 2005. Technical Report.
[21] Adaptive and Iterative Least Squares Support Vector Regression Based
on Quadratic Renyi Entropy. Jingqing Jiang, Chuyi Song,Haiyan
Zhao,Chunguo Wu,Yanchun Liang. Beijing, China : s.n.
[22] Polani, Tobias Jung and Daniel.Sequential Learning with LS-SVM for
Large-Scale Data Sets. Dept. of Computer Science, Univ. of Mainz.
Mainz, Germany : s.n. Technical Report.
[23] Using Analytic QP and Sparseness to Speed Training of Support
VectorMachines. Platt, John C. 11, 1999, Advances in Neural
Information Processing Systems.
[1] U.S Environmental Protection Agency. Clean Air Act as of 2008.
Chapter 85: Air Pollution Prevention and Control. s.l. : U.S Government
Printing Office, 2008.
[2] ENVIRONMENTAL QUALITY (CLEAN AIR) REGULATIONS 1978.
FEDERAL SUBSIDIARY LEGISLATION ENVIRONMENTAL QUALITY
ACT 1974 [ACT 127]. s.l. : Department of Environment, Malaysia,
2000.
[3] Design CEMS For Flue Gas From Thermal Power Plant. Fan Xiaoliang,
Zheng Haiming. Baoding, China : IEEE, 2009.
[4] Developing Data Acquisition and Handling System for Continous
Emission Monitoring System from Coal-Fired Power Plant. Haiming
Zheng, Guiji Tang. Baoding, China : IEEE, 2008.
[5] US Environmental Protection Agency. Climate Change - Health and
Environmental Effects. US EPA Home Page. [Online] [Cited: April 8,
2011.] http://www.epa.gov/climatechange/effects/index.html.
[6] Emission Monitoring Using Multivariate Soft Sensors. Dong, Dong and
McAvoy, Thomas J. Seattle, Washington : American Control
Conference, , 1995.
[7] Neural Networks for Boiler Emission Prediction. Baines, Glenn. s.l. :
Performance Consultant Fisher-Rosemount Solutions, 1999, pp. 435-
439.
[8] Predictive emission monitors (PEMS) for NOx generation in process
heaters. S. S. S. Chakravarthy, A. K. Vohra, B. S. Gill. Gurgaon, India :
Elsevier, 2000, Computers and Chemical Engineering 23 (2000), pp.
1649-1659.
[9] Combined Hybrid Clustering Techniques and Neural Fuzzy Networks to
Predict Diesel Engine Emissions. Jiamei Deng, Richard Stobart.
Brighton, UK : IEEE, 2007.
[10] Monitoring NOx Emissions from Coal-Fired Boilers using Generalized
Regression Neural Network. Ligang Zheng, Shuijun Yu, Minggao Yu.
Jiaozuo Henan, China : IEEE, 2008, pp. 1916-1919.
[11] Prediction of NOx Concentration from Coal Combustion Using LS-SVR.
Ligang Zheng, Hailin Jia, Shuijun Yu, Minggao Yu. Jiaozuo Henan,
China : IEEE, 2010, pp. 1-4.
[12] Modeling and optimization of the NOx emission characteristics of a
tangentially firedboiler with artificial neural networks. Hao Zhou, Kefa
Cen, Jianren Fan. Hangzhou, PR China : Science Direct, 2001, Energy
29 (2004) 167-183, pp. 167-183.
[13] S., Haykins.Neural networks: a comprehensive foundation, 2nd ed.
Englewood Cliffs, NJ : Prentice-Hall, 1999.
[14] Monitoring pollutant emissions in a 4.8 MW power plant through neural
network. Tronci, S., Baratti, R. and Servida, A. 2002, Neurocomputing,
Vol. 43, pp. 3 - 15.
[15] J.A.K Suykens, T.V. Gestel, J.D Brabenter, B.D Moor, J.
Vandewelle.Least Squares Support Vector Machines. NJ 07661 : World
Scientific Publishing , 2002.
[16] N, Cristianini and J, Shawe-Taylor.An introduction to support vector
machine and other kernel-based learning method. Cambridge :
Cambridge University Press, 2000.
[17] Chih-Wei Hsu, Chih-Chung Chang, and Chih-Jen Lin.A Practical Guide
to Support Vector Classi. Department of Computer Science, National
Taiwan University, Taipei 106, Taiwan. 2010.
[18] Teukolsky, Vetterling, Flannery.Numerical Recipes in C. 2nd Edition.
Cambridge University Press : s.n., 1998.
[19] Optimization by Simulated Annealing. S. Kirkpatrick, C. D. Gelatt and
M. P. Vecchi. 4598, s.l. : American Association for the Advancement of
Science, May 13, 1983, Science, New Series, Vol. 220, pp. 671-680.
[20] S.Jamaludin, S.Manaf, P.Oortwin.World Largest Tangentially Fired
Acid Gas Incinerator in LNG Plant: Startup and Operational
Experiences. Malaysia LNG Sdn. Bhd & Shell Global Solutions
International . 2005. Technical Report.
[21] Adaptive and Iterative Least Squares Support Vector Regression Based
on Quadratic Renyi Entropy. Jingqing Jiang, Chuyi Song,Haiyan
Zhao,Chunguo Wu,Yanchun Liang. Beijing, China : s.n.
[22] Polani, Tobias Jung and Daniel.Sequential Learning with LS-SVM for
Large-Scale Data Sets. Dept. of Computer Science, Univ. of Mainz.
Mainz, Germany : s.n. Technical Report.
[23] Using Analytic QP and Sparseness to Speed Training of Support
VectorMachines. Platt, John C. 11, 1999, Advances in Neural
Information Processing Systems.
@article{"International Journal of Earth, Energy and Environmental Sciences:56672", author = "Elangeshwaran Pathmanathan and Rosdiazli Ibrahim and Vijanth Sagayan Asirvadam", title = "Development of NOx Emission Model for a Tangentially Fired Acid Incinerator", abstract = "This paper aims to develop a NOx emission model of
an acid gas incinerator using Nelder-Mead least squares support
vector regression (LS-SVR). Malaysia DOE is actively imposing the
Clean Air Regulation to mandate the installation of analytical
instrumentation known as Continuous Emission Monitoring System
(CEMS) to report emission level online to DOE . As a hardware
based analyzer, CEMS is expensive, maintenance intensive and often
unreliable. Therefore, software predictive technique is often
preferred and considered as a feasible alternative to replace the
CEMS for regulatory compliance. The LS-SVR model is built based
on the emissions from an acid gas incinerator that operates in a LNG
Complex. Simulated Annealing (SA) is first used to determine the
initial hyperparameters which are then further optimized based on the
performance of the model using Nelder-Mead simplex algorithm.
The LS-SVR model is shown to outperform a benchmark model
based on backpropagation neural networks (BPNN) in both training
and testing data.", keywords = "artificial neural networks, industrial pollution,
predictive algorithms, support vector machines", volume = "5", number = "10", pages = "582-6", }
