Abstract
ABSTRACT Material flow simulation is a powerful tool to realize efficient operations in complicated production systems such as high-mix and low-volume production. Nevertheless, great effort and expertise are necessary to construct accurate simulation models. We have proposed a semi-automatic modeling approach designated as data-driven and multi-scale modeling. The approach combines various modeling methods to maximize the simulation accuracy. This article introduces the proposed method and presents the experimentally obtained results for simple production systems to examine the characteristics of modeling methods based on queue models or machine learning models. The results of computational experiments indicate that the superiority and inferiority of modeling methods depend on the complexity of the system and the background knowledge about the activity configuration in the system.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have