Fault detection and diagnosis in a cement rotary kiln using PCA with EWMA-based adaptive threshold monitoring scheme

Abstract This paper presents main results of fault detection and diagnosis in a cement manufacturing plant using a new monitoring scheme. The scheme is based on multivariate statistical analysis and an adaptive threshold strategy. The process is statistically modeled using Principle Component Analysis (PCA). Instead of the conventional fixed control limits, adaptive thresholds are used to evaluate the common T 2 and Q statistics as faults indicators. The adaptive thresholds are computed and updated using a modified Exponentially Weighted Moving Average (EWMA) chart. These techniques are merged together to construct a novel monitoring scheme whose effectiveness is demonstrated using involuntary real fault of a cement plant process and some simulated faulty cases.

[1]  J. Pohlmann,et al.  Parallel Analysis: a method for determining significant principal components , 1995 .

[2]  L. Luo,et al.  Quality prediction and quality-relevant monitoring with multilinear PLS for batch processes , 2016 .

[3]  Ali Ajami,et al.  Data driven approach for fault detection and diagnosis of turbine in thermal power plant using Independent Component Analysis (ICA) , 2012 .

[4]  Giorgio Rizzoni,et al.  Model-based diagnosis and fault tolerant control for ensuring torque functional safety of pedal-by-wire systems , 2017 .

[5]  Hazem Nounou,et al.  PLS-based EWMA fault detection strategy for process monitoring , 2015 .

[6]  Bo Zhou,et al.  Process monitoring of iron-making process in a blast furnace with PCA-based methods , 2016 .

[7]  Hua Chen,et al.  Recognition of the Temperature Condition of a Rotary Kiln Using Dynamic Features of a Series of Blurry Flame Images , 2016, IEEE Transactions on Industrial Informatics.

[8]  Ying Sun,et al.  Amalgamation of anomaly-detection indices for enhanced process monitoring , 2016 .

[9]  Jie Zhang,et al.  Fault detection in dynamic processes using a simplified monitoring-specific CVA state space modelling approach , 2012, Comput. Chem. Eng..

[10]  Timothy I. Salsbury,et al.  A method for setpoint alarming using a normalized index , 2017 .

[11]  J. Horn.  A rationale and test for the number of factors in factor analysis , 1965, Psychometrika.

[12]  Wen Tan,et al.  Design of univariate alarm systems via rank order filters , 2017 .

[13]  Babak Nadjar Araabi,et al.  Abnormal condition detection in a cement rotary kiln with system identification methods , 2009 .

[14]  Leo H. Chiang,et al.  Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis , 2000 .

[15]  Jicong Fan,et al.  Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA , 2014 .

[16]  Cristina Verde,et al.  Comments on the applicability of “An improved weighted recursive PCA algorithm for adaptive fault detection” , 2017 .

[17]  Chi-Hyuck Jun,et al.  A new multivariate EWMA control chart via multiple testing , 2015 .

[18]  Ivan Prebil,et al.  EEMD-based multiscale ICA method for slewing bearing fault detection and diagnosis , 2016 .

[19]  Navid Sahebjamnia,et al.  IMAQCS: Design and implementation of an intelligent multi-agent system for monitoring and controlling quality of cement production processes , 2013, Comput. Ind..

[20]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[21]  Hare Krishna Mohanta,et al.  Online monitoring of cement clinker quality using multivariate statistics and Takagi-Sugeno fuzzy-inference technique , 2016 .

[22]  Chudong Tong,et al.  Ensemble modified independent component analysis for enhanced non-Gaussian process monitoring , 2017 .

[23]  Alessandro Beghi,et al.  Data-driven Fault Detection and Diagnosis for HVAC water chillers , 2016 .

[24]  Jan Poland,et al.  Model predictive control of a rotary cement kiln , 2011 .

[25]  Jicong Fan,et al.  Online Monitoring of Multivariate Processes Using Higher-Order Cumulants Analysis , 2014 .

[26]  Biao Huang,et al.  Dynamic higher-order cumulants analysis for state monitoring based on a novel lag selection , 2016, Inf. Sci..

[27]  Abdelmalek Kouadri,et al.  An adaptive threshold estimation scheme for abrupt changes detection algorithm in a cement rotary kiln , 2012, J. Comput. Appl. Math..

[28]  Charles W. Champ,et al.  A multivariate exponentially weighted moving average control chart , 1992 .

[29]  S. W. Roberts.  Control chart tests based on geometric moving averages , 2000 .

[30]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[31]  L. Guttman.  Some necessary conditions for common-factor analysis , 1954 .

[32]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[33]  Xie Qing-song,et al.  A lime shaft kiln diagnostic expert system based on holographic monitoring and real-time simulation , 2011, Expert Syst. Appl..

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

[35]  Pierluigi Pisu,et al.  Model-based real-time thermal fault diagnosis of Lithium-ion batteries , 2016 .

[36]  Richard D. Braatz,et al.  A combined canonical variate analysis and Fisher discriminant analysis (CVA-FDA) approach for fault diagnosis , 2015, Comput. Chem. Eng..

[37]  Abdolreza Ohadi,et al.  Comparison of FDA-based and PCA-based features in fault diagnosis of automobile gearboxes , 2013, Neurocomputing.

[38]  Giancarlo Diana,et al.  Cross-validation methods in principal component analysis: A comparison , 2002 .

[39]  Youming Chen,et al.  An enhanced chiller FDD strategy based on the combination of the LSSVR-DE model and EWMA control charts , 2016 .

[40]  Masoud Sadeghian,et al.  Identification, prediction and detection of the process fault in a cement rotary kiln by locally linear neuro-fuzzy technique , 2011 .

[41]  José Luis Godoy,et al.  A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space , 2013 .

[42]  J. A. Conesa,et al.  Emissions of PCDD/Fs, PBDD/Fs, dioxin like-PCBs and PAHs from a cement plant using a long-term monitoring system. , 2016, The Science of the total environment.

[43]  Girijesh Prasad,et al.  EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments , 2015, Pattern Recognit..

[44]  Marco E. Sanjuan,et al.  An improved weighted recursive PCA algorithm for adaptive fault detection , 2016 .