Prediction Model of SO2 Distribution in Boiler Based on Deep Neural Network

被引：0

作者：

Tang, Zhenhao ^{[1
]}

Zhang, Chong ^{[1
]}

Cao, Shengxian ^{[1
]}

Shen, Tao ^{[2
]}

机构：

[1] Northeast Elect Power Univ, Sch Automat Engn, Jilin, Jilin, Peoples R China

[2] Harbin Boiler Co Ltd, Harbin, Peoples R China

来源：

2020 CHINESE AUTOMATION CONGRESS (CAC 2020) | 2020年

基金：

中国国家自然科学基金;

关键词：

CFD simulation; SO2; distribution; DNN algorithm; Lasso method; NOX EMISSION CHARACTERISTICS; COMBUSTION;

D O I：

10.1109/CAC51589.2020.9326956

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The prediction of SO2 distribution in the boiler is an important basis for accurate control of the combustion process. In order to better grasp the distribution of SO2 inside the boiler, and at the same time solve the problems of long time-consuming CFD numerical simulation process and narrow coverage of typical working conditions, a deep neural network (DNN)-based SO2 prediction model in the furnace is proposed. The model uses the Lasso method to select the characteristics of SO2 related variables, and on this basis, selects the DNN algorithm for predictive modeling. Experimental results show that DNN has higher prediction accuracy compared with common data modeling methods, and the average absolute error is reduced by about 36.66% and 76.38%.

引用

页码：3222 / 3225

页数：4

共 16 条

[1] Numerical investigation on the flow, combustion and NOx emission characteristics in a 500 MWe tangentially fired pulverized-coal boiler [J].

Choi, Choeng Ryul ;

Kim, Chang Nyung .

FUEL, 2009, 88 (09) :1720-1731

[2]

Hari P. S., 2002, ENERGY FUELS, V15, P470

[3]

Hill S. C., 2011, PROGR ENERGY COMBUST, V26, P417

[4] A generalized model of SO2 emissions from large- and small-scale CFB boilers by artificial neural network approach Part 1. The mathematical model of SO2 emissions in air-firing, oxygen-enriched and oxycombustion CFB conditions [J].

Krzywanski, J. ;

Czakiert, T. ;

Blaszczuk, A. ;

Rajczyk, R. ;

Muskala, W. ;

Nowak, W. .

FUEL PROCESSING TECHNOLOGY, 2015, 137 :66-74

[5] Development of high-temperature corrosion risk monitoring system in pulverized coal boilers based on reducing conditions identification and CFD simulations [J].

Modlinski, Norbert ;

Hardy, Tomasz .

APPLIED ENERGY, 2017, 204 :1124-1137

[6] Predicting air pollutant emissions from a medical incinerator using grey model and neural network [J].

Pai, Tzu-Yi ;

Lo, Huang-Mu ;

Wan, Terng-Jou ;

Chen, Li ;

Hung, Pei-Shan ;

Lo, Hsuan-Hao ;

Lai, Wei-Jia ;

Lee, Hsin-Yi .

APPLIED MATHEMATICAL MODELLING, 2015, 39 (5-6) :1513-1525

[7] Effects of burner tilt angle on the combustion and NOx emission characteristics of a 700 MWe deep-air-staged tangentially pulverized-coal-fired boiler [J].

Tan, Peng ;

Tian, Dengfeng ;

Fang, Qingyan ;

Ma, Lun ;

Zhang, Cheng ;

Chen, Gang ;

Zhong, Lijin ;

Zhang, Honggang .

FUEL, 2017, 196 :314-324

[8] The multi-objective optimization of combustion system operations based on deep data-driven models [J].

Tang, Zhenhao ;

Zhang, Zijun .

ENERGY, 2019, 182 :37-47

[9] Adaptive Nonlinear Model Predictive Control of the Combustion Efficiency under the NOx Emissions and Load Constraints [J].

Tang, Zhenhao ;

Wu, Xiaoyan ;

Cao, Shengxian .

ENERGIES, 2019, 12 (09)

[10] Numerical Modeling of Victorian Brown Coal Combustion in a Tangentially Fired Furnace [J].

Tian, Zhao F. ;

Witt, Peter J. ;

Schwarz, M. Phillip ;

Yang, William .

ENERGY & FUELS, 2010, 24 (09) :4971-4979

← 1 2 →