Multivariate Analysis and Monitoring of the Performance of Aluminum Reduction Cells

A multiblock partial least squares (PLS) modeling approach is proposed in this Article for multivariate analysis and monitoring of aluminum reduction smelters and other electrochemical processes. These industries commonly operate from hundreds to a thousand of metallurgical reactors in parallel, which makes is difficult to build and maintain separate models for each unit. To cope with this problem, the proposed approach is based on the assumption that reactors sharing the same design (i.e., technology) and fed with the same lots of raw materials should also share a similar latent variable space. This allows reducing the number of latent variable models to build for process monitoring. The approach is illustrated on the basis of data collected from 31 reactors used for aluminum reduction. It was shown that well-defined regions in the raw material property and process operation spaces were associated with higher smelter performance. These could be used to establish joint multivariate specification regions for raw materials as well as for plant-wide process monitoring.

[1]  John F. MacGregor,et al.  Multi-block PLS modeling for L-shape data structures with applications to mixture modeling , 2007 .

[2]  C. Jun,et al.  Performance of some variable selection methods when multicollinearity is present , 2005 .

[3]  Theodora Kourti,et al.  Multivariate SPC for startups and grade transitions , 2002 .

[4]  J. Westerhuis,et al.  Multivariate modelling of the pharmaceutical two‐step process of wet granulation and tableting with multiblock partial least squares , 1997 .

[5]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[6]  Jayson Tessier,et al.  Increasing Potlife of Hall–Héroult Reduction Cells Through Multivariate On-Line Monitoring of Preheating, Start-Up, and Early Operation , 2010 .

[7]  Ketil Svinning,et al.  Modelling of multi‐block data , 2006 .

[8]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[9]  Salvador García Muñoz,et al.  Data-based latent variable methods for process analysis, monitoring and control , 2005, Comput. Chem. Eng..

[10]  Theodora Kourti,et al.  Product transfer between sites using Joint-Y PLS , 2005 .

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

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

[13]  Theodora Kourti,et al.  Application of latent variable methods to process control and multivariate statistical process control in industry , 2005 .

[14]  Theodora Kourti,et al.  Process analysis and abnormal situation detection: from theory to practice , 2002 .

[15]  Bhupinder S. Dayal,et al.  Improved PLS algorithms , 1997 .

[16]  E. Skybakmoen,et al.  Influence of electrolyte impurities on current efficiency in aluminium electrolysis cells , 1998 .

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

[18]  S. Wold.  Cross-Validatory Estimation of the Number of Components in Factor and Principal Components Models , 1978 .

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

[20]  S. Wold,et al.  The kernel algorithm for PLS , 1993 .

[21]  Theodora Kourti,et al.  Comparing alternative approaches for multivariate statistical analysis of batch process data , 1999 .

[22]  Jayson Tessier.  Multivariate statistical analysis of Hall-Héroult reduction cells : investigation and monitoring of factors affecting performance , 2010 .

[23]  E. Dewing.  Loss of current efficiency in aluminum electrolysis cells , 1991 .

[24]  Michael S. Dudzic,et al.  An industrial perspective on implementing on-line applications of multivariate statistics , 2004 .

[25]  J. Edward Jackson,et al.  A User's Guide to Principal Components: Jackson/User's Guide to Principal Components , 2004 .

[26]  A. J. Morris,et al.  Confidence limits for contribution plots , 2000 .

[27]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[28]  A. Höskuldsson.  PLS regression methods , 1988 .

[29]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[30]  J. Metson,et al.  The nature and impacts of fines in smelter-grade alumina , 2009 .