基于主成分分析的电站锅炉受热面灰污监测方法

A PCA-Based Method for Ash Fouling Monitoring on Heating Surfaces Power Plant Boiler

目前我国电站锅炉的吹灰一般基于操作规程定期进行,可能导致受热面欠吹或过吹,影响电厂的经济性运行。为此提出一种基于主成分分析法的电站锅炉受热面灰污监测方法。以某660 MW电厂的屏式过热器、高温再热器和低温再热器为例,首先选取影响受热面换热的运行参数;对获取的机组运行数据进行异常值筛选和剔除,并将数据划分为训练集和测试集;然后采用PCA方法获得运行数据的主成分;最后通过测试集SPE统计量与训练集SPE统计量的控制限进行比较,判断受热面灰污情况。通过对比同一数据源机理建模的洁净因子验证可知,所提出的方法可以有效准确地对电站锅炉受热面进行灰污在线监测。

At present,the soot blowing of power plant boilers in my country is generally carried out regularly based on operating regulations,which may lead to under-blowing or over-blowing of the heating surface and affect the economic operation of power plant.To this end,the paper proposes a method for monitoring dust pollution on the heating surface of power plant boilers based on principal component analysis(PCA).Taking the panel superheater,high temperature reheater and low temperature reheater of a 660 MW power plant as an example,the paper first selects the operating parameters that affect the heat transfer of the heating surface,screens and eliminates outliers in the obtained operating data of the unit,and divides the data into training set and test set,then uses PCA method to obtain the principal components of the operating data,and finally makes comparison between the control limit of the squared prediction error(SPE)statistic of the test set and that of the SPE statistic of the training set to determine the ash fouling condition of the heating surface.Comparing the clean factor verification of the same data source mechanism modeling finds that the proposed method can effectively and accurately monitor the ash pollution on the heating surface of the power plant boiler online.