IOMCS for Pulp and Paper Processes

  • Ming Rao
  • Qijun Xia
  • Yiqun Ying
Part of the Advances in Industrial Control book series (AIC)


The previous nine chapters present a number of control algorithms and their applications to unit operation of paper machines. The growing complexity of industrial processes and the need for higher efficiency, great flexibility, better product quality, lower cost and environment protection have changed the face of industrial practice. Mill wide information management, decision-making automation and operation support have become very crucial for the modern pulp and paper company to stay competitive internationally. Artificial intelligence can play an important role in attaining the above goal. Considering that most of the nowadays modern pulp and paper mills have successfully installed distributed computer control systems (DCS) and information management systems, it is of very significant economic benefit to improve the existing systems by adding “intelligence” and enhancing functionality. This chapter presents an intelligent on-line monitoring and control system (IOMCS) for pulp and paper processes. IOMCS is a real-time intelligent system which links with DCS and a mill wide information system. It takes advantage from the DCS value-added data in the information management system. The system fulfills functions such as monitoring the process for abnormal situations; advising evasive and corrective operation actions to operators; pulp quality prediction; and operation optimization. Unlike in the previous chapters, we will not limit our attention to paper machines, but to whole pulp and paper processes. The techniques proposed in this chapter are applicable to paper machines.


Fault Diagnosis Action Variable Pulp Mill Information Management System Paper Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Dvorak D. and Kuipers B. Process Monitoring and Diagnosis. IEEE Expert 1991; 6: 67–74CrossRefGoogle Scholar
  2. Dumont G.A. Control techniques in the pulp and paper industry. In: Control and Dynamic Systems 1990; 37:65–113Google Scholar
  3. Dyne B. and Harvey M. Decision support system for pulp blending strategy. Presented at Pulp and Paper Expert Systems Workshop, Pointe Claire, Quebec, 1992.Google Scholar
  4. Frith M.D. and Henriksson C. Integration of distributed control and mill wide information systems at the Slave Lake Pulp Corporation plant. Presented at CPPA Spring Conference, Jasper, Canada, 1992Google Scholar
  5. Gesser R. Building a Hypertext System. Dr. Dobb’s Journal 1990; 165: 22–33Google Scholar
  6. Harris C.A., Sprentz P., Hall M. and Meech J.A. How expert systems can improve productivity in the mill. Pulp & Paper Canada 1990; 91 (11): 29–34Google Scholar
  7. Henriksson C., Smith W., Danielson K. and Olofsson J. Value-added informationa high payback investiment for the mill. Proc Tappi Process Control Conference, Atlanta, Georgia, USA, 1992, pp 5–19Google Scholar
  8. Hobbs G.C. and Abbot J. Peroxide bleaching reaction under alkaline and acidic conditions. Journal of Wood Chemistry and Technology 1991; 11: 329–347CrossRefGoogle Scholar
  9. Holloway L.E., Paul C.J., Strosnider J.K. and Krogh B.H. Integration of behavioural fault-detection models and an intelligent reactive scheduler. Proc of the 1991 IEEE International Symposium on Intelligent Control, Arlington, Virginia, USA, 1991, pp 134–139Google Scholar
  10. Hoskins J.C., Kaliyar K.M. and Himmelblau D.M. Fault diagnosis in complex chemical plants using artificial neural networks. AIChE J. 1991; 37: 137–146CrossRefGoogle Scholar
  11. Kim H., Shen X. and Rao M., Mcintosh A. and Mahalec V. Refinery product volatility prediction using neural network. Proc 42nd Canadian Chemical Engineering Conference, Toronto, Ontario, Canada, 1992, pp 243–244Google Scholar
  12. Kitzmiller C.T. and Kowalik J.S. Symbolic and numerical computing in knowledgebased systems. In: Kowalik J.S. (editor) Coupling Symbolic and Numerical Computing in Expert Systems, Amsterdam, New York, Oxford, Tokyo, 1985Google Scholar
  13. Kowalski A. Diagnostic expert system for solving pitch problems. Presented at Pulp and Paper Expert Systems Workshop, Pointe Claire, Quebec, 1991Google Scholar
  14. Kramer M. and Palowitch B. A rule-based approach to fault diagnosis using the signed directed graph. AIChE J. 1987; 33: 1067–1078CrossRefGoogle Scholar
  15. Kramer M. A. and Leonard J. A. Diagnosis using backpropagation neural networksanalysis and criticism. Computers Chem. Engng. 1990; 12: 1323–1338Google Scholar
  16. Lapointe J., Marcos B., Veillette M. and Laflamme G. BIOEXPERT-an expert system for wastewater treatment process diagnosis. Computers chem. Engng 1989; 13: 619–630CrossRefGoogle Scholar
  17. Macchietto S., Stuart G., Perris T.A. and Dissinger G.R. Monitoring and online optimization of process using speedup. Computers Chem. Engng. 1989; 13: 571–76CrossRefGoogle Scholar
  18. Matson W. The outlook for the Canadian pulp and paper industry. Pulp and Paper Canada 1989; 90 (9): T297–T303Google Scholar
  19. Murdock J.L. and Hayes-Roth G. Intelligent monitoring and control of semiconductor manufacturing equipment. IEEE Expert 1991; 6 (6): 19–31CrossRefGoogle Scholar
  20. Qian D. An improved method for fault location of chemical plants. Computers Chem. Engng. 1990; 14: 41–48CrossRefGoogle Scholar
  21. Rao M. and Corbin J. Intelligent operation support system for batch chemical pulping process. Engineering applic. of Artificial Intelligence 1993; 6: 357–380CrossRefGoogle Scholar
  22. Rao M. Integrated system for intelligent control, Springer-Verlag, Berlin, 1991Google Scholar
  23. Rao M. and Xia Q. Integrated distributed intelligent system for on-line monitoring and control of pulp processes. Canadian Journal of Artificial Intelligence 1994; Winter Issue:5–10Google Scholar
  24. Shafaghi A., Andom P.K. and Lees F.P. Fault tree synthesis based on control loop structure. Chem. Eng. Res. Des. 1984; 62: 101–110Google Scholar
  25. Stephanoploulos G. Artificial intelligence in process engineering-current state and future trends. Computers Chem. Engng. 1990; 14: 1259–1270CrossRefGoogle Scholar
  26. Soucek B. From modules to application-oriented integrated systems. In: Neural and Intelligent Systems Integration: Fifth and Sixth Generation Integrated Reasoning Information Systems. John Wiley & Sons, Inc., 1991, pp 1–36Google Scholar
  27. Xia Q. and Rao M. Fault tolerant control of paper machine headbox. Journal of Process Control 1992; 3: 171–178CrossRefGoogle Scholar
  28. Xia Q., Farzadeh H., Rao M., Henriksson C., Danielson K. and Olofsson J. Integrated intelligent control system for peroxide bleaching processes. Proc 1993 IEEE Conference on Control Application, Vancouver, Canada, 1993, pp 593–598Google Scholar
  29. Yestresky J. and Ziemacki M. Fuzzy data comparator with neural network postprocessor: A hardware implementation. In: Neural and Intelligent Systems Integration: Fifth and Sixth Generation Integrated Reasoning Information Systems, John Wiley & Sons Inc., 1991, pp 323–332Google Scholar
  30. Yu C. and Lee C. Fault diagnosis based on qualitative/quantitative process knowledge. AIChE J. 1991; 37: 617–628CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1994

Authors and Affiliations

  • Ming Rao
    • 1
  • Qijun Xia
    • 1
  • Yiqun Ying
    • 1
  1. 1.Department of Chemical EngineeringUniversity of AlbertaEdmontonCanada

Personalised recommendations