The Integrated Design Technology for Simultaneous Dust Control and Desulfurization System Based on Bayes Network Model

doi:10.11930/j.issn.1004-9649.201606172

Abstract

Abstract: Based on the theoretical and data analysis, this paper finds out the design and operation parameters of the desulfurization system capable of removing the dust simultaneously, then builds up the Bayes Network Model and trains the model with a large number of the design and operation data collected from the units adopting simultaneous dust removal and desulfurization technology. The model quantifies the impacts of desulfurization parameters on dust removal efficiency and is integrated into the design system to conduct future reconstruction for dust simultaneous control, and solve the problem of excessive dust emission in the applications of the desulfurization system with simultaneous dust removal technology in coal fired power plants. The integrated design system has been successfully used in several coal fired power plant of China Datang Corporation. After reconstruction, the dust emissions at the inlet of the chimney have met the designed target and been stabilized for long term.

Key words: coal fired power plant, dust removal control, desulfurization, integrated system

CLC Number:

TK39
TM621

WANG Yifei. The Integrated Design Technology for Simultaneous Dust Control and Desulfurization System Based on Bayes Network Model[J]. Electric Power, 2017, 50(9): 129-134.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.201606172

https://www.electricpower.com.cn/EN/Y2017/V50/I9/129

References

[1] 朱法华. 燃煤电厂烟气污染物超低排放技术路线的选择[J]. 中国电力,2017,50（3）：11-16.
ZHU Fahua. Methodologies on choosing appropriate technical route for ultra low emission of flue gas pollutants from coal-fired power plants [J]. Electric Power, 2017, 50(3): 11-16.
[2] 黄茹,马德彭,莫华,等. 基于CFB-FGD技术的烟气超低排放工程性能测试评估[J]. 中国电力,2017,50（3）：17-21.
HUANG Ru, MA Depeng, MO Hua, et al . Testing and assessment on performance of flue gas ultra low emission based on CFB-FGD technology [J]. Electric Power, 2017, 50(3): 17-21.
[3] 曾令可,牛艳鸽,刘涛,等. 湿法烟气脱硫除尘一体化技术[J]. 中国陶瓷工业,2009,16(1)：39-41.
ZENG Lingke, NIU Yange, LIU Tao, et al . The integrated wet flue gas desulfurization and dust separation technology [J]. China Ceramic Industry, 2009, 16(1): 39-41.
[4] 霍利民,朱永利,范高峰,等. 一种基于贝叶斯网络的电力系统可靠性评估新方法[J]. 电力系统自动化,2003,27（5）：36-40.
HUO Limin, ZHU Yongli, FAN Gaofeng, et al . A new method for reliability assessment of power system based on Bayeslan networks[J]. Automation of Electric Power Systems, 2003, 27(5): 36-40.
[5] 冯金煌,陈活虎. 脱硫喷淋塔除尘的影响因素及效果分析[J]. 环境工程,2010,28（3）：70-84.
FENG Jinhuang, CHEN Huohu. Analysis of dedusting influencing factors and effect of sprayer in desulphurization system[J]. Environmental Engineering, 2010, 28(3): 70-84.
[6] 岳焕玲,原永涛,宏哲. 石灰石-石膏湿法烟气脱硫喷淋塔除尘机理分析[J]. 电力环境保护,2006,22（6）：13-15.
YU Huanling, YUAN Yongtao, HONG Zhe. Analysis of dust removal mechanism in sprayer of limestone/gypsum wet flue gas desulfurization system[J]. Electric Power Environmental Protection, 2006, 22(6): 13-15.
[7] 夏力伟,张学锁,梁会友,等. 脱硫协同除尘技术在大型火电机组中的应用研究[J]. 中国高新技术企业,2016（12）：83-85.
[8] DAVID H. A tutorial on learning with Bayesian networks, in learning in graphical [M]. Cambridges MIT Press: 1997.
[9] MURPHY K. A brief introduction to graphical models and Bayesian networks [EB/OL]. [2017-01-05]. http://www.cs.ubc.ca/~murphyk/Bayes/bnintro.html.
[10] 郑慧萌,刘卫东,肖承地,等. 基于贝叶斯网络的硬件产品设计缺陷评估[J]. 计算机工程与应用,2016,52（19）：228-233.
ZHENG Huimeng, LIU Weidong, XIAO Chengdi, et al . Assessment of hardware product design defects using Bayesian networks[J]. Computer Engineering and Applications, 2016, 52(19): 228-233.
[11] FRIEDMAN N, GOLDSZMIDT M. Learning Bayesian networks with local structure[C]// Proceedings of the 12 th conference on uncertainty in artificial intelligence. Portland, August 1-4, 1996.
[12] 张孝远,张新萍,苏保平. 基于最小最大核 K 均值聚类算法的水电机组振动故障诊断[J].电力系统保护与控制,2015,43（5）：27-34.
ZHANG Xiaoyuan, ZHANG Xinping, SU Baoping. Vibrant fault diagnosis for hydro-turbine generating unit using minmax kernel K-means clustering algorithm[J]. Power System Protection and Control, 2015, 43(5): 27-34.
[13] 周志华. 机器学习[M]. 北京：清华大学出版社,2016：198-200.
[14] 蔡娜,王俊英,刘惟一. 一种基于小数据集的贝叶斯网络学习方法[J]. 云南大学学报（自然科学版）,2007,29（4）：359-363.
CAI Na, WANG Junying, LIU Weiyi. An approach to learning Bayesian networks from small data set[J]. Journal of Yunnan University(Natural Sciences Edition), 2007, 29(4): 359-363.
[15] 王双成,冷翠平,李小琳. 小数据集的贝叶斯网络结构学习[J]. 自动化学报,2009,35（8）：1063-1070.
WANG Shuangcheng, LENG Cuiping, LI Xiaolin. Learning Bayesian network structure from small data set[J]. Acta Autornatica Sinica, 2009, 35(8): 1063-1070.
[16] Ethem Alpaydin. 机器学习导论[M]. 范明,译. 北京：机械工业出版社,2015.