No Cover Image

Journal article 477 views 291 downloads

A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders

Aniekan Essien Orcid Logo, Cinzia Giannetti Orcid Logo

IEEE Transactions on Industrial Informatics, Volume: 16, Issue: 9, Pages: 6069 - 6078

Swansea University Authors: Aniekan Essien Orcid Logo, Cinzia Giannetti Orcid Logo

Abstract

Timeseries forecasting is applied to many areas of smart factories, including machine health monitoring (MHM), predictive maintenance, and production scheduling. In smart factories, machine speed prediction can be used to dynamically adjust production processes based on different system conditions,...

Full description

Published in: IEEE Transactions on Industrial Informatics
ISSN: 1551-3203 1941-0050
Published: Institute of Electrical and Electronics Engineers (IEEE) 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa53318
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-02-28T19:41:54Z
last_indexed 2021-08-06T03:10:48Z
id cronfa53318
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-08-05T15:42:16.9287367</datestamp><bib-version>v2</bib-version><id>53318</id><entry>2020-01-21</entry><title>A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders</title><swanseaauthors><author><sid>8fee3cc958c5121489b2575535864ae6</sid><ORCID>0000-0001-9501-0647</ORCID><firstname>Aniekan</firstname><surname>Essien</surname><name>Aniekan Essien</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2020-01-21</date><deptcode>EEN</deptcode><abstract>Timeseries forecasting is applied to many areas of smart factories, including machine health monitoring (MHM), predictive maintenance, and production scheduling. In smart factories, machine speed prediction can be used to dynamically adjust production processes based on different system conditions, optimise production throughput, and minimise energy consumption. However, making accurate data-driven machine speed forecasts is challenging. Given the complex nature of industrial manufacturing processes, predictive models that are robust to noise and can capture the temporal and spatial distributions of the input timeseries are prerequisites for accurate forecasting. Motivated by recent deep learning studies in smart manufacturing, this paper proposes an end-to-end model for multi-step-ahead machine speed prediction. The model, known as 2D-Convolutional LSTM Autoencoder (2DConvLSTMAE), comprises a deep convolutional LSTM (ConvLSTM) encoder-decoder architecture. Extensive empirical analyses using real-world data obtained from a metal packaging plant in the United Kingdom demonstrate the value of the proposed method when compared to state-of-the-art deep learning models.</abstract><type>Journal Article</type><journal>IEEE Transactions on Industrial Informatics</journal><volume>16</volume><journalNumber>9</journalNumber><paginationStart>6069</paginationStart><paginationEnd>6078</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1551-3203</issnPrint><issnElectronic>1941-0050</issnElectronic><keywords>deep learning, ConvLSTM, stacked autoencoders, timeseries prediction, Industry 4.0</keywords><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-09-01</publishedDate><doi>10.1109/tii.2020.2967556</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEN</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>UKRI, EP/S001387/1</funders><lastEdited>2021-08-05T15:42:16.9287367</lastEdited><Created>2020-01-21T10:14:33.2458190</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Aniekan</firstname><surname>Essien</surname><orcid>0000-0001-9501-0647</orcid><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author></authors><documents><document><filename>53318__17414__2da379d11c2f437aa113e87ad1ed306b.pdf</filename><originalFilename>53318.pdf</originalFilename><uploaded>2020-06-03T16:26:37.7735253</uploaded><type>Output</type><contentLength>5125326</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>true</copyrightCorrect><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-08-05T15:42:16.9287367 v2 53318 2020-01-21 A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders 8fee3cc958c5121489b2575535864ae6 0000-0001-9501-0647 Aniekan Essien Aniekan Essien true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2020-01-21 EEN Timeseries forecasting is applied to many areas of smart factories, including machine health monitoring (MHM), predictive maintenance, and production scheduling. In smart factories, machine speed prediction can be used to dynamically adjust production processes based on different system conditions, optimise production throughput, and minimise energy consumption. However, making accurate data-driven machine speed forecasts is challenging. Given the complex nature of industrial manufacturing processes, predictive models that are robust to noise and can capture the temporal and spatial distributions of the input timeseries are prerequisites for accurate forecasting. Motivated by recent deep learning studies in smart manufacturing, this paper proposes an end-to-end model for multi-step-ahead machine speed prediction. The model, known as 2D-Convolutional LSTM Autoencoder (2DConvLSTMAE), comprises a deep convolutional LSTM (ConvLSTM) encoder-decoder architecture. Extensive empirical analyses using real-world data obtained from a metal packaging plant in the United Kingdom demonstrate the value of the proposed method when compared to state-of-the-art deep learning models. Journal Article IEEE Transactions on Industrial Informatics 16 9 6069 6078 Institute of Electrical and Electronics Engineers (IEEE) 1551-3203 1941-0050 deep learning, ConvLSTM, stacked autoencoders, timeseries prediction, Industry 4.0 1 9 2020 2020-09-01 10.1109/tii.2020.2967556 COLLEGE NANME Engineering COLLEGE CODE EEN Swansea University UKRI, EP/S001387/1 2021-08-05T15:42:16.9287367 2020-01-21T10:14:33.2458190 College of Engineering Engineering Aniekan Essien 0000-0001-9501-0647 1 Cinzia Giannetti 0000-0003-0339-5872 2 53318__17414__2da379d11c2f437aa113e87ad1ed306b.pdf 53318.pdf 2020-06-03T16:26:37.7735253 Output 5125326 application/pdf Version of Record true true https://creativecommons.org/licenses/by/4.0/
title A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
spellingShingle A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
Aniekan Essien
Cinzia Giannetti
title_short A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
title_full A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
title_fullStr A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
title_full_unstemmed A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
title_sort A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders
author_id_str_mv 8fee3cc958c5121489b2575535864ae6
a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv 8fee3cc958c5121489b2575535864ae6_***_Aniekan Essien
a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author Aniekan Essien
Cinzia Giannetti
author2 Aniekan Essien
Cinzia Giannetti
format Journal article
container_title IEEE Transactions on Industrial Informatics
container_volume 16
container_issue 9
container_start_page 6069
publishDate 2020
institution Swansea University
issn 1551-3203
1941-0050
doi_str_mv 10.1109/tii.2020.2967556
publisher Institute of Electrical and Electronics Engineers (IEEE)
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Engineering{{{_:::_}}}College of Engineering{{{_:::_}}}Engineering
document_store_str 1
active_str 0
description Timeseries forecasting is applied to many areas of smart factories, including machine health monitoring (MHM), predictive maintenance, and production scheduling. In smart factories, machine speed prediction can be used to dynamically adjust production processes based on different system conditions, optimise production throughput, and minimise energy consumption. However, making accurate data-driven machine speed forecasts is challenging. Given the complex nature of industrial manufacturing processes, predictive models that are robust to noise and can capture the temporal and spatial distributions of the input timeseries are prerequisites for accurate forecasting. Motivated by recent deep learning studies in smart manufacturing, this paper proposes an end-to-end model for multi-step-ahead machine speed prediction. The model, known as 2D-Convolutional LSTM Autoencoder (2DConvLSTMAE), comprises a deep convolutional LSTM (ConvLSTM) encoder-decoder architecture. Extensive empirical analyses using real-world data obtained from a metal packaging plant in the United Kingdom demonstrate the value of the proposed method when compared to state-of-the-art deep learning models.
published_date 2020-09-01T04:07:32Z
_version_ 1737027435775393792
score 10.917563