首页 | 本学科首页   官方微博 | 高级检索  
     

从实测轨迹提取知识时的困难及展望
引用本文:徐伟,薛禹胜,陈实,葛斐,Zhaoyang DONG.从实测轨迹提取知识时的困难及展望[J].电力系统自动化,2009,33(15):1-7.
作者姓名:徐伟  薛禹胜  陈实  葛斐  Zhaoyang DONG
作者单位:1.东南大学电气工程学院,江苏省南京市 210096; 2.国网电力科学研究院/南京南瑞集团公司,江苏省南京市 210003; 3.安徽省电力公司,安徽省合肥市 230002; 4.香港理工大学电机工程学系,香港
基金项目:国家自然科学基金重大项目
摘    要:分析实测轨迹可提供的知识,并按对模型依赖的程度分类。强调在不依赖系统模型的前提下,提炼受扰轨迹信息的重要性。归纳先对实测轨迹降维再提取知识的思路,即利用保稳降维变换将多机轨迹模态的时域识别任务转化为单机的对应问题。采用时频分析方法提取映象单机轨迹的时变特征,并研究轨迹降维及时变因素的影响。指出应该采用可信度校验,在轨迹时变性过强的场合给出提示。指出模型与参数的校核关键是建立随着轨迹动态特征的差异程度而单调变化的指标,进而通过其灵敏度搜索收敛到真值附近。

关 键 词:实测轨迹  动态特征  无模型分析  知识提取  时变性
收稿时间:2009/2/13 0:00:00
修稿时间:7/22/2009 9:42:23 AM

Difficulties and Prospects of Knowledge Extracting from Measured Trajectories
XU Wei,XUE Yusheng,CHEN Shi,GE Fei,Zhaoyang DONG.Difficulties and Prospects of Knowledge Extracting from Measured Trajectories[J].Automation of Electric Power Systems,2009,33(15):1-7.
Authors:XU Wei  XUE Yusheng  CHEN Shi  GE Fei  Zhaoyang DONG
Affiliation:1.Southeast University;Nanjing 210096;China;2.State Grid Electric Power Research Institute;Nanjing 210003;3.Anhui Electric Power Corporation;Hefei 230002;4.Hong Kong Polytechnic University;Hong Kong;China
Abstract:Knowledge extracted from measured trajectories is categorized according to the support extent of system models.The importance of extracting information from disturbed trajectories without system models is emphasized.The idea of extracting knowledge after trajectory aggregation is summarized.Therefore,mode identification task of multi-machine trajectories in time domain is converted into that of single-machine trajectory with the stability-preserving dimensional-reduction transformation.Time-frequency analys...
Keywords:measured trajectory  dynamic characteristic  model free analysis  knowledge extracting  time-variation
本文献已被 CNKI 等数据库收录!
点击此处可从《电力系统自动化》浏览原始摘要信息
点击此处可从《电力系统自动化》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号