中国电力 ›› 2017, Vol. 50 ›› Issue (12): 87-92.DOI: 10.11930/j.issn.1004-9649.201608015

• 发电 • 上一篇    下一篇

基于动态数据挖掘的汽轮机调节门流量特性在线计算

文乐1, 杨新民1, 薛志恒1, 高林1, 赵金旭2   

  1. 1. 西安热工研究院有限公司,陕西 西安 710054;
    2. 大唐七台河发电有限责任公司,黑龙江 七台河 154600
  • 收稿日期:2016-09-10 修回日期:2017-08-30 出版日期:2017-12-20 发布日期:2018-01-30
  • 作者简介:文乐(1987—),男,陕西镇安人,硕士,工程师,从事火电大数据挖掘与应用、火电站设备节能与诊断研究。E-mail:wenle@tpri.com.cn

Online Calculation of Steam Turbine Valve Discharge Characteristics by Dynamic Data Mining Approaches

WEN Le1, YANG Xinmin1, XUE Zhiheng1, GAO Lin1, ZHAO Jinxu2   

  1. 1. Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China;
    2. Datang Qitaihe Power Generation Co., Ltd., Qitaihe 154600, China
  • Received:2016-09-10 Revised:2017-08-30 Online:2017-12-20 Published:2018-01-30

摘要: 为实现汽轮机调节门流量特性实时分析和在线监测,建立动态数据挖掘模型用于调节门流量特性计算,以某厂350 MW超临界汽轮机组为例检验该方法。研究结果表明:所建立的动态数据挖掘模型能够从实时运行数据中提取和更新计算样本,利用移动最小二乘法建立的数学模型很好地反映了输入参数与输出参数之间的映射关系,与汽轮机性能试验结果相比偏差在1.5%以内,是一种行之有效的在线计算方法。

关键词: 火电厂, 汽轮机, 调节门流量特性, 动态数据挖掘, 移动最小二乘法

Abstract: For the purpose of conducting real-time analysis and online monitoring on the valve discharge characteristics of the steam turbine, one dynamic data mining model is built up for the valve discharge characteristics calculation. A 350 MW turbine set is used to validate the dynamic data mining model. The results show that the dynamic data mining model can extract and update calculation samples. Moreover, the mathematical model established by moving least square method can simulate the mapping relationship between the input and output parameters well. The average relative error is less than 1.5% between the mathematical model and the results of the steam turbine performance testing, which verifies that this dynamic data mining model is an effective approach for valve discharge characteristics online calculation.

Key words: thermal power plant, steam turbine, valve discharge characteristics, dynamic data mining, moving least square

中图分类号: