Congestion-aware dynamic routing for an overhead hoist transporter system using a graph convolutional gated recurrent unit

Kyuree Ahn, Kanghoon Lee, Juneyoung Yeon and Jinkyoo Park

IISE Transactions, 2022, vol. 54, issue 8, 803-816

Abstract: Overhead hoist transportors (OHT) that transport semiconductor wafers between tools/stockers, is a crucial component of an Automated Material Handling System (AMHS). As semiconductor fabrication plants (FABs) become larger, more OHT vehicles need to be operated. This necessitates the development of a scalable algorithm to effectively operate these OHTs and increase the productivity of the AMHS. This study proposes an algorithm that can predict the entire traveling times of the edges in an OHT rail network by utilizing past traffic information. The model first represents the OHT rail network and the dynamic traffic conditions using a graph. A sequence of graphs that represent the past traffic is then used as an input to produce a sequence of graphs that predicts the future traffic conditions as an output. Using the AutoMod simulator, we have shown that the proposed model scalably and effectively predicts the future edge-traveling time. We have also demonstrated that the predicted values can be used to reroute the OHTs optimally to avoid congestion.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/24725854.2021.2000680 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:uiiexx:v:54:y:2022:i:8:p:803-816

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/uiie20

DOI: 10.1080/24725854.2021.2000680

Access Statistics for this article

IISE Transactions is currently edited by Jianjun Shi

More articles in IISE Transactions from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().