A fuzzy approach to using expert knowledge for tuning paper machines

Research output: Contribution to journalArticle


  • Jozsef Mezei
  • Matteo Brunelli
  • Christer Carlsson

Research units

  • Lappeenranta University of Technology
  • Arcada University of Applied Sciences
  • Åbo Akademi University


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.


Original languageEnglish
Pages (from-to)605-616
Number of pages12
JournalJournal of the Operational Research Society
Issue number6
Publication statusPublished - Jun 2017
MoE publication typeA1 Journal article-refereed

    Research areas

  • paper machines, fuzzy ontology, multiobjective optimization, goal programming, possibilistic chance programming, soft computing, OPTIMIZATION, INTEGRATION, PREFERENCE, INDUSTRY, SYSTEMS, DESIGN

ID: 13679872