Hybrid modeling of paper machine grade changes

It would be possible to save millions of euros per paper machine production line if grade changes could be completed in even half of the time needed for typical grade change methods. Despite the fact that very sophisticated grade change automation is currently available, major grade changes have to be executed manually, If major grade changes could be made as easily as small ones, the production program could be made a lot more flexible. Production cycles could be shortened and as a result the need for large warehouses would decrease. One of the building blocks in successful grade change automation is a mathematical model that describes the dependence between the manipulated and the controlled variables. A hybrid modeling method is proposed as a solution to this modeling problem. It is defined here as a combination of empirical and simple first principles. The method is applied to the modeling of paper web moisture. The results are compared with actual process measurements for grade changes.

[1]  M. Lampinen,et al.  Mathematical modeling of web drying , 1993 .

[2]  M. Harrmann,et al.  CONVECTIVE DRYING OF PAPER CALCULATED WITH A NEW MODEL OF THE PAPER STRUCTURE , 1990 .

[3]  Jukka Ranta,et al.  Information technology and structural change in the paper and pulp industry: some technological, organizational and managerial implications , 1992 .

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

[5]  Atanu Banerjee,et al.  Model Predictive Control of Plant Transitions using a New Identification Technique for Interpolating Nonlinear Models , 1997 .

[6]  Heikki N. Koivo,et al.  Dynamic modelling of paper machine from grade change data , 1998 .

[7]  M. Soininen.  Modeling of Web Drying , 1995 .

[8]  C. H. Oh,et al.  Some comments on , 1998 .

[9]  M. Kramer,et al.  Embedding Theoretical Models in Neural Networks , 1992, American Control Conference.

[10]  M. Elmusrati,et al.  Performance analysis of DS-CDMA mobile communication systems with MIMO antenna system and power control , 2002, IEEE Seventh International Symposium on Spread Spectrum Techniques and Applications,.

[11]  Robert A. Lordo,et al.  Learning from Data: Concepts, Theory, and Methods , 2001, Technometrics.

[12]  John F. MacGregor.  STATISTICAL PROCESS CONTROL OF MULTIVARIATE PROCESSES , 1994 .

[13]  J. Lehtinen.  The heat pipe process in intraweb heat transfer in hot-surface paper drying , 1992 .

[14]  Lyle H. Ungar,et al.  Process Modeling using Structured Neural Networks , 1992, 1992 American Control Conference.

[15]  K. Iida,et al.  Dynamic simulation for efficient paper machine grade change , 1988 .

[16]  Heikki N. Koivo,et al.  Application of Neural Networks in the Detection of Breaks in a Paper Machine , 1992 .

[17]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[18]  Teuvo Suntio,et al.  Implementation of optimal output characteristic for a telecom power supply: Fuzzy-logic approach , 2002 .

[19]  Kauko Leiviskä.  Industrial Applications of Soft Computing , 2001 .

[20]  Colin L. Mallows,et al.  Some Comments on Cp , 2000, Technometrics.

[21]  C. J. Nederveen,et al.  Present theories on multi-cylinder paper drying , 1991 .

[22]  T. Pekkarinen,et al.  New approach to wet end management , 1999 .

[23]  Vladimir Cherkassky,et al.  Learning from Data: Concepts, Theory, and Methods , 1998 .

[24]  Jean-Peter Ylén,et al.  Measuring, modelling and controlling the pH value and the dynamic chemical state , 2001 .

[25]  Gary A. Smook,et al.  Handbook for Pulp and Paper Technologists , 1982 .

[26]  J. A. Wilson,et al.  A generalised approach to process state estimation using hybrid artificial neural network/mechanistic models , 1997 .

[27]  Masashi Sugiyama,et al.  Subspace Information Criterion for Model Selection , 2001, Neural Computation.

[28]  P. O. Meinander,et al.  Compact airless backwater circulation with centrifugal deaeration , 1999 .

[29]  Takashi Yoneyama,et al.  GRADE TRANSITION CONTROL FOR AN IMPACT COPOLYMERIZATION REACTOR , 1994 .

[30]  Kenji Takao,et al.  The Development of New Automatic Grade Change Control System of Paper Machine , 1998 .

[31]  Karl-Erik Årzén,et al.  A Frame Work for Process State Transitions: Grade Changes , 2002 .

[32]  Sirish L. Shah,et al.  Modeling and control of multivariable processes: Dynamic PLS approach , 1997 .

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

[34]  Alf Isaksson,et al.  Preface to the special section on benchmarking for paper machine MD-control , 1995 .

[35]  Jukka Lehtinen,et al.  Helsinki Symposium on Alternate Methods of Pulp and Paper Drying , 1991 .

[36]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[37]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

[38]  Lennart Ljung,et al.  Tools for Semi-Physical Modeling , 1994 .

[39]  Andreas Hans Kemna,et al.  Identification of Combined Physical and Empirical Models Using Nonlinear a Priori Knowledge , 1994 .

[40]  K. A. Kosanovich,et al.  Transition control for time-delayed systems , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[41]  H. Bozdogan,et al.  Akaike's Information Criterion and Recent Developments in Information Complexity. , 2000, Journal of mathematical psychology.

[42]  Yaman Arkun,et al.  Model predictive control of plant transitions using a new identification technique for interpolating nonlinear models , 1998 .

[43]  Heikki Hyötyniemi,et al.  PROCESS PERFORMANCE OPTIMIZATION USING ITERATIVE REGRESSION TUNING , 2005 .

[44]  Antero Arkkio,et al.  Comparison of reconstruction schemes of multiple SVM s applied to fault classification of a cage induction motor , 2002 .

[45]  Heikki N. Koivo,et al.  Estimation of Target Values for Grade Changes in Paper Machine , 2001 .

[46]  PeMi Heikkila.  A Study on the Drying Process of Pigment Coated Paper Webs , 1996 .

[47]  Tor Arne Johansen,et al.  Operating regime based process modeling and identification , 1997 .

[48]  Kai Zenger,et al.  Modelling, analysis and controller design of time-variable flow processes , 2003 .

[49]  Idris A. Gadoura,et al.  Design of robust controllers for telecom power supplies , 2002 .

[50]  Jari Lappalainen.  Paperin- ja kartonginvalmistusprosessien mallinnus ja dynaaminen reaaliaikainen simulointi: Lisensiaatintyö , 2004 .