Generating operating curves in complex systems using machine learning

Birkan Can, Cathal Heavey, Kamil Erkan Kabak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes using data analytic tools to generate operating curves in complex systems. Operating curves are productivity tools that benchmark factory performance based on key metrics, cycle time and throughput. We apply a machine learning approach on the flow time data gathered from a manufacturing system to derive predictive functions for these metrics. To perform this, we investigate incorporation of detailed shop-floor data typically available from manufacturing execution systems. These functions are in explicit mathematical form and have the ability to predict the operating points and operating curves. Simulation of a real system from semiconductor manufacturing is used to demonstrate the proposed approach.

Original languageEnglish
Title of host publicationProceedings of the 2014 Winter Simulation Conference, WSC 2014
EditorsAndreas Tolk, Levent Yilmaz, Saikou Y. Diallo, Ilya O. Ryzhov
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2404-2413
Number of pages10
ISBN (Electronic)9781479974863
DOIs
Publication statusPublished - 23 Jan 2015
Event2014 Winter Simulation Conference, WSC 2014 - Savannah, United States
Duration: 7 Dec 201410 Dec 2014

Publication series

NameProceedings - Winter Simulation Conference
Volume2015-January
ISSN (Print)0891-7736

Conference

Conference2014 Winter Simulation Conference, WSC 2014
Country/TerritoryUnited States
CitySavannah
Period7/12/1410/12/14

Fingerprint

Dive into the research topics of 'Generating operating curves in complex systems using machine learning'. Together they form a unique fingerprint.

Cite this