火电厂湿法脱硫系统浆液循环泵组合运行优化方法研究  

Research on Optimization Method for Combined Operation of Slurry Circulating Pump in Wet Desulfurization System of Thermal Power Plant

作　　者：晏儒先 胡蓉蓉 肖承明 程恩路 YAN Ruxian;HU Rongrong;XIAO Chengming;CHENG Enlu(Guodian Huangjinbu Power Co.,Ltd.,Shangrao,China 335101;Nanjing Guodian Environmental Protection Technology Co.,Ltd.,Nanjing,China 210061)

机构地区：[1]国能黄金埠发电有限公司,江西上饶335101 [2]南京国电环保科技有限公司,江苏南京210061

出　　处：《热能动力工程》2024年第7期140-147,156,共9页Journal of Engineering for Thermal Energy and Power

基　　金：国家能源投资集团有限责任公司科技项目(HJ-22-KJ|2022|4)。

摘　　要：针对浆液循环泵传统依靠操作人员经验运行、缺乏精细化管理手段导致运行能耗偏高的问题提出了一种基于数据挖掘的浆液循环泵组合运行优化方法,通过模糊C-均值算法(FCM)对历史运行数据进行特征相似组的聚类,并构建以烟囱出口SO_(2)排放浓度为约束的能耗目标函数,从而在聚类中筛选出最优泵组合形成历史工况库,并利用该库训练了LightGBM分类器,实现了泵组合的智能优化运行。将所提优化方法实际应用于某650 MW火电机组,结果表明:相比传统经验运行方式,脱硫能耗环比降低6.6%,同比降低7.3%,证明了该优化方法的有效性和实用性。As the slurry circulating pump traditionally relies on the experience of operators and lacks the means of fine management,resulting in high energy consumption during operation,this paper proposes a slurry circulating pump combined operation optimization method based on data mining.The fuzzy Cmeans(FCM)clustering algorithm is used to cluster the historical operation data with similar characteristics,and the energy consumption objective function is constructed with SO_(2)emission concentration at the chimney outlet as constraint,so as to screen the optimal pump combination in the clustering and form the historical working condition database.The light gradient boosting machine(LightGBM)classifier is trained by the database,and the intelligent optimal operation of pump combination is realized.The optimization method proposed in this paper is actually deployed in a 650 MW thermal power unit.The results show that compared with the traditional empirical operation mode,the desulfurization energy consumption is reduced by 6.6%on a month-on-month basis and 7.3%on a year-on-year basis,which proves the effectiveness and practicability of the optimization method.

关 键 词：湿法脱硫 浆液循环泵 组合运行优化 模糊C-均值聚类 LightGBM 数据挖掘 

分 类 号：X511[环境科学与工程—环境工程]