A distributed learning method for due date assignment in flexible job shops

Wei Weng, Gang Rong, Shigeru Fujimura

Research output: Contribution to journalArticle

Abstract

This study intends to help manufacturers that use flexible job shops improve performance of due date assignment, that is, setting delivery times to jobs that arrive dynamically. High performing due date assignment enables achieving on-time delivery and quick response of delivery time to customer orders. Traditional methods for due date assignment are predefined equations that estimate the duration of making a product in the production system. Such equations are sufficient for relatively simple systems such as single machine shops, but are not very high in accuracy for complex systems such as flexible job shops. To improve due date assignment for such systems, we propose a more flexible method that uses distributed learning to learn the remaining time of a job inside the system. We let each workstation in the production shop be a distributed unit that updates its local queuing time and interacts with other units to provide the total remaining time of a job. We carry out extensive computational experiments to evaluate performance of the proposed method, and the results show that it outperforms two advanced equational methods in terms of both accuracy of estimation and stability in performance.

Original languageEnglish
Pages (from-to)791-798
Number of pages8
JournalCEUR Workshop Proceedings
Volume1623
Publication statusPublished - 2016

Fingerprint

Machine shops
Large scale systems
Experiments

Keywords

  • Artificial intelligence in production
  • Distributed system
  • Due date assignment

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

A distributed learning method for due date assignment in flexible job shops. / Weng, Wei; Rong, Gang; Fujimura, Shigeru.

In: CEUR Workshop Proceedings, Vol. 1623, 2016, p. 791-798.

Research output: Contribution to journalArticle

@article{a200e071292548c191e295e2caa365b8,
title = "A distributed learning method for due date assignment in flexible job shops",
abstract = "This study intends to help manufacturers that use flexible job shops improve performance of due date assignment, that is, setting delivery times to jobs that arrive dynamically. High performing due date assignment enables achieving on-time delivery and quick response of delivery time to customer orders. Traditional methods for due date assignment are predefined equations that estimate the duration of making a product in the production system. Such equations are sufficient for relatively simple systems such as single machine shops, but are not very high in accuracy for complex systems such as flexible job shops. To improve due date assignment for such systems, we propose a more flexible method that uses distributed learning to learn the remaining time of a job inside the system. We let each workstation in the production shop be a distributed unit that updates its local queuing time and interacts with other units to provide the total remaining time of a job. We carry out extensive computational experiments to evaluate performance of the proposed method, and the results show that it outperforms two advanced equational methods in terms of both accuracy of estimation and stability in performance.",
keywords = "Artificial intelligence in production, Distributed system, Due date assignment",
author = "Wei Weng and Gang Rong and Shigeru Fujimura",
year = "2016",
language = "English",
volume = "1623",
pages = "791--798",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - A distributed learning method for due date assignment in flexible job shops

AU - Weng, Wei

AU - Rong, Gang

AU - Fujimura, Shigeru

PY - 2016

Y1 - 2016

N2 - This study intends to help manufacturers that use flexible job shops improve performance of due date assignment, that is, setting delivery times to jobs that arrive dynamically. High performing due date assignment enables achieving on-time delivery and quick response of delivery time to customer orders. Traditional methods for due date assignment are predefined equations that estimate the duration of making a product in the production system. Such equations are sufficient for relatively simple systems such as single machine shops, but are not very high in accuracy for complex systems such as flexible job shops. To improve due date assignment for such systems, we propose a more flexible method that uses distributed learning to learn the remaining time of a job inside the system. We let each workstation in the production shop be a distributed unit that updates its local queuing time and interacts with other units to provide the total remaining time of a job. We carry out extensive computational experiments to evaluate performance of the proposed method, and the results show that it outperforms two advanced equational methods in terms of both accuracy of estimation and stability in performance.

AB - This study intends to help manufacturers that use flexible job shops improve performance of due date assignment, that is, setting delivery times to jobs that arrive dynamically. High performing due date assignment enables achieving on-time delivery and quick response of delivery time to customer orders. Traditional methods for due date assignment are predefined equations that estimate the duration of making a product in the production system. Such equations are sufficient for relatively simple systems such as single machine shops, but are not very high in accuracy for complex systems such as flexible job shops. To improve due date assignment for such systems, we propose a more flexible method that uses distributed learning to learn the remaining time of a job inside the system. We let each workstation in the production shop be a distributed unit that updates its local queuing time and interacts with other units to provide the total remaining time of a job. We carry out extensive computational experiments to evaluate performance of the proposed method, and the results show that it outperforms two advanced equational methods in terms of both accuracy of estimation and stability in performance.

KW - Artificial intelligence in production

KW - Distributed system

KW - Due date assignment

UR - http://www.scopus.com/inward/record.url?scp=85019754605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019754605&partnerID=8YFLogxK

M3 - Article

VL - 1623

SP - 791

EP - 798

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -