A demonstration of machine learning for explicit functions for cycle time prediction using MES data

Birkan Can; Cathal Heavey

doi:10.1109/WSC.2016.7822289

A demonstration of machine learning for explicit functions for cycle time prediction using MES data

Birkan Can
, Cathal Heavey

School of Engineering

University of Limerick

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Cycle time prediction represents a challenging problem in complex manufacturing scenarios. This paper demonstrates an approach that uses genetic programming (GP) and effective process time (EPT) to predict cycle time using a discrete event simulation model of a production line, an approach that could be used in complex manufacturing systems, such as a semiconductor fab. These predictive models could be used to support control and planning of manufacturing systems. GP results in a more explicit function for cycle time prediction. The results of the proposed approach show a difference between 1-6% on the demonstrated production line.

Original language	English
Title of host publication	2016 Winter Simulation Conference
Subtitle of host publication	Simulating Complex Service Systems, WSC 2016
Editors	Theresa M. Roeder, Peter I. Frazier, Robert Szechtman, Enlu Zhou
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2500-2511
Number of pages	12
ISBN (Electronic)	9781509044863
DOIs	https://doi.org/10.1109/WSC.2016.7822289
Publication status	Published - 2 Jul 2016
Event	2016 Winter Simulation Conference, WSC 2016 - Arlington, United States Duration: 11 Dec 2016 → 14 Dec 2016

Publication series

Name	Proceedings - Winter Simulation Conference
Volume	0
ISSN (Print)	0891-7736

Conference

Conference	2016 Winter Simulation Conference, WSC 2016
Country/Territory	United States
City	Arlington
Period	11/12/16 → 14/12/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1109/WSC.2016.7822289

Cite this

Can, B., & Heavey, C. (2016). A demonstration of machine learning for explicit functions for cycle time prediction using MES data. In T. M. Roeder, P. I. Frazier, R. Szechtman, & E. Zhou (Eds.), 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016 (pp. 2500-2511). Article 7822289 (Proceedings - Winter Simulation Conference; Vol. 0). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2016.7822289

Can, Birkan ; Heavey, Cathal. / A demonstration of machine learning for explicit functions for cycle time prediction using MES data. 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. editor / Theresa M. Roeder ; Peter I. Frazier ; Robert Szechtman ; Enlu Zhou. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2500-2511 (Proceedings - Winter Simulation Conference).

@inproceedings{e99adb33bab243f28062dd334bb7e9aa,

title = "A demonstration of machine learning for explicit functions for cycle time prediction using MES data",

abstract = "Cycle time prediction represents a challenging problem in complex manufacturing scenarios. This paper demonstrates an approach that uses genetic programming (GP) and effective process time (EPT) to predict cycle time using a discrete event simulation model of a production line, an approach that could be used in complex manufacturing systems, such as a semiconductor fab. These predictive models could be used to support control and planning of manufacturing systems. GP results in a more explicit function for cycle time prediction. The results of the proposed approach show a difference between 1-6\% on the demonstrated production line.",

author = "Birkan Can and Cathal Heavey",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 Winter Simulation Conference, WSC 2016 ; Conference date: 11-12-2016 Through 14-12-2016",

year = "2016",

month = jul,

day = "2",

doi = "10.1109/WSC.2016.7822289",

language = "English",

series = "Proceedings - Winter Simulation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2500--2511",

editor = "Roeder, \{Theresa M.\} and Frazier, \{Peter I.\} and Robert Szechtman and Enlu Zhou",

booktitle = "2016 Winter Simulation Conference",

}

Can, B & Heavey, C 2016, A demonstration of machine learning for explicit functions for cycle time prediction using MES data. in TM Roeder, PI Frazier, R Szechtman & E Zhou (eds), 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016., 7822289, Proceedings - Winter Simulation Conference, vol. 0, Institute of Electrical and Electronics Engineers Inc., pp. 2500-2511, 2016 Winter Simulation Conference, WSC 2016, Arlington, United States, 11/12/16. https://doi.org/10.1109/WSC.2016.7822289

A demonstration of machine learning for explicit functions for cycle time prediction using MES data. / Can, Birkan; Heavey, Cathal.
2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. ed. / Theresa M. Roeder; Peter I. Frazier; Robert Szechtman; Enlu Zhou. Institute of Electrical and Electronics Engineers Inc., 2016. p. 2500-2511 7822289 (Proceedings - Winter Simulation Conference; Vol. 0).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A demonstration of machine learning for explicit functions for cycle time prediction using MES data

AU - Can, Birkan

AU - Heavey, Cathal

PY - 2016/7/2

Y1 - 2016/7/2

N2 - Cycle time prediction represents a challenging problem in complex manufacturing scenarios. This paper demonstrates an approach that uses genetic programming (GP) and effective process time (EPT) to predict cycle time using a discrete event simulation model of a production line, an approach that could be used in complex manufacturing systems, such as a semiconductor fab. These predictive models could be used to support control and planning of manufacturing systems. GP results in a more explicit function for cycle time prediction. The results of the proposed approach show a difference between 1-6% on the demonstrated production line.

AB - Cycle time prediction represents a challenging problem in complex manufacturing scenarios. This paper demonstrates an approach that uses genetic programming (GP) and effective process time (EPT) to predict cycle time using a discrete event simulation model of a production line, an approach that could be used in complex manufacturing systems, such as a semiconductor fab. These predictive models could be used to support control and planning of manufacturing systems. GP results in a more explicit function for cycle time prediction. The results of the proposed approach show a difference between 1-6% on the demonstrated production line.

UR - https://www.scopus.com/pages/publications/85014235437

U2 - 10.1109/WSC.2016.7822289

DO - 10.1109/WSC.2016.7822289

M3 - Conference contribution

AN - SCOPUS:85014235437

T3 - Proceedings - Winter Simulation Conference

SP - 2500

EP - 2511

BT - 2016 Winter Simulation Conference

A2 - Roeder, Theresa M.

A2 - Frazier, Peter I.

A2 - Szechtman, Robert

A2 - Zhou, Enlu

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 Winter Simulation Conference, WSC 2016

Y2 - 11 December 2016 through 14 December 2016

ER -

Can B, Heavey C. A demonstration of machine learning for explicit functions for cycle time prediction using MES data. In Roeder TM, Frazier PI, Szechtman R, Zhou E, editors, 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2500-2511. 7822289. (Proceedings - Winter Simulation Conference). doi: 10.1109/WSC.2016.7822289

A demonstration of machine learning for explicit functions for cycle time prediction using MES data

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this