期刊文献+

基于k均值聚类与K近邻的故障检测方法研究 被引量:3

下载PDF
导出
摘要 基于K近邻的故障检测(FD-KNN)方法可以有效处理非线性、多模态的故障检测问题,但在过程故障检测中存在计算量大,存储复杂等缺陷.将k均值聚类和K近邻相结合,提出一种新的故障检测方法kFD-KNN,该方法继承传统方法的优点,同时降低计算与存储的影响.首先应用k均值聚类将训练集聚成k类,同时计算聚类中心.通过计算样本与聚类中心的距离,判断样本所属分类.在所属分类中寻求K近邻,进而完成基于KNN的故障检测.本文方法具有计算量小,存储简单等优点,可有效提高检测效率.通过仿真多模态仿真实例进一步验证本文方法的有效性.
出处 《通化师范学院学报》 2013年第6期38-40,共3页 Journal of Tonghua Normal University
基金 国家自然科学基金资助 项目批准号:61174119
  • 相关文献

参考文献7

  • 1Zalik K R. An Efficient K - means Clustering Algorithm [ J ]. Pattern Recognition Letters ,2008,29 (9) : 1385 - 1391.
  • 2J. Ham and M. Kamber. Data mining : concepts and techniques [ M ]. 2nd edition. Morgan Kaufman Publishers,2006 : 1 - 6.
  • 3边肇祺 张学工.模式识别[M].北京:清华大学出版社,1999.282-283.
  • 4Q. P. He and J. Wang. Fault detection using k - nearest neighbor rule for Semiconductor manufacturing processes [ J ]. IEEE Trans. Semic. Manuf. ,2007,20 (4) :345 - 354.
  • 5T. Adamson et al. Strategies for successfully implementing lab- wide fdc methodologies in semiconductor manufacturing [ C ]//Pror. AEC/APC Symp. XVIII, Westminster, CO,2006.
  • 6T. Moore et al. Intel fde proliferation in 300ram hvm: Progress and lessons learned [ C ]//Proc. AEC/APC Syrup. XVIII, Westminster, CO, 2006.
  • 7R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification [ M]. second edition. John Wiley & Sons,blew York,2001.

共引文献142

同被引文献27

  • 1郭江华,侯馨光,陈国钧,张庆.船舶柴油机故障诊断技术研究[J].中国航海,2005,28(4):75-78. 被引量:38
  • 2朱志宇,张冰,刘维亭.模糊支持向量机在船舶柴油机故障诊断中的应用[J].中国造船,2006,47(3):64-69. 被引量:4
  • 3WILLIAMS D,LIAO X J,XUE Y,et al_ On classification with incomplete data [J]. IEEE transactionson March 2007,29(3) : 427-436.
  • 4ANDREA M. Analyzing a randomized experiment with imperfect compliance and ignorable conditions formissing data: theoretical and computational issues [J]. Computational Statistics Data Analysis, 2004,46:493-509.
  • 5HYEKYUNG J,JOSEPH L S,BYUNGTAE S. A latent class selection model for non-ignorable missingdata [J], Computational Statistics and Data Analysis,2001,55: 802-812.
  • 6AMANDA N B,CRAGIG K E. An introduction to modern missing data analyses [J]. Journal of SchoolPsychology,2010,48: 5-37.
  • 7KRZYSZTOF P, MARCIN W,JOZEF K. Towards robustness in neural network based fault diagnosis [J].International Journal Applied Math Computation Science, 2008,18(4) : 443-454.
  • 8MOHAMED E A, ABDELAZIZ A Y, MOSTAFA A S. Fault diagnosis system for power transformers [J].JKAU: England Science,2007, 18(2) : 73-79.
  • 9YAN S,YIYUAN T,SHUXUE D, et al. Diagnose the mild cognitive impairment by constructingBayesian network with missing data [J], Expert Systems with Applications, 2011,38: 442-449.
  • 10TSHILIDZI M,CHAKRAVERTY S. Fault classification in structures with incomplete measured data usingautoassociative neural networks and genetic algorithm [J]. Current Science,2006,90(4) : 542-548.

引证文献3

二级引证文献23

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部