摘要
为了解决石灰石-石膏湿法烟气脱硫系统(Wet Flue Gas Desulfurization System,WFGD)的运行优化问题,基于某电厂600 MW机组的脱硫系统历史运行数据,采用关联规则挖掘方法中的FP-tree(Frequent Pattern-Tree)算法对历史数据进行关联规则的挖掘。在数据挖掘过程中,利用3σ法则去除原始数据中的粗大误差;利用聚类方法中的竞争凝聚(Competitive Agglomeration,CA)算法,对处理后数据的各个属性分别进行聚类,使其划分为不同的区间;选取不同锅炉负荷工况下的数据,利用FP-tree算法挖掘关联规则;挑选出有意义的关联规则。结果表明:在锅炉负荷为540 MW工况时,将脱硫系统中的可调参数浆液pH值设置为4.9901,吸收塔液位设置为8.9478 m,吸收塔给浆流量设置为8.1782 m^3/h,吸收塔给浆密度设置为1229.2723 kg/m^3,可以在满足脱硫效率的前提下使得脱硫成本最低,从而提高电厂的经济效益。
In order to solve the operation optimization problem of the Wet Flue Gas Desulfurization System(WFGD),based on the historical operation data of the desulfurization system of a 600 MW unit of a power plant,the FP-tree(Frequent Pattern Tree)in the association rule mining method is adopted.The algorithm mines the association rules of historical data.In the data mining process,the 3σrules are used to remove the coarse errors in the original data;secondly,the Competitive Agglomeration(CA)algorithm in the clustering method is used to cluster the attributes of the processed data to divide them for different intervals;then select the data under different boiler load conditions,use FP-tree algorithm to mine association rules;finally select meaningful association rules.The research results show that when the boiler load is 540 MW,the adjustable parameter slurry pH value in the desulfurization system is set to 4.9901,the absorption tower liquid level is set to 8.9478 m,and the absorption tower slurry flow is set to 8.1782 m^3/h,and the pulp density of the absorption tower is set to 1229.2723 kg/m^3,the desulfurization cost can be reduced to the lowest under the premise of satisfying the desulfurization efficiency,thereby improving the economic benefit of the power plant.
作者
康英伟
周昊
郭为民
段松涛
KANG Ying-wei;ZHOU Hao;GUO Wei-min;DUAN Song-tao(College of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Rundian Energy Science and Technology Co.Ltd.,Zhengzhou 450052,China)
出处
《热能动力工程》
CAS
CSCD
北大核心
2020年第7期145-151,共7页
Journal of Engineering for Thermal Energy and Power
基金
国家自然科学基金(61573239)
上海发电过程智能管控工程技术研究中心资助项目(14DZ2251100)。
关键词
运行优化
数据挖掘
模糊关联规则
FP-TREE算法
竞争凝聚算法
operation optimization
data mining
fuzzy association rule
FP-tree algorithm
competitive agglomeration algorithm
