Chemical Industry and Engineering Progress ›› 2019, Vol. 38 ›› Issue (03): 1573-1578.DOI: 10.16085/j.issn.1000-6613.2018-1190

Previous Articles     Next Articles

Online monitoring heating surface pollution of a boiler economizer in coal-fired power plant

Haiping XIAO1(),Yuhui CHEN1,Jinlin GE1,Xiaoning WANG1,Jianlin XI2,Lining LIU2   

  1. 1. School of Energy Power and Mechanical Engineering, North China Electric Power University, Beijing 102206, China
    2. Huaneng Ningxia Daba Fourth Power Generation Company, Qingtongxia 751600, Ningxia, China
  • Received:2018-06-07 Revised:2018-10-11 Online:2019-03-05 Published:2019-03-05

电站锅炉省煤器受热面的积灰监测

肖海平1(),陈裕辉1,葛金林1,王晓宁1,席建林2,刘利宁2   

  1. 1. 华北电力大学能源动力与机械工程学院,北京 102206
    2. 华能宁夏大坝电厂四期发电有限公司,宁夏 青铜峡 751600
  • 作者简介:肖海平(1978—),男,博士,副教授,主要从事燃煤污染物生成机理与控制技术等方面的研究。E-mail:xiaohaiping@ncepu.edu.cn
  • 基金资助:
    华能集团总部科技项目(HNK J18-H21);基金项目:国家科技支撑计划(2015BAA04B02)

Abstract:

To realize online monitoring heating surface pollution of an economizer in coal-fired power plant boiler, support vector machine (SVM) algorithm was used to predict the clean heat absorption of the economizer. At the same time, the gray wolf algorithm (GWO) and genetic algorithm was used for parameters optimization, and prediction accuracy in two models was compared. According to the cleaning heat absorption, the cleaning factor was calculated. The economizer’s fouling was judged according to the change of cleaning factor. Take a 660MW unit as an example, the data after short blow was taken as clean samples for training and validation. The results showed that GWO has higher prediction accuracy than genetic algorithm (GA), and the training time of GWO is shorter. Finally, this model was used to predict the clean heat absorption of an economizer before long blowing, then the clean factor curve was drawn. The fouling in an economizer heating surface can be performed well. Thus, a basis for an economizer fouling on-line monitoring is offered.

Key words: coal-fired power plant boiler, economizer, fouling, support vector machine, grey wolf optimization algorithm, cleaning factor

摘要:

为了实现电站锅炉省煤器受热面的污染情况在线监测,采用支持向量机算法对省煤器的清洁吸热量进行预测,使用灰狼算法(GWO)和遗传算法对模型进行参数寻优并进行预测精确度的对比。再由清洁吸热量计算清洁因子,根据清洁因子的变化来判断省煤器的积灰状态。以某660MW机组为例,将短吹后的数据作为清洁数据样本进行训练和验证,结果表明灰狼算法比遗传算法预测精度更高,所需训练时间更短。最后利用上述模型来预测长吹前省煤器的清洁吸热量,绘制出清洁曲线图。该模型能较好表现省煤器的积灰情况,为受热面积灰在线监测提供依据。

关键词: 电站燃煤锅炉, 省煤器, 积灰, 支持向量机, 灰狼算法, 清洁因子

CLC Number: 

京ICP备12046843号-2;京公网安备 11010102001994号
Copyright © Chemical Industry and Engineering Progress, All Rights Reserved.
E-mail: hgjz@cip.com.cn
Powered by Beijing Magtech Co. Ltd