基于模糊聚类的NOx排放多模型预测优化  

Multi-model prediction and optimization for NO_(x) emission based on fuzzy clustering

作　　者：殷喆 杨春来 袁晓磊 吴斌 吕游[2,3] YIN Zhe;YANG Chunlai;YUAN Xiaolei;WU Bin;LYU You(State Grid Hebei Energy Technology Service Co.,Ltd.,Shijiazhuang 050021,China;School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China;Key Laboratory of Power Station Energy Transfer Conversion and System,North China Electric Power University,Beijing 102206,China)

机构地区：[1]国网河北能源技术服务有限公司,河北石家庄050021 [2]华北电力大学控制与计算机工程学院,北京102206 [3]华北电力大学电站能量传递转化与系统教育部重点实验室,北京102206

出　　处：《热力发电》2022年第4期105-111,共7页Thermal Power Generation

基　　金：河北省火力发电节能环保工程技术研究中心项目(20567681H);河北省电力有限公司科技项目(TSS2020-11)。

摘　　要：火电机组广泛参与调峰导致运行工况频繁变动,使得锅炉出口NO_(x)排放的控制难度增大。基于对燃烧状态的影响将锅炉运行参数分为可调参数和不可调参数,并利用不可调参数分布将运行数据样本进行模糊均值聚类划分,以此实现锅炉出口NO_(x)排放特性的多模型预测。同时,利用粒子群算法对各工况所属子模型的可调参数进行寻优来实现NO_(x)排放的优化。对某1000 MW燃煤机组数据仿真表明,提出的NO_(x)排放多模型预测方法比单一模型具有更好的精度,且模型训练时间更短,经过粒子群算法参数优化后NO_(x)排放质量浓度降低了9.98%。The extensive participation of thermal power units in peak regulation leads to frequent fluctuations in operating conditions,which increases the difficulty of NO_(x)emission control at boiler outlet.According to its influence on the combustion,the boiler operation parameters are divided into manipulatable parameters and nonmanipulatable parameters.The data samples are classified according to the non-manipulatable parameter distribution and fuzzy c-means clustering.On this basis,a multi-model method is proposed to predict NO_(x)emission at boiler outlet.Meanwhile,particle swarm optimization algorithm is used to optimize the manipulatable parameters of the sub-models under each working condition,thus to achieve optimization of the NO_(x)emission at the boiler outlet.The simulation on operation data of a 1000 MW coal-fired unit shows that,the proposed multi-model for NO_(x)emission prediction has higher prediction accuracy and consumes less training time.After optimization by particle swarm algorithm,the NO_(x)emission at the boiler outlet reduces by 9.98%.

关 键 词：锅炉 NO_(x)排放 运行优化 模糊均值聚类 多模型预测 

分 类 号：TK268[动力工程及工程热物理—动力机械及工程]