A fuzzy approach to using expert knowledge for tuning paper machines

Abstract

Paper machines are very complex production systems, but their scope is simple: they consume materials and resources, called factors, to produce paper, which in turn can be described by its characteristics. In this paper, a decision support system is developed in cooperation with an industrial partner to help them with operational decision making when tuning a paper machine. The decision support system was developed in two phases. Firstly, the knowledge of experts is collected and stored in the form of a fuzzy ontology. Secondly, this knowledge is made usable so that a user of the decision support system can specify what characteristics of the produced paper to increase or to decrease and be returned with a recommendation on what factors to change. In this paper, we will work out the optimization problems on which the system is based. Additionally to a basic goal programming model, two extensions are explored, accounting for uncertainty and non-linearity, respectively.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3

Notes

  1. 1.

    http://sal.aalto.fi/publications/pdf-files/models_gp.zip.

  2. 2.

    https://jmezei.shinyapps.io/paper_app/.

References

  1. Åstrom KJ (1967). Computer Control of a Paper Machine — an Application of Linear Stochastic Control Theory. IBM Journal of Research and Development 11(4):389–405.

    Article  Google Scholar 

  2. Bobillo F (2008). Managing Vagueness in Ontologies. PhD Dissertation, University of Granada, Spain.

  3. Brunelli M and Mezei J (2013). How different are ranking methods for fuzzy numbers?. International Journal of Approximate Reasoning 54(5):627–639.

    Article  Google Scholar 

  4. Carlsson C, Brunelli M and Mezei J (2012). Decision making with a fuzzy ontology. Soft Computing 16(7):1143–1152.

    Article  Google Scholar 

  5. Carlsson C, Brunelli M and Mezei J (2013a). Fuzzy ontology used for knowledge mobilisation. International Journal of Intelligent Systems 28(1):52–71.

    Article  Google Scholar 

  6. Carlsson C, Brunelli M and Mezei J (2013b). A soft computing approach to mastering paper machines. In: Proceedings of the 46th Hawaii International Conference on System Sciences (pp. 1394–1401). IEEE.

  7. Charnes A, Cooper WW and Ferguson R (1955). Optimal estimation of executive compensation by linear programming. Management Science 1(2):138–151.

    Article  Google Scholar 

  8. Charnes A, Cooper WW and Ferguson R (1959). Chance-constrained programming. Management Science 6(1):73–79.

    Article  Google Scholar 

  9. Claassen GDH (2014). Mixed Integer (0–1) Fractional Programming for Decision Support in Paper Production Industry. Omega 43:21–29.

    Article  Google Scholar 

  10. D’Amours S, Rönnqvist M, and Weintraub A (2008). Using operational research for supply chain planning in the forest products industry. INFOR: Information Systems and Operational Research 46(4):265–281.

  11. Dubois D and Prade H (2008). An introduction to bipolar representations of information and preference. International Journal of Intelligent Systems 23(8):866–877.

    Article  Google Scholar 

  12. Gruber T (1993). A translation approach to portable ontology specification. Knowledge Acquisition 5(2):199–220.

    Article  Google Scholar 

  13. Hämäläinen JP, Miettinen K, Tarvainen P and Toivanen J (2003). Interactive solution approach to a multiobjective optimization problem in a paper machine headbox design. Journal of Optimization Theory and Applications 116(2):265–281.

    Article  Google Scholar 

  14. Herrera-Viedma E, Herrera F, Chiclana F and Luque M (2004). Some issues on consistency of fuzzy preference relations. European Journal of Operational Research 154(1):98–109.

    Article  Google Scholar 

  15. Hirvonen J, Tommila T, Pakonen A, Carlsson C, Fedrizzi M and Fullér R (2010). Fuzzy Keyword Ontology for Annotating and Searching Event Reports. In: Proceedings of International Conference on Knowledge Engineering and Ontology Development (KEOD 2010). Valencia, Spain.

  16. Ignizio JP (1978). A review of goal programming: A tool for multiobjective analysis. Journal of the Operational Research Society 29(11):1109–1119.

    Article  Google Scholar 

  17. Juuso EK (2004). Integration of intelligent systems in development of smart adaptive systems. International Journal of Approximate Reasoning 35(3):307–337.

    Article  Google Scholar 

  18. Liu B and Iwamura K (1998). Chance constrained programming with fuzzy parameters. Fuzzy Sets and Systems 94(2):227–237.

    Article  Google Scholar 

  19. Narasimhan R (1980). Goal programming in a fuzzy environment. Decision Sciences 11(2):325–336.

    Article  Google Scholar 

  20. Ni XF, Shen Y and Hu HZ (1988). Expert control for a papermaking process. Engineering Applications of Artificial Intelligence 1(2):119–125.

    Article  Google Scholar 

  21. O’Leary D (1991). Design, development and validation of expert systems: A survey of developers. In: Ayel M and Laurent JP (eds). Validation, Verification and Test of Knowledge-based Systems (pp. 3–19). Wiley: New York

  22. Parra MA, Terol AB and Urian MVR (2001). A fuzzy goal programming approach to portfolio selection. European Journal of Operational Research 133(2):287–297.

    Article  Google Scholar 

  23. Parry D (2006). Fuzzy ontologies for information retrieval on the WWW. In: Sanchez E (ed). Fuzzy Logic and the semantic Web, Capturing Intelligence (Vol. 1, pp. 21–48). Elsevier: New York.

  24. Sanchez E (ed.) (2006). Fuzzy Logic and the Semantic Web, Capturing Intelligence (Vol. 1). Elsevier: New York.

  25. Statistics Finland (2013). Finland in Figures - National Accounts. http://www.stat.fi/tup/suoluk/suoluk_kansantalous_en.html, accessed 11 May 2015.

  26. Straccia U (2013). Foundations of Fuzzy Logic and Semantic Web Languages. CRC Press: Boca Raton.

    Google Scholar 

  27. Strömman M, Seilonen I and Koskinen, K (2014). Collaborative Optimization Based Design Process for Process Engineering. In: Simulation and Modeling Methodologies, Technologies and Applications (Advances in Intelligent Systems and Computing) (Vol. 256, pp. 291–303). Springer International Publishing.

  28. Strömman M, Seilonen I, Peltola J and Koskinen K (2013). Integration of Optimization to the Design of Pulp and Paper Production Processes. In: Simulation and Modeling Methodologies, Technologies and Applications (Advances in Intelligent Systems and Computing) (Vol. 197, pp. 239–254). Springer International Publishing.

  29. Tommila T, Hirvonen J and Pakonen A (2010). Fuzzy Ontologies for Retrieval of Industrial Knowledge – A Case Study. VTT Working Papers 153, Helsinki.

  30. Wilkinson L and Friendly M (2009). The history of the cluster heat map. The American Statistician 63(2):179–184.

    Article  Google Scholar 

  31. Wu LC and Tsai IC (2013). Three fuzzy goal programming models for index portfolios. Journal of the Operational Research Society 65(8):1155–1169.

    Article  Google Scholar 

  32. Yousefi M, Gopaluni RB, Loewen PD, Forbes MG, Dumont GA and Backstrom J (2015). Impact of model plant mismatch on performance of control systems: An application to paper machine control. Control Engineering Practice 43:59–68.

    Article  Google Scholar 

  33. Zeleny M (1982). Multi Criteria Decision Making. McGraw Hill: New York.

    Google Scholar 

  34. Zadeh LA (1978). Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets and Systems 1(1):3–28.

    Article  Google Scholar 

  35. Zadeh LA (1994). Fuzzy logic, neural networks, and soft computing. Communications of the ACM 37(3):77–85.

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to József Mezei.

Additional information

A preliminary version of this paper was presented at the 46th Hawaii International Conference on Systems Sciences: Carlsson C., Brunelli M. and Mezei J. (2013), A soft computing approach to mastering paper machines, HICSS 2013, pp. 1394–1401.

Appendix: List of factors and characteristics

Appendix: List of factors and characteristics

The following are the lists of factors and characteristics used in Figure 1:

  • Factors: Deinked pulp (DIP), Thermomechanical pulp (TMP), Pressurized groundwood pulp (PGW), Clay (kaolin), Calcium carbonate, CaCO3, Talc, Refining, DIP refining, Absorbency, Flow rate, Water in blade section, Retention, Loading of nip, Steam amount, Press draw, Initial dryness, Initial drying rate, Hood covers, Soft nips, Stack nip loadings, Steam amount in calendering, Temperature in calendering, Reeling load, Winding

  • Characteristics: Runnability, Energy, Tensile, Permeability, Scott bond, Formation, Bulk, Smoothness, Brightness, Opacity, Density, Gloss, Absorption, Two sided, Dimensional stability, Friction, Linting

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mezei, J., Brunelli, M. & Carlsson, C. A fuzzy approach to using expert knowledge for tuning paper machines. J Oper Res Soc 68, 605–616 (2017). https://doi.org/10.1057/s41274-016-0105-3

Download citation

Keywords

  • paper machines
  • fuzzy ontology
  • multiobjective optimization
  • goal programming
  • possibilistic chance programming
  • soft computing