Process incipient fault detection using canonical variate analysis

Process monitoring of incipient faults, as opposed to abrupt faults, in an industrial process is increasingly becoming more important. These are slowly developing faults that may eventually lead to severe abnormal conditions, and ultimately, failure of a critical component. Data-driven multivariate statistical process monitoring (MSPM) methods are extensively studied and widely used for abrupt fault detection. One such method is Canonical Variate Analysis (CVA), which has strength for dynamic process monitoring. This paper now aims to demonstrate the effectiveness of CVA in detecting incipient faults — in particular, catalyst decay and heat transfer fouling occurring in a temperature-controlled CSTR, simulated separately and simultaneously. Performance is evaluated by noting detection delays and investigating the effects of process control. The results show the sensitivity of CVA to incipient faults, providing an early detection even in the case of multiple faults that mask each other.

[1]  Donghua Zhou,et al.  Incipient Sensor Fault Diagnosis Using Moving Window Reconstruction-Based Contribution , 2016 .

[2]  Marios M. Polycarpou,et al.  A robust detection and isolation scheme for abrupt and incipient faults in nonlinear systems , 2002, IEEE Trans. Autom. Control..

[3]  Mehrdad Heydarzadeh,et al.  A Two-Stage Fault Detection and Isolation Platform for Industrial Systems Using Residual Evaluation , 2016, IEEE Transactions on Instrumentation and Measurement.

[4]  Jing Wang,et al.  Incipient Fault Detection Based on Fault Extraction and Residual Evaluation , 2015 .

[5]  Donghua Zhou,et al.  Recursive transformed component statistical analysis for incipient fault detection , 2017, Autom..

[6]  Steven X. Ding,et al.  Improved canonical correlation analysis-based fault detection methods for industrial processes , 2016 .

[7]  Masahiro Abe,et al.  Incipient fault diagnosis of chemical processes via artificial neural networks , 1989 .

[8]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

[9]  Demba Diallo,et al.  Incipient fault detection and diagnosis based on Kullback-Leibler divergence using Principal Component Analysis: Part I , 2014, Signal Process..

[10]  Akshya Swain,et al.  Detection and isolation of incipient sensor faults for a class of uncertain non-linear systems , 2012 .

[11]  Amir Wachs,et al.  Improved PCA methods for process disturbance and failure identification , 1999 .

[12]  Richard D. Braatz,et al.  Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis , 2000 .

[13]  Cristobal Ruiz-Carcel,et al.  Canonical Variate Analysis for Performance Degradation under Faulty Conditions , 2016 .

[14]  Cristobal Ruiz-Carcel,et al.  Statistical process monitoring of a multiphase flow facility , 2015 .

[15]  Richard D. Braatz,et al.  Diagnosis of multiple and unknown faults using the causal map and multivariate statistics , 2015 .

[16]  D. M. Himmelblau,et al.  Incipient fault diagnosis of nonlinear processes with multiple causes of faults , 1984 .

[17]  Zhiqiang Ge,et al.  Local ICA for multivariate statistical fault diagnosis in systems with unknown signal and error distributions , 2012 .

[18]  Claude Delpha,et al.  Incipient fault detection and diagnosis based on Kullback-Leibler divergence using principal component analysis: Part II , 2015, Signal Process..

[19]  Yi Cao,et al.  Application of Canonical Variate Analysis for fault detection and performance control , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

[20]  Fei Liu,et al.  Statistical Modeling of Dynamic Multivariate Process Using Canonical Variate Analysis , 2006, 2006 International Conference on Information and Automation.

[21]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[22]  Wallace E. Larimore,et al.  Canonical variate analysis in identification, filtering, and adaptive control , 1990, 29th IEEE Conference on Decision and Control.

[23]  Yi Cao,et al.  Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations , 2009 .

[24]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[25]  Dale E. Seborg,et al.  Fault Detection Using Canonical Variate Analysis , 2004 .

[26]  Liang Ming,et al.  Abnormal situation management: Challenges and opportunities in the big data era , 2016, Comput. Chem. Eng..

[27]  Donghua Zhou,et al.  Incipient fault detection with smoothing techniques in statistical process monitoring , 2017 .

[28]  Frank L. Lewis,et al.  Intelligent Fault Diagnosis and Prognosis for Engineering Systems , 2006 .