郭小萍,徐月,李元

• 1:沈阳化工大学 信息工程学院，辽宁 沈阳 110142

摘要(Abstract)：

针对工业生产过程故障检测模型不能及时更新的问题，提出了一种特征空间自适应k近邻（feature space adaptive k-nearest neighbor，FS-AkNN）故障检测方法。首先利用主元分析对训练数据进行降维，构建特征空间，然后利用k最近邻方法建立故障检测模型。在过程监视过程中，提出了基于距离规则的自适应更新故障检测模型。通过一个数值例子和TE过程的仿真实验结果表明了该方法的有效性。

关键词(KeyWords)： 自适应;k近邻(kNN);主元分析;故障检测

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（61673279）；国家自然科学基金重大项目（61490701）；辽宁省科学事业公益研究基金（2016001006）。

作者(Author): 郭小萍,徐月,李元

DOI: 10.3969/j.issn.1003-9015.2019.02.025

参考文献(References)：

• [1] QIN S J. Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control, 2012, 36(2):220-234.
  [2] YIN S, LI X, GAO H, et al. Data-based techniques focused on modern industry:An overview[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1):657-667.
  [3] 马贺贺. 基于数据驱动的复杂工业过程故障检测方法研究[D]. 上海:华东理工大学, 2013.MA H H. Research on fault detection method for complex industrial process based on data driven[D]. Shanghai:East China University of Science and Technology, 2013.
  [4] MISRA M, YUE H H, QIN S J, et al. Multivariate process monitoring and fault diagnosis by multi-scale PCA[J]. Computers & Chemical Engineering, 2002, 26(9):1281-1293.
  [5] WANG Q, LIU Y B, HE X, et al. Fault diagnosis of bearing based on kPCA and kNN method[J]. Advanced Materials Research, 2014, 986-987:1491-1496.
  [6] 张汉元, 田学民. 基于异步PCA的故障识别方法)[J]. 高校化学工程学报, 2016, 30(3):680-685.ZHANG H Y, TIAN X M. Fault identification method based on asynchronous PCA[J]. Journal of Chemical Engineering of Chinese Universities, 2016, 30(3):680-685.
  [7] 刘康玲. 基于自适应PCA和时序逻辑的动态系统故障诊断研究[D]. 杭州:浙江大学, 2017.LIU K L. Research on fault diagnosis of dynamic system based on adaptive PCA and sequential logic[D]. Hangzhou:Zhejiang University, 2017.
  [8] HE Q P, WANG J W J. Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4):345-354.
  [9] LI W, YUE H H, VALLE-CERVANTES S, et al. Recursive PCA for adaptive process monitoring[J]. Journal of Process Control, 2000, 10(5):471-486.
  [10] WOLD S. Exponentially weighted moving principal components analysis and projections to latent structure[J]. Chemometrics & Intelligent Laboratory Systems, 1994, 23(1):149-161.
  [11] LEE D S, VANROLLEGHEM P A. Monitoring of a sequencing batch reactor using adaptive multiblock principal component analysis[J]. Biotechnology and Bioengineering, 2003, 82(4):489-497.
  [12] LEE D S, PARK J M, VANROLLEGHEM P A. Adaptive multiscale principal component analysis for on-line monitoring of a sequencing batch reactor[J]. Journal of Biotechnology, 2005, 116(2):195-210.
  [13] LENNOX J, ROSEN C. Adaptive multiscale principal components analysis for online monitoring of wastewater treatment[J]. Water Science & Technology A Journal of the International Association on Water Pollution Research, 2002, 45(4-5):227.
  [14] 杨丰铭. 基于自适应PCA的油田生产故障诊断方法[J]. 化工管理, 2017(18):21-21.YANG F M. Oilfield production fault diagnosis method based on adaptive PCA[J]. Chemical Industry Management, 2017(18):21-21.
  [15] 张媛媛, 韩少廷, 耿志强, 等.自适应移动窗递推PCA过程监测方法研究)[J]. 计算机与应用化学, 2011, 28(8):1022-1026.ZHANG Y Y, HAN S T, GENG Z Q, et al. Research on monitoring method of recursive PCA process with adaptive mobile window[J]. Computers and Applied Chemistry, 2011, 28(8):1022-1026.
  [16] RYU S R, NODA I, JUNG Y M. Moving window principal component analysis for detecting positional fluctuation of spectral changes[J]. Bulletin-Korean Chemical Society, 2011, 32(7):2332-2338.
  [17] 郭小萍, 袁杰, 李元. 基于特征空间k最近邻的批次过程监视[J]. 自动化学报, 2014, 40(1):135-142.GUO X P, YUAN J, LI Y. Batch process monitoring based on k-nearest neighbor in feature space[J]. Acta Automatica Sinica, 2014, 40(1):135-142.
  [18] 郭金玉, 王鑫, 李元. 基于加权差分主元分析的化工过程故障检测[J]. 高校化学工程学报, 2018, 32(1):186-196.GUO J Y, WANG X, LI Y. Chemical process fault detection based on weighted difference principal component analysis[J]. Journal of Chemical Engineering of Chinese Universities, 2018, 32(1):186-196.
  [19] ZHU W, SUN W, ROMAGNOLI J A. Adaptive k-nearest-neighbor method for process monitoring[J]. Industrial & Engineering Chemistry Research, 2018, 57(7):2574-2586.
  [20] GE Z, SONG Z. Multimode process monitoring based on Bayesian method[J]. Journal of Chemometrics, 2010, 23(12):636-650.
  [21] 周东华, 李钢, 李元. 数据驱动的工业过程故障诊断技术[M]. 北京:科学出版社, 2011.ZHOU D H, LI G, LI Y. Data driven industrial process fault diagnosis technology[M]. Beijing:Science Press, 2011.