An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing

Rapid automated logistics within a factory are essential to maximize productivity. In semiconductor manufacturing, the most important logistics management is the efficient operation of overhead hoist transports (OHTs). To transfer wafers via OHTs without delays, it is necessary to predict short-term...

Full description

Saved in:
Bibliographic Details
Main Authors: Donghun Lee, Suhee Kim, Hoonseok Park, Haejoong Kim, Ri Choe, Younkook Kang, Jae-Yoon Jung, Kwanho Kim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11071687/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850094257587617792
author Donghun Lee
Suhee Kim
Hoonseok Park
Haejoong Kim
Ri Choe
Younkook Kang
Jae-Yoon Jung
Kwanho Kim
author_facet Donghun Lee
Suhee Kim
Hoonseok Park
Haejoong Kim
Ri Choe
Younkook Kang
Jae-Yoon Jung
Kwanho Kim
author_sort Donghun Lee
collection DOAJ
description Rapid automated logistics within a factory are essential to maximize productivity. In semiconductor manufacturing, the most important logistics management is the efficient operation of overhead hoist transports (OHTs). To transfer wafers via OHTs without delays, it is necessary to predict short-term traffic congestion in the OHT railway accurately. However, the congestion prediction is a significant challenge due to the complexity of investigating all traffic conditions and dynamic traffic changes. Several studies have utilized machine learning approaches to address these concerns, but limitations arise in predicting the short-term congestion due to the performance bias stemming from large input features. Recurrent neural networks are effective in predicting traffic flow in transportation. However, they may not be suitable for OHT railway congestion prediction due to unpredictable loading/unloading events and varying traffic volumes. Therefore, this study proposes an integrated neural network-based method where multiple neural networks are trained considering current conditions of the railway network and expected changes in traffic conditions. To verify the effectiveness of the proposed method, a simulated dataset was used to reflecting real-world semiconductor fabrication. The experiment results demonstrate that the proposed method outperforms existing methods, including machine learning- and deep learning-based methods.
format Article
id doaj-art-c28898867d494e17a50e11bf6fea02e1
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c28898867d494e17a50e11bf6fea02e12025-08-20T02:41:42ZengIEEEIEEE Access2169-35362025-01-011312163012164010.1109/ACCESS.2025.358591411071687An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor ManufacturingDonghun Lee0https://orcid.org/0000-0003-2141-6761Suhee Kim1https://orcid.org/0009-0003-5897-1950Hoonseok Park2Haejoong Kim3Ri Choe4Younkook Kang5Jae-Yoon Jung6https://orcid.org/0000-0002-4850-6284Kwanho Kim7https://orcid.org/0000-0002-9487-2365Department of Industrial and Management Engineering, Incheon National University, Incheon, Republic of KoreaDepartment of Industrial and Management Engineering, Incheon National University, Incheon, Republic of KoreaDepartment of Big Data Analytics, Kyung Hee University, Yongin, Republic of KoreaDepartment of Industrial and Management Engineering, Kyonggi University, Suwon, Republic of KoreaMaterial Handling Automation Group, Samsung Electronics, Hwaseong, Republic of KoreaMaterial Handling Automation Group, Samsung Electronics, Hwaseong, Republic of KoreaDepartment of Big Data Analytics, Kyung Hee University, Yongin, Republic of KoreaDepartment of Industrial and Systems Engineering, Dongguk University, Seoul, Republic of KoreaRapid automated logistics within a factory are essential to maximize productivity. In semiconductor manufacturing, the most important logistics management is the efficient operation of overhead hoist transports (OHTs). To transfer wafers via OHTs without delays, it is necessary to predict short-term traffic congestion in the OHT railway accurately. However, the congestion prediction is a significant challenge due to the complexity of investigating all traffic conditions and dynamic traffic changes. Several studies have utilized machine learning approaches to address these concerns, but limitations arise in predicting the short-term congestion due to the performance bias stemming from large input features. Recurrent neural networks are effective in predicting traffic flow in transportation. However, they may not be suitable for OHT railway congestion prediction due to unpredictable loading/unloading events and varying traffic volumes. Therefore, this study proposes an integrated neural network-based method where multiple neural networks are trained considering current conditions of the railway network and expected changes in traffic conditions. To verify the effectiveness of the proposed method, a simulated dataset was used to reflecting real-world semiconductor fabrication. The experiment results demonstrate that the proposed method outperforms existing methods, including machine learning- and deep learning-based methods.https://ieeexplore.ieee.org/document/11071687/Integrated neural networksshort-term traffic congestion predictionsemiconductor fabricationsustainable operation
spellingShingle Donghun Lee
Suhee Kim
Hoonseok Park
Haejoong Kim
Ri Choe
Younkook Kang
Jae-Yoon Jung
Kwanho Kim
An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
IEEE Access
Integrated neural networks
short-term traffic congestion prediction
semiconductor fabrication
sustainable operation
title An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
title_full An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
title_fullStr An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
title_full_unstemmed An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
title_short An Integrated Neural Network-Based Traffic Congestion Prediction for Material Handling Systems of Semiconductor Manufacturing
title_sort integrated neural network based traffic congestion prediction for material handling systems of semiconductor manufacturing
topic Integrated neural networks
short-term traffic congestion prediction
semiconductor fabrication
sustainable operation
url https://ieeexplore.ieee.org/document/11071687/
work_keys_str_mv AT donghunlee anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT suheekim anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT hoonseokpark anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT haejoongkim anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT richoe anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT younkookkang anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT jaeyoonjung anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT kwanhokim anintegratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT donghunlee integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT suheekim integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT hoonseokpark integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT haejoongkim integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT richoe integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT younkookkang integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT jaeyoonjung integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing
AT kwanhokim integratedneuralnetworkbasedtrafficcongestionpredictionformaterialhandlingsystemsofsemiconductormanufacturing