Dynamic dispatching system using a deep denoising autoencoder for semiconductor manufacturing

Sangmin Lee, Hae Joong Kim, Seoung Bum Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Deep denoising autoencoders (DDAE), which are variants of the autoencoder, have shown outstanding performance in various machine learning tasks. In this study, we propose using a DDAE to address a dispatching rule selection problem that represents a major problem in semiconductor manufacturing. Recently, the significance of dispatching systems for storage allocation has become more apparent because operational issues lead to transfer inefficiency, resulting in production losses. Further, recent approaches have overlooked the possibility of a class imbalance problem in predicting the best dispatching rule. The main purpose of this study is to examine DDAE-based predictive control of the storage dispatching systems to reduce idle machines and production losses. We conducted an experimental evaluation to compare the predictive performance of DDAE with those of five other novelty detection algorithms. Finally, we compared our adaptive approach with the optimization and existing heuristic approaches to demonstrate the effectiveness and efficiency of the proposed method. The experimental results demonstrated that the proposed method outperformed the existing methods in terms of machine utilizations and throughputs.

Original languageEnglish
Article number105904
JournalApplied Soft Computing Journal
Volume86
DOIs
Publication statusPublished - 2020 Jan

Fingerprint

Semiconductor materials
Learning systems
Throughput

Keywords

  • Class imbalance problem
  • Deep denoising autoencoder
  • Dispatching rule selection
  • Novelty detection
  • Storage allocation

ASJC Scopus subject areas

  • Software

Cite this

Dynamic dispatching system using a deep denoising autoencoder for semiconductor manufacturing. / Lee, Sangmin; Kim, Hae Joong; Kim, Seoung Bum.

In: Applied Soft Computing Journal, Vol. 86, 105904, 01.2020.

Research output: Contribution to journalArticle

@article{9df7bec2b5bd42c6a9ba33fcaf34cfcf,
title = "Dynamic dispatching system using a deep denoising autoencoder for semiconductor manufacturing",
abstract = "Deep denoising autoencoders (DDAE), which are variants of the autoencoder, have shown outstanding performance in various machine learning tasks. In this study, we propose using a DDAE to address a dispatching rule selection problem that represents a major problem in semiconductor manufacturing. Recently, the significance of dispatching systems for storage allocation has become more apparent because operational issues lead to transfer inefficiency, resulting in production losses. Further, recent approaches have overlooked the possibility of a class imbalance problem in predicting the best dispatching rule. The main purpose of this study is to examine DDAE-based predictive control of the storage dispatching systems to reduce idle machines and production losses. We conducted an experimental evaluation to compare the predictive performance of DDAE with those of five other novelty detection algorithms. Finally, we compared our adaptive approach with the optimization and existing heuristic approaches to demonstrate the effectiveness and efficiency of the proposed method. The experimental results demonstrated that the proposed method outperformed the existing methods in terms of machine utilizations and throughputs.",
keywords = "Class imbalance problem, Deep denoising autoencoder, Dispatching rule selection, Novelty detection, Storage allocation",
author = "Sangmin Lee and Kim, {Hae Joong} and Kim, {Seoung Bum}",
year = "2020",
month = "1",
doi = "10.1016/j.asoc.2019.105904",
language = "English",
volume = "86",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Dynamic dispatching system using a deep denoising autoencoder for semiconductor manufacturing

AU - Lee, Sangmin

AU - Kim, Hae Joong

AU - Kim, Seoung Bum

PY - 2020/1

Y1 - 2020/1

N2 - Deep denoising autoencoders (DDAE), which are variants of the autoencoder, have shown outstanding performance in various machine learning tasks. In this study, we propose using a DDAE to address a dispatching rule selection problem that represents a major problem in semiconductor manufacturing. Recently, the significance of dispatching systems for storage allocation has become more apparent because operational issues lead to transfer inefficiency, resulting in production losses. Further, recent approaches have overlooked the possibility of a class imbalance problem in predicting the best dispatching rule. The main purpose of this study is to examine DDAE-based predictive control of the storage dispatching systems to reduce idle machines and production losses. We conducted an experimental evaluation to compare the predictive performance of DDAE with those of five other novelty detection algorithms. Finally, we compared our adaptive approach with the optimization and existing heuristic approaches to demonstrate the effectiveness and efficiency of the proposed method. The experimental results demonstrated that the proposed method outperformed the existing methods in terms of machine utilizations and throughputs.

AB - Deep denoising autoencoders (DDAE), which are variants of the autoencoder, have shown outstanding performance in various machine learning tasks. In this study, we propose using a DDAE to address a dispatching rule selection problem that represents a major problem in semiconductor manufacturing. Recently, the significance of dispatching systems for storage allocation has become more apparent because operational issues lead to transfer inefficiency, resulting in production losses. Further, recent approaches have overlooked the possibility of a class imbalance problem in predicting the best dispatching rule. The main purpose of this study is to examine DDAE-based predictive control of the storage dispatching systems to reduce idle machines and production losses. We conducted an experimental evaluation to compare the predictive performance of DDAE with those of five other novelty detection algorithms. Finally, we compared our adaptive approach with the optimization and existing heuristic approaches to demonstrate the effectiveness and efficiency of the proposed method. The experimental results demonstrated that the proposed method outperformed the existing methods in terms of machine utilizations and throughputs.

KW - Class imbalance problem

KW - Deep denoising autoencoder

KW - Dispatching rule selection

KW - Novelty detection

KW - Storage allocation

UR - http://www.scopus.com/inward/record.url?scp=85075351858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075351858&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2019.105904

DO - 10.1016/j.asoc.2019.105904

M3 - Article

AN - SCOPUS:85075351858

VL - 86

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

M1 - 105904

ER -