郭金玉,王鑫,李元

• 1:沈阳化工大学 信息工程学院，辽宁 沈阳 110142

摘要(Abstract)：

针对工业生产过程的多模态和非线性特性，提出了一种新的基于加权差分主元分析的故障检测算法。首先选取原始数据样本的最近邻x_f以及x_f的前k个近邻，分别计算出x_f的前j个近邻样本的均值m_j和权值w_j，利用加权差分的方法对原始数据进行预处理，剔除多模态和非线性特征；然后利用主元分析法（PCA）计算出负载矩阵P以及SPE和T²检测指标的控制限，建立PCA模型；最后将待检测数据运用加权差分法预处理后投影到PCA模型上计算检测指标，通过检测指标是否超过控制限进行故障检测。将该方法应用于数值例子和半导体生产过程来验证其有效性。

关键词(KeyWords)： 故障检测;多模态;非线性;主元分析;差分预处理;加权差分主元分析

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金重大项目（61490701）；国家自然科学基金（61673279）；辽宁省教育厅重点实验室项目（LZ2015059）；辽宁省自然科学基金（201602584）；辽宁省教育厅项目（L2016007，L2015432）。

作者(Author): 郭金玉,王鑫,李元

DOI: 10.3969/j.issn.1003-9015.2018.01.025

参考文献(References)：

• [1] ZHOU Dong-hua (周东华), LI Gang (李钢), LI Yuan (李元). Fault detection and diagnosis technology of industrial process based on data driven (数据驱动的工业过程故障检测与诊断技术)[M]. Beijing (北京):Science Press (科学出版社), 2011:1-76.
  [2] ZHANG Han-yuan (张汉元), TIAN Xue-min (田学民). A fault identification method based on asynchronous PCA (基于异步PCA的故障识别方法)[J]. Journal of Chemical Engineering of Chinese Universities (高校化学工程学报), 2016, 30(3):680-685.
  [3] Gueddi I, Nasri O, Benothman K, et al. Fault detection and isolation of spacecraft thrusters using an extended principal component analysis to interval data[J]. International Journal of Control Automation & Systems, 2017, 15(2):1-14.
  [4] Hamadache M, Lee D. Principal component analysis based signal-to-noise ratio improvement for inchoate faulty signals:application to ball bearing fault detection[J]. International Journal of Control Automation & Systems, 2017, 15(2):1-12.
  [5] Jaffel I, Taouali O, Harkat M F, et al. Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring[J]. International Journal of Advanced Manufacturing Technology, 2016, 88(9-12):1-15.
  [6] Adedigba S A, Khan F, Yang M. Dynamic failure analysis of process systems using principal component analysis and Bayesian Network[J]. Industrial & Engineering Chemistry Research, 2017, 56(8):2094-2106.
  [7] WANG Ya-jun (王亚君), ZHOU Qi (周岐). Research on statistical process monitoring strategy based on multi-dynamic kernel PCA (基于多动态核PCA的统计过程监测策略研究)[J]. Journal of Liaoning University of Technology (Natural Science Edition) (辽宁工业大学学报(自然科学版)), 2012, 32(5):295-298.
  [8] CHEN Ru-qing (陈如清). Nonlinear process fault detection method under noise environment using KPCA and MVU (基于KPCA-MVU的噪声非线性过程故障检测方法)[J]. Chinese Journal of Scientific Instrument (仪器仪表学报), 2014, 35(12):2673-2680.
  [9] Xiao Y W, Zhang X H. Novel nonlinear process monitoring and fault diagnosis method based on KPCA-ICA and MSVMs[J]. Journal of Control, Automation and Electrical Systems, 2016, 27(3):289-299.
  [10] Joseph A A, Tokumoto T, Ozawa S. Online feature extraction based on accelerated kernel principal component analysis for data stream[J]. Evolving Systems, 2016, 7(1):15-27.
  [11] MA He-he (马贺贺), HU Yi (胡益), SHI Hong-bo (侍洪波). Unsupervised fault detection for multimode processes using distance space statistics analysis (基于距离空间统计量分析的多模态过程无监督故障检测)[J]. CIESC Journal (化工学报), 2012, 63(3):873-880.
  [12] GUO Jin-yu (郭金玉), YUAN Tang-ming (袁堂明), LI Yuan (李元). Fault detection method for uneven-length multimode batch processes (一种不等长的多模态间歇过程故障检测方法)[J]. CIESC Journal (化工学报), 2016, 67(7):2916-2924.
  [13] LIU Bang-li (刘帮莉), MA Yu-xin (马玉鑫), SHI Hong-bo (侍洪波). Multimode process monitoring based on local density estimation (基于局部密度估计的多模态过程故障检测)[J]. CIESC Journal (化工学报), 2014, 65(8):3071-3081.
  [14] Deng X G, Tian X M. Multimode process fault detection using local neighborhood similarity analysis[J]. Chinese Journal of Chemical Engineering, 2014, 22(11-12):1260-1267.
  [15] Guo J Y, Yuan T M, Li Y. Fault detection of multimode process based on local neighbor normalized matrix[J]. Chemometrics & Intelligent Laboratory Systems, 2016, 1548:162-175.
  [16] Yang Y W, Ma Y X, Song B, et al. An aligned mixture probabilistic principal component analysis for fault detection of multimode chemical processes[J]. Chinese Journal of Chemical Engineering, 2015, 23(8):1357-1363.
  [17] Jiang Q C, Yan X F. Joint probability density and double-weighted independent component analysis for multimode non-gaussian process monitoring[J]. Industrial & Engineering Chemistry Research, 2014, 53(52):20168-20176.
  [18] He Q P, Wang J. Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4):345-354.
  [19] Ma H H, Hu Y, Shi H B. Fault detection and identification based on the neighborhood standardized local outlier factor method[J]. Industrial & Engineering Chemistry Research, 2013, 52(6):2389-2402.
  [20] Odiowei P P, Cao Y. Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations[J]. Computer Aided Chemical Engineering, 2009, 27(1):1557-1562.
  [21] Mori J, Yu J. Quality relevant nonlinear batch process performance monitoring using a kernel based multiway non-Gaussian latent subspace projection approach[J]. Journal of Process Control, 2014, 24(1):57-71.
  [22] Ge Z Q, Song Z H. Multimode process monitoring based on Bayesian method[J]. Journal of Chemometrics, 2009, 23(12):636-650.
  [23] Wise B M, Gallagher N B, Butler S W, et al. A comparison of principal component analysis, multiway principal component analysis, trilinear decomposition and parallel factor analysis for fault detection in a semiconductor etch process[J]. Journal of Chemometrics, 1999, 13(3-4):379-396.
  [24] Lee S P, Chao A K, Tsung F, et al. Monitoring batch processes with multiple on-off steps in semiconductor manufacturing[J]. Journal of Quality Technology, 2011, 43(2):142-157.
  [25] He Q P, Wang J. Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4):345-354.
  [26] Yu J. Fault detection using principal components-based Gaussian mixture model for semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2011, 24(3):432-444.
  [27] Yang J G, Zhang J, Yang J X, et al. A principal component analysis based fault detection method in etch process of semiconductor manufacturing[J]. Key Engineering Materials, 2012, 522:793-798.
  [28] Fan S K S, Huang S H. Full fault detection for semiconductor processes using independent component analysis[M]. Proceedings of the Institute of Industrial Engineers Asian Conference, 2013:465-470.