Dynamic process monitoring using adaptive local outlier factor

Abstract A numerically efficient moving window local outlier factor (LOF) algorithm is proposed in this paper for monitoring industrial processes with time-varying and multimode characteristics. The key feature of the proposed algorithm can be identified as its underlying capability to handle complex data distributions and incursive operating condition changes including both slow dynamic variations and instant mode shifts. With some updating of the rules developed for accelerating the computation speed, a two-step adaption approach is introduced to keep the monitoring model up-to-date. Then, a switch strategy and an update termination rule are designed to deal with operating mode changes. Due to the utilization of local information, the proposed algorithm has a superior ability both in detecting faulty conditions and fast adapting to new operating modes. Finally, the utility of the proposed method is demonstrated through a numerical example and a non-isothermal continuous stirred tank reactor (CSTR).

[1]  Uwe Kruger,et al.  Recursive partial least squares algorithms for monitoring complex industrial processes , 2003 .

[2]  Jialin Liu.  Modeling a Large-Scale Nonlinear System Using Adaptive Takagi−Sugeno Fuzzy Model on PCA Subspace , 2007 .

[3]  Wei Wang,et al.  A comparison of outlier detection algorithms for ITS data , 2010, Expert Syst. Appl..

[4]  Rajagopalan Srinivasan,et al.  Multi-model based process condition monitoring of offshore oil and gas production process , 2010 .

[5]  Zhi-huan Song,et al.  Mixture Bayesian regularization method of PPCA for multimode process monitoring , 2010 .

[6]  S. Zhao,et al.  Monitoring of Processes with Multiple Operating Modes through Multiple Principle Component Analysis Models , 2004 .

[7]  Zhi-huan Song,et al.  Online monitoring of nonlinear multiple mode processes based on adaptive local model approach , 2008 .

[8]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[9]  In-Beum Lee,et al.  Adaptive multivariate statistical process control for monitoring time-varying processes , 2006 .

[10]  Jyh-Cheng Jeng,et al.  Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms , 2010 .

[11]  Zhi-huan Song,et al.  Process Monitoring Based on Independent Component Analysis - Principal Component Analysis ( ICA - PCA ) and Similarity Factors , 2007 .

[12]  C. Yoo,et al.  Overall statistical monitoring of static and dynamic patterns , 2003 .

[13]  Lamiaa M. Elshenawy,et al.  Recursive Fault Detection and Isolation Approaches of Time-Varying Processes , 2012 .

[14]  Chunhui Zhao,et al.  Nonlinear Batch Process Monitoring Using Phase-Based Kernel-Independent Component Analysis-Principal Component Analysis (KICA-PCA) , 2009 .

[15]  Zhiming Li,et al.  Modeling and Monitoring of Dynamic Processes , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Hans-Peter Kriegel,et al.  LoOP: local outlier probabilities , 2009, CIKM.

[17]  H. Shi,et al.  Dynamic Multimode Process Modeling and Monitoring Using Adaptive Gaussian Mixture Models , 2012 .

[18]  Aleksandar Lazarevic,et al.  Incremental Local Outlier Detection for Data Streams , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[19]  Oliver Tomic,et al.  Independent component analysis applied on gas sensor array measurement data , 2003 .

[20]  In-Beum Lee,et al.  Fault Detection Based on a Maximum-Likelihood Principal Component Analysis (PCA) Mixture , 2005 .

[21]  Jie Yu,et al.  A particle filter driven dynamic Gaussian mixture model approach for complex process monitoring and fault diagnosis , 2012 .

[22]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[23]  Fuli Wang,et al.  Multimode Process Monitoring Based on Mode Identification , 2012 .

[24]  Bokyoung Kang,et al.  Integrating independent component analysis and local outlier factor for plant-wide process monitoring , 2011 .

[25]  Shuai Li,et al.  Dynamic processes monitoring using recursive kernel principal component analysis , 2012 .

[26]  Chonghun Han,et al.  Robust Recursive Principal Component Analysis Modeling for Adaptive Monitoring , 2006 .

[27]  Carlos F. Alcala,et al.  Reconstruction-based contribution for process monitoring with kernel principal component analysis , 2010, Proceedings of the 2010 American Control Conference.

[28]  G. Irwin,et al.  Process monitoring approach using fast moving window PCA , 2005 .

[29]  Weihua Li,et al.  Recursive PCA for adaptive process monitoring , 1999 .

[30]  U. Kruger,et al.  Moving window kernel PCA for adaptive monitoring of nonlinear processes , 2009 .

[31]  Pekka Teppola,et al.  Adaptive Fuzzy C-Means clustering in process monitoring , 1999 .

[32]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD 2000.

[33]  Yi Hu,et al.  A novel local neighborhood standardization strategy and its application in fault detection of multimode processes , 2012 .

[34]  Zhiqiang Ge,et al.  Maximum-likelihood mixture factor analysis model and its application for process monitoring , 2010 .

[35]  S. Qin,et al.  Multimode process monitoring with Bayesian inference‐based finite Gaussian mixture models , 2008 .

[36]  Chonghun Han,et al.  On-Line Process State Classification for Adaptive Monitoring , 2006 .

[37]  Yi Hu,et al.  Fault Detection and Identification Based on the Neighborhood Standardized Local Outlier Factor Method , 2013, Industrial & Engineering Chemistry Research.

[38]  Alessandro Pisano,et al.  On-line adaptive clustering for process monitoring and fault detection , 2012, Expert Syst. Appl..

[39]  In-Beum Lee,et al.  Fault detection and diagnosis based on modified independent component analysis , 2006 .

[40]  Seongkyu Yoon,et al.  Fault diagnosis with multivariate statistical models part I: using steady state fault signatures , 2001 .

[41]  Furong Gao,et al.  Mixture probabilistic PCR model for soft sensing of multimode processes , 2011 .

[42]  Jie Yu.  A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes , 2012 .