Process monitoring of iron-making process in a blast furnace with PCA-based methods

Abstract Incidents happening in the blast furnace will strongly affect the stability and smoothness of the iron-making process. Thus far, diagnosis of abnormalities in furnaces still mainly relies on the personal experiences of individual workers in many iron works. In this paper, principal component analysis (PCA)-based algorithms are developed to monitor the iron-making process and achieve early abnormality detection. Because the process exhibits a non-normal distribution and a time-varying nature in the measurement data, a static convex hull-based PCA algorithm (SCHPCA) which replaces the traditional T2-based abnormality detection logic with the convex hull-based abnormality detection logic, and its moving window version, called the moving window convex hull-based PCA algorithm (MWCHPCA) are proposed, respectively. These two algorithms are tested on the real process data to verify their effectiveness in the early abnormality detection of iron-making process.

[1]  Yunlu Li,et al.  Optional SVM for Fault Diagnosis of Blast Furnace with Imbalanced Data , 2011 .

[2]  Jie Zhang,et al.  Process performance monitoring using multivariate statistical process control , 1996 .

[3]  Si-Zhao Joe Qin,et al.  Monitoring Non-normal Data with Principal Component Analysis and Adaptive Density Estimation , 2007, 2007 46th IEEE Conference on Decision and Control.

[4]  Julian Szekely,et al.  Blast furnace technology, science and practice : proceedings , 1972 .

[5]  Asdrúbal López Chau,et al.  Structural Health Monitoring of Tall Buildings with Numerical Integrator and Convex-Concave Hull Classification , 2012 .

[6]  Zhiqiu Hu,et al.  A New Distribution-Free Approach to Constructing the Confidence Region for Multiple Parameters , 2013, PloS one.

[7]  Markus A. Reuter,et al.  Monitoring of metallurgical reactors by the use of topographic mapping of process data , 1999 .

[8]  Erik Vanhatalo,et al.  Multivariate process monitoring of an experimental blast furnace , 2010, Qual. Reliab. Eng. Int..

[9]  Gilbert Saporta,et al.  Non parametric on-line control of batch processes based on STATIS and clustering , 2013 .

[10]  Satoshi Watanabe,et al.  Expert system for blast furnace operation at Kimitsu works. , 1990 .

[11]  Abdul Rahman Mohamed,et al.  Neural networks for the identification and control of blast furnace hot metal quality , 2000 .

[12]  Alkan Alkaya,et al.  Variance sensitive adaptive threshold-based PCA method for fault detection with experimental application. , 2011, ISA transactions.

[13]  Anil K. Bera,et al.  A test for normality of observations and regression residuals , 1987 .

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

[15]  N. Wang,et al.  Phosphorous Enrichment in Molten Adjusted Converter Slag: Part I Effect of Adjusting Technological Conditions , 2011 .

[16]  Hui Zhao,et al.  Judging the States of Blast Furnace by ART2 Neural Network , 2009, ISNN.

[17]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[18]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[19]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[20]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[21]  Masami Konishi,et al.  An AI Tool and Its Applications to Diagnosis Problems , 1990 .

[22]  P. Oh,et al.  A n-dimensional convex hull approach for fault detection and mitigation for high degree of freedom robots humanoid robots , 2012, 2012 12th International Conference on Control, Automation and Systems.

[23]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[24]  Peng Sun,et al.  Computation of Minimum Volume Covering Ellipsoids , 2002, Oper. Res..

[25]  Limei Liu,et al.  Multi-Class Classification Methods of Cost-Conscious LS-SVM for Fault Diagnosis of Blast Furnace , 2011 .

[26]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[27]  H. Lilliefors.  On the Kolmogorov-Smirnov Test for the Exponential Distribution with Mean Unknown , 1969 .

[28]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[29]  B. Bakshi.  Multiscale PCA with application to multivariate statistical process monitoring , 1998 .

[30]  Michael J. Todd,et al.  On Khachiyan's algorithm for the computation of minimum-volume enclosing ellipsoids , 2007, Discret. Appl. Math..

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

[32]  Hao Ye,et al.  Fault Diagnosis for Blast Furnace Ironmaking Process Based on Two-stage Principal Component Analysis , 2014 .

[33]  J. Dorn,et al.  Expert Systems in the Steel Industry , 1996, IEEE Expert.

[34]  Wu Juan,et al.  Genetic Algorithm for Multiuser Discrete Network Design Problem under Demand Uncertainty , 2012 .

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

[36]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[37]  M. Luo.  Multivariate fault detection with convex hull , 2004, The 23rd Digital Avionics Systems Conference (IEEE Cat. No.04CH37576).

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

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

[40]  Mark de Berg,et al.  Computational geometry: algorithms and applications , 1997 .

[41]  J. G. Peacey,et al.  The Iron Blast Furnace: Theory and Practice , 1979 .

[42]  Spiros Mancoridis,et al.  On the use of computational geometry to detect software faults at runtime , 2010, ICAC '10.

[43]  David J. Sandoz,et al.  The application of principal component analysis and kernel density estimation to enhance process monitoring , 2000 .

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

[45]  Kanji Takeda,et al.  Ironmaking Technology for the Last 100 Years: Deployment to Advanced Technologies from Introduction of Technological Know-how, and Evolution to Next-generation Process , 2015 .

[46]  Pan Lian,et al.  Fault Diagnosis of the Blast Furnace Based on the Bayesian Network Model , 2010, 2010 International Conference on Electrical and Control Engineering.

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

[48]  Sirkka-Liisa Jämsä-Jounela.  Current status and future trends in the automation of mineral and metal processing , 2001 .

[49]  Joaquím Meléndez,et al.  Predicting aerodynamic instabilities in a blast furnace , 2006, Eng. Appl. Artif. Intell..

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

[51]  Junghui Chen,et al.  Mixture Principal Component Analysis Models for Process Monitoring , 1999 .

[52]  Jin Hyun Park,et al.  Process monitoring using a Gaussian mixture model via principal component analysis and discriminant analysis , 2004, Comput. Chem. Eng..