Databased prediction of order-specific transition times

An increasing product individualization has led to workshop(-like) production in many companies. Mastering the resulting planning complexity has proven to be a challenging task. Today’s production planning and control in many cases does not succeed in providing reliable production plans. One reason...

Full description

Saved in:
Bibliographic Details
Published in:CIRP annals 2019, Vol.68 (1), p.467-470
Main Authors: Schuh, Günther, Prote, Jan-Philipp, Sauermann, Frederick, Franzkoch, Bastian
Format: Article
Language:English
Subjects:
Artificial intelligence
Machine learning
Production planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An increasing product individualization has led to workshop(-like) production in many companies. Mastering the resulting planning complexity has proven to be a challenging task. Today’s production planning and control in many cases does not succeed in providing reliable production plans. One reason is that transition times account for a major part of lead times, that are difficult to predict due to a high number of partly unknown and volatile influencing factors. In this paper, a data mining approach is presented that increases planning quality by a databased prediction of order-specific transition times, and thus supports mastering of planning complexity.
ISSN:0007-8506
DOI:10.1016/j.cirp.2019.03.008