Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

Process monitoring and fault diagnosis of the continuous annealing process lines (CAPLs) have been a primary concern in industry. Stable operation of the line is essential to final product quality and continuous processing of the upstream and downstream materials. In this paper, a multilevel principal component analysis (MLPCA)-based fault diagnosis method is proposed to provide meaningful monitoring of the underlying process and help diagnose faults. First, multiblock consensus principal component analysis (CPCA) is extended to MLPCA to model the large scale continuous annealing process. Secondly, a decentralized fault diagnosis approach is designed based on the proposed MLPCA algorithm. Finally, experiment results on an industrial CAPL are obtained to demonstrate the effectiveness of the proposed method.

[1]  Tianyou Chai,et al.  Fault diagnosis of continuous annealing processes using a reconstruction-based method , 2012 .

[2]  J. Macgregor,et al.  Analysis of multiblock and hierarchical PCA and PLS models , 1998 .

[3]  G. Box.  Some Theorems on Quadratic Forms Applied in the Study of Analysis of Variance Problems, I. Effect of Inequality of Variance in the One-Way Classification , 1954 .

[4]  Peter A Vanrolleghem,et al.  Adaptive Consensus Principal Component Analysis for On-Line Batch Process Monitoring , 2004, Environmental monitoring and assessment.

[5]  Xue Z. Wang,et al.  MULTILEVEL PCA AND INDUCTIVE LEARNING FOR KNOWLEDGE EXTRACTION FROM OPERATIONAL DATA OF BATCH PROCESSES , 2001 .

[6]  B. Caffo,et al.  MULTILEVEL FUNCTIONAL PRINCIPAL COMPONENT ANALYSIS. , 2009, The annals of applied statistics.

[7]  Si-Zhao Joe Qin,et al.  Reconstruction-based contribution for process monitoring , 2009, Autom..

[8]  Udo Schubert,et al.  Unified model-based fault diagnosis for three industrial application studies , 2011 .

[9]  S.J. Qin,et al.  Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis , 2006, IEEE Transactions on Semiconductor Manufacturing.

[10]  Jayson Tessier,et al.  Multiblock Monitoring of Aluminum Reduction Cells Performance , 2011 .

[11]  Theodora Kourti,et al.  Process analysis, monitoring and diagnosis, using multivariate projection methods , 1995 .

[12]  Donghua Zhou,et al.  Generalized Reconstruction-Based Contributions for Output-Relevant Fault Diagnosis With Application to the Tennessee Eastman Process , 2011, IEEE Transactions on Control Systems Technology.

[13]  S. Joe Qin,et al.  Subspace approach to multidimensional fault identification and reconstruction , 1998 .

[14]  Amitabh Barua,et al.  Hierarchical Fault Diagnosis and Health Monitoring in Satellites Formation Flight , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[15]  Chai Tianyou.  Modeling and Simulation for Strip Tension in Continuous Annealing Process , 2007 .

[16]  Yong Chen,et al.  Reliability of Coordinate Sensor Systems Under the Risk of Sensor Precision Degradations , 2010, IEEE Transactions on Automation Science and Engineering.

[17]  Danwei Wang,et al.  Quantitative Hybrid Bond Graph-Based Fault Detection and Isolation , 2010, IEEE Transactions on Automation Science and Engineering.

[18]  Heng Wang,et al.  Fault Detection for a Class of Uncertain State-Feedback Control Systems , 2010, IEEE Transactions on Control Systems Technology.

[19]  S. X. Yang,et al.  An Adaptive Approach Based on KPCA and SVM for Real-Time Fault Diagnosis of HVCBs , 2011, IEEE Transactions on Power Delivery.

[20]  N.A. Ebler,et al.  Tension control: dancer rolls or load cells , 1992, Conference Record on Pulp and Paper Industry Technical Conference.

[21]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[22]  Michael J. Piovoso,et al.  On unifying multiblock analysis with application to decentralized process monitoring , 2001 .

[23]  Marcos E. Orchard,et al.  Local models for soft-sensors in a rougher flotation bank , 2003 .

[24]  S. de Jong,et al.  A framework for sequential multiblock component methods , 2003 .

[25]  Seung-Ki Sul,et al.  A new tension controller for continuous strip processing line , 1998, Conference Record of 1998 IEEE Industry Applications Conference. Thirty-Third IAS Annual Meeting (Cat. No.98CH36242).

[26]  J. Ruiz C.,et al.  Estimating the strip tension in multi-drive systems , 1997, Proceedings of the IECON'97 23rd International Conference on Industrial Electronics, Control, and Instrumentation (Cat. No.97CH36066).

[27]  Richard G. Brereton,et al.  Window consensus PCA for multiblock statistical process control: adaption to small and time‐dependent normal operating condition regions, illustrated by online high performance liquid chromatography of a three‐stage continuous process , 2010 .

[28]  William C. Messner,et al.  Controller development for a prototype high-speed low-tension tape transport , 1998, IEEE Trans. Control. Syst. Technol..

[29]  El Mostafa Qannari,et al.  Shedding new light on Hierarchical Principal Component Analysis , 2010 .

[30]  S. Joe Qin,et al.  A unified geometric approach to process and sensor fault identification and reconstruction : The unidimensional fault case , 1998 .

[31]  Myrtille Vivien,et al.  A new linear method for analyzing four‐way multiblock tables: STATIS‐4 , 2008 .

[32]  Zhiqiang Ge,et al.  Batch process monitoring based on multilevel ICA-PCA , 2008 .

[33]  Leyuan Shi,et al.  IEEE Transactions on Automation Science and Engineering , 2009, IEEE Transactions on Automation Science and Engineering.

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

[35]  S. Joe Qin,et al.  Analysis and generalization of fault diagnosis methods for process monitoring , 2011 .

[36]  Barry Lennox,et al.  Monitoring a complex refining process using multivariate statistics , 2008 .

[37]  G. Rizzoni,et al.  Hierarchical Model-Based Fault Diagnosis for an Electrical Power Generation Storage Automotive System , 2007, 2007 American Control Conference.

[38]  Age K. Smilde,et al.  Generalized contribution plots in multivariate statistical process monitoring , 2000 .

[39]  Ku Chin Lin,et al.  Observer-based tension feedback control with friction and inertia compensation , 2003, IEEE Trans. Control. Syst. Technol..

[40]  Hector Budman,et al.  Fault detection, identification and diagnosis using CUSUM based PCA , 2011 .

[41]  Xiaodong Zhang,et al.  Sensor Bias Fault Detection and Isolation in a Class of Nonlinear Uncertain Systems Using Adaptive Estimation , 2011, IEEE Transactions on Automatic Control.

[42]  Hong Zhou,et al.  Decentralized Fault Diagnosis of Large-Scale Processes Using Multiblock Kernel Partial Least Squares , 2010, IEEE Transactions on Industrial Informatics.

[43]  In-Beum Lee,et al.  Multiblock PLS-based localized process diagnosis , 2005 .

[44]  Yale Zhang,et al.  Online monitoring of steel casting processes using multivariate statistical technologies: From continuous to transitional operations☆ , 2006 .