基于KLD信息距的过热汽温建模数据提取方法  

A Data Extraction Method for the Modeling of Superheated Steam Temperature Systems Using Kullback-Leibler Divergence

作　　者：杨巍[1] 洪烽 于浩洋 申忠利[2] YANG Wei;HONG Feng;YU Haoyang;SHEN Zhongli(State Key Lab of Alternate Electric Power System with Renewable Energy Sources,North China Electric Power University,Beijing 102206,China;School of Energy and Power Engineering,Changsha University of Science and Technology,Changsha 410114,China)

机构地区：[1]华北电力大学新能源电力系统国家重点实验室,北京102206 [2]长沙理工大学能源与动力工程学院,长沙410114

出　　处：《动力工程学报》2020年第3期219-223,256,共6页Journal of Chinese Society of Power Engineering

基　　金：国家重点研发计划资助项目(2016YFB0600205);中央高校基本科研业务费专项资助项目(JB2018ZD05,JB2019MS019)。

摘　　要：提出一种基于KLD(Kullback-Leibler Divergence)信息距的建模数据提取方法,首先利用运行数据构建KLD序列,然后对KLD序列进行线性分段,再根据分段结果提取建模数据。利用大型火电机组过热汽温仿真数据和运行数据进行了数据提取和建模验证。结果表明:采用所提方法取得了较好的建模效果,检验了该方法的有效性。A data extraction method was proposed for the modeling of superheated steam temperature systems based on Kullback-Leibler divergence(KLD),which uses operation data to construct the KLD sequence,and then the KLD sequence is linearly segmented.The data for modeling are finally extracted according to the segmented results.The simulation and field operation data of a large-scale thermal power unit were applied to verify the data extraction method for the modeling of its superheated steam temperature system.Results show that better modeling effect could be achieved by the way proposed,proving the data extraction method to be effective.

关 键 词：KLD信息距 曲线熵 串级控制系统 数据分段 系统辨识 

分 类 号：TK39[动力工程及工程热物理—热能工程]