Satisfying various requirements in different levels and stages of machining using one general ANN-based process model

L. Monostori, Zs J. Viharos, S. Markos

Research output: Contribution to journalConference article

34 Citations (Scopus)


Reliable process models are extremely important in different fields of computer integrated manufacturing. They are required, e.g., for selecting optimal parameters during process planning, for designing and implementing adaptive control systems or model based monitoring algorithms. Artificial neural networks (ANNs) can be used as process models because they can handle strong non-linearities, a large number of parameters, missing information and can be used also when no exact knowledge is available about the relationships among the various parameters of manufacturing. The input-output configuration of the used ANN strongly influences the accuracy of the developed model especially if dependencies between parameters are non-invertable. At various stages of production (e.g., in planning, optimisation or control) different tasks arise, consequently, the estimation capabilities of the related applied models are different even if the same set of parameters is used. One of the main goals of the research to be reported here was to find a general model for a set of assignments, which can satisfy accuracy requirements. Research was also focused on how to apply the general model for various tasks.

Original languageEnglish
Pages (from-to)228-235
Number of pages8
JournalJournal of Materials Processing Technology
Issue number1-3
Publication statusPublished - Nov 22 2000
Event15th International Conference on Computer-Aided Production Engineering (CAPE'99) - Durham, UK
Duration: Apr 19 1999Apr 21 1999

ASJC Scopus subject areas

  • Ceramics and Composites
  • Computer Science Applications
  • Metals and Alloys
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Satisfying various requirements in different levels and stages of machining using one general ANN-based process model'. Together they form a unique fingerprint.

  • Cite this