Login / Signup

Personalization of the MES System to the Needs of Highly Variable Production.

Bożena ZwolińskaAgnieszka Anna TubisNorbert Chamier-GliszczyńskiMariusz Kostrzewski
Published in: Sensors (Basel, Switzerland) (2020)
The new generation Manufacturing Executions System (MES) is considered as one of the most important solutions supporting the idea of Industry 4.0. This is confirmed by research conducted among companies interested in the implementation of the Industry 4.0 concept, as well as the publications of researchers who study this issue. However, if MES software is a link that connects the world of machines and business systems, it must take into account the specifics of the supported production systems. This is especially true in case of production systems with a high level of automation, which are characterised by flexibility and agility at the operational level. Therefore, personalization of the MES software is proposed for this class of production systems. The aim of the article is to present the MES system personalization method for a selected production system. The proposed approach uses the rules of Bayesian inference and the area of customisation is the technological structure of production, taking into account the required flexibility of the processes. As part of the developed approach, the variability index was proposed as a parameter evaluating the effectiveness of the production system. Then, the results of evaluation of the current system effectiveness by use of this index are presented. The authors also present the assumptions for the developed MES personalization algorithm. The algorithm uses the rules of Bayesian inference, which enable multiple adjustments of the model to the existing environmental conditions without the need to formulate a new description of reality. The application of the presented solution in a real facility allowed for determining production areas which are the determinants of system instability. The implementation of the developed algorithm enabled control of the generated variability in real time. The proposed approach to personalization of MES software for a selected class of production systems is the main novelty of the presented research and contributes to the development of the described area of research.
Keyphrases
  • healthcare
  • machine learning
  • primary care
  • randomized controlled trial
  • systematic review
  • deep learning