Loading…

Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction

Remaining useful life (RUL) prediction is crucial for enhancing equipment reliability and safety in industry. In recent years, deep learning techniques, particularly those based on Long Short-Term Memory (LSTM) networks, have been widely used in the field. However, the performance of LSTM-based mode...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2024-02, Vol.24 (3), p.1-1
Main Authors: Li, Xuanlin, Hu, Yawei, Wang, Hang, Liu, Yongbin, Liu, Xianzeng, Cao, Zheng
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993
cites cdi_FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993
container_end_page 1
container_issue 3
container_start_page 1
container_title IEEE sensors journal
container_volume 24
creator Li, Xuanlin
Hu, Yawei
Wang, Hang
Liu, Yongbin
Liu, Xianzeng
Cao, Zheng
description Remaining useful life (RUL) prediction is crucial for enhancing equipment reliability and safety in industry. In recent years, deep learning techniques, particularly those based on Long Short-Term Memory (LSTM) networks, have been widely used in the field. However, the performance of LSTM-based models is often constrained by the loss of early time dependence. Additionally, learning the mapping relationships between large multi-sensor data and features poses a challenge. To address these issues, a novel multi-sensor data-driven RUL prediction method named the Spatial-Temporal Attention and Information Reinforcement Network (STAIRnet) is proposed. First, the spatial-temporal attention module adaptively weights and encodes the original signal in both temporal and spatial dimensions. Second, the feature extraction module extracts hidden features from the weighted data, while the lookback mechanism filters the hidden states. Following that, the information reinforcement module decodes the encoded information and supplements, which reinforces the hidden features to improve the model performance. Finally, degraded features are mapped to specific RUL values. The effectiveness of STAIRnet was validated using a commonly used dataset. The results demonstrated that the proposed method outperformed other approaches in terms of prediction accuracy and computational efficiency.
doi_str_mv 10.1109/JSEN.2023.3342884
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2920286032</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10367835</ieee_id><sourcerecordid>2920286032</sourcerecordid><originalsourceid>FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993</originalsourceid><addsrcrecordid>eNpNkEtLxDAQgIMouK7-AMFDwHPXvNqmR1nWF4seVsFbSdOJZm3TmqaI_950dw-e5sE3M8yH0CUlC0pJcfO0WT0vGGF8wblgUoojNKNpKhOaC3k85Zwkgufvp-hsGLaE0CJP8xlqN70KVjVJgLbvvGqwCgFcsJ3DytXYOtP5Vu1qD7tKQxsB7CD8dP4Lxw5ulf60DiLRKuus-8DjAGZscGMN4N5DbfW04hydGNUMcHGIc_R2t3pdPiTrl_vH5e060awQIVGMqUoKmRrNFTAhREYkCAGZ1qKuskyq-JvhtTY5pRXlqqpFLVKW8iI1RcHn6Hq_t_fd9whDKLfd6F08WbIiWpIZ4SxSdE9p3w2DB1P23rbK_5aUlJPVcrJaTlbLg9U4c7WfsQDwj-dZLnnK_wCA-3Ys</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2920286032</pqid></control><display><type>article</type><title>Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Li, Xuanlin ; Hu, Yawei ; Wang, Hang ; Liu, Yongbin ; Liu, Xianzeng ; Cao, Zheng</creator><creatorcontrib>Li, Xuanlin ; Hu, Yawei ; Wang, Hang ; Liu, Yongbin ; Liu, Xianzeng ; Cao, Zheng</creatorcontrib><description>Remaining useful life (RUL) prediction is crucial for enhancing equipment reliability and safety in industry. In recent years, deep learning techniques, particularly those based on Long Short-Term Memory (LSTM) networks, have been widely used in the field. However, the performance of LSTM-based models is often constrained by the loss of early time dependence. Additionally, learning the mapping relationships between large multi-sensor data and features poses a challenge. To address these issues, a novel multi-sensor data-driven RUL prediction method named the Spatial-Temporal Attention and Information Reinforcement Network (STAIRnet) is proposed. First, the spatial-temporal attention module adaptively weights and encodes the original signal in both temporal and spatial dimensions. Second, the feature extraction module extracts hidden features from the weighted data, while the lookback mechanism filters the hidden states. Following that, the information reinforcement module decodes the encoded information and supplements, which reinforces the hidden features to improve the model performance. Finally, degraded features are mapped to specific RUL values. The effectiveness of STAIRnet was validated using a commonly used dataset. The results demonstrated that the proposed method outperformed other approaches in terms of prediction accuracy and computational efficiency.</description><identifier>ISSN: 1530-437X</identifier><identifier>EISSN: 1558-1748</identifier><identifier>DOI: 10.1109/JSEN.2023.3342884</identifier><identifier>CODEN: ISJEAZ</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Deep learning ; Feature extraction ; Information reinforcement ; Life prediction ; long short-term memory ; Modules ; Performance degradation ; Remaining useful life prediction ; Spatial-temporal attention ; Useful life</subject><ispartof>IEEE sensors journal, 2024-02, Vol.24 (3), p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993</citedby><cites>FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993</cites><orcidid>0000-0002-3420-3784 ; 0000-0002-1849-1720 ; 0000-0003-0329-6110 ; 0000-0002-6937-9958 ; 0000-0001-8797-434X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10367835$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27923,27924,54795</link.rule.ids></links><search><creatorcontrib>Li, Xuanlin</creatorcontrib><creatorcontrib>Hu, Yawei</creatorcontrib><creatorcontrib>Wang, Hang</creatorcontrib><creatorcontrib>Liu, Yongbin</creatorcontrib><creatorcontrib>Liu, Xianzeng</creatorcontrib><creatorcontrib>Cao, Zheng</creatorcontrib><title>Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction</title><title>IEEE sensors journal</title><addtitle>JSEN</addtitle><description>Remaining useful life (RUL) prediction is crucial for enhancing equipment reliability and safety in industry. In recent years, deep learning techniques, particularly those based on Long Short-Term Memory (LSTM) networks, have been widely used in the field. However, the performance of LSTM-based models is often constrained by the loss of early time dependence. Additionally, learning the mapping relationships between large multi-sensor data and features poses a challenge. To address these issues, a novel multi-sensor data-driven RUL prediction method named the Spatial-Temporal Attention and Information Reinforcement Network (STAIRnet) is proposed. First, the spatial-temporal attention module adaptively weights and encodes the original signal in both temporal and spatial dimensions. Second, the feature extraction module extracts hidden features from the weighted data, while the lookback mechanism filters the hidden states. Following that, the information reinforcement module decodes the encoded information and supplements, which reinforces the hidden features to improve the model performance. Finally, degraded features are mapped to specific RUL values. The effectiveness of STAIRnet was validated using a commonly used dataset. The results demonstrated that the proposed method outperformed other approaches in terms of prediction accuracy and computational efficiency.</description><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Information reinforcement</subject><subject>Life prediction</subject><subject>long short-term memory</subject><subject>Modules</subject><subject>Performance degradation</subject><subject>Remaining useful life prediction</subject><subject>Spatial-temporal attention</subject><subject>Useful life</subject><issn>1530-437X</issn><issn>1558-1748</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpNkEtLxDAQgIMouK7-AMFDwHPXvNqmR1nWF4seVsFbSdOJZm3TmqaI_950dw-e5sE3M8yH0CUlC0pJcfO0WT0vGGF8wblgUoojNKNpKhOaC3k85Zwkgufvp-hsGLaE0CJP8xlqN70KVjVJgLbvvGqwCgFcsJ3DytXYOtP5Vu1qD7tKQxsB7CD8dP4Lxw5ulf60DiLRKuus-8DjAGZscGMN4N5DbfW04hydGNUMcHGIc_R2t3pdPiTrl_vH5e060awQIVGMqUoKmRrNFTAhREYkCAGZ1qKuskyq-JvhtTY5pRXlqqpFLVKW8iI1RcHn6Hq_t_fd9whDKLfd6F08WbIiWpIZ4SxSdE9p3w2DB1P23rbK_5aUlJPVcrJaTlbLg9U4c7WfsQDwj-dZLnnK_wCA-3Ys</recordid><startdate>20240201</startdate><enddate>20240201</enddate><creator>Li, Xuanlin</creator><creator>Hu, Yawei</creator><creator>Wang, Hang</creator><creator>Liu, Yongbin</creator><creator>Liu, Xianzeng</creator><creator>Cao, Zheng</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-3420-3784</orcidid><orcidid>https://orcid.org/0000-0002-1849-1720</orcidid><orcidid>https://orcid.org/0000-0003-0329-6110</orcidid><orcidid>https://orcid.org/0000-0002-6937-9958</orcidid><orcidid>https://orcid.org/0000-0001-8797-434X</orcidid></search><sort><creationdate>20240201</creationdate><title>Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction</title><author>Li, Xuanlin ; Hu, Yawei ; Wang, Hang ; Liu, Yongbin ; Liu, Xianzeng ; Cao, Zheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Information reinforcement</topic><topic>Life prediction</topic><topic>long short-term memory</topic><topic>Modules</topic><topic>Performance degradation</topic><topic>Remaining useful life prediction</topic><topic>Spatial-temporal attention</topic><topic>Useful life</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Xuanlin</creatorcontrib><creatorcontrib>Hu, Yawei</creatorcontrib><creatorcontrib>Wang, Hang</creatorcontrib><creatorcontrib>Liu, Yongbin</creatorcontrib><creatorcontrib>Liu, Xianzeng</creatorcontrib><creatorcontrib>Cao, Zheng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE sensors journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Xuanlin</au><au>Hu, Yawei</au><au>Wang, Hang</au><au>Liu, Yongbin</au><au>Liu, Xianzeng</au><au>Cao, Zheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction</atitle><jtitle>IEEE sensors journal</jtitle><stitle>JSEN</stitle><date>2024-02-01</date><risdate>2024</risdate><volume>24</volume><issue>3</issue><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>1530-437X</issn><eissn>1558-1748</eissn><coden>ISJEAZ</coden><abstract>Remaining useful life (RUL) prediction is crucial for enhancing equipment reliability and safety in industry. In recent years, deep learning techniques, particularly those based on Long Short-Term Memory (LSTM) networks, have been widely used in the field. However, the performance of LSTM-based models is often constrained by the loss of early time dependence. Additionally, learning the mapping relationships between large multi-sensor data and features poses a challenge. To address these issues, a novel multi-sensor data-driven RUL prediction method named the Spatial-Temporal Attention and Information Reinforcement Network (STAIRnet) is proposed. First, the spatial-temporal attention module adaptively weights and encodes the original signal in both temporal and spatial dimensions. Second, the feature extraction module extracts hidden features from the weighted data, while the lookback mechanism filters the hidden states. Following that, the information reinforcement module decodes the encoded information and supplements, which reinforces the hidden features to improve the model performance. Finally, degraded features are mapped to specific RUL values. The effectiveness of STAIRnet was validated using a commonly used dataset. The results demonstrated that the proposed method outperformed other approaches in terms of prediction accuracy and computational efficiency.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/JSEN.2023.3342884</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-3420-3784</orcidid><orcidid>https://orcid.org/0000-0002-1849-1720</orcidid><orcidid>https://orcid.org/0000-0003-0329-6110</orcidid><orcidid>https://orcid.org/0000-0002-6937-9958</orcidid><orcidid>https://orcid.org/0000-0001-8797-434X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1530-437X
ispartof IEEE sensors journal, 2024-02, Vol.24 (3), p.1-1
issn 1530-437X
1558-1748
language eng
recordid cdi_proquest_journals_2920286032
source IEEE Electronic Library (IEL) Journals
subjects Deep learning
Feature extraction
Information reinforcement
Life prediction
long short-term memory
Modules
Performance degradation
Remaining useful life prediction
Spatial-temporal attention
Useful life
title Spatial-temporal attention and information reinforcement network for machine remaining useful life prediction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T02%3A56%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Spatial-temporal%20attention%20and%20information%20reinforcement%20network%20for%20machine%20remaining%20useful%20life%20prediction&rft.jtitle=IEEE%20sensors%20journal&rft.au=Li,%20Xuanlin&rft.date=2024-02-01&rft.volume=24&rft.issue=3&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=1530-437X&rft.eissn=1558-1748&rft.coden=ISJEAZ&rft_id=info:doi/10.1109/JSEN.2023.3342884&rft_dat=%3Cproquest_ieee_%3E2920286032%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c294t-a22ab8485fc3ae2444608e44e6cc4db668a155f3dcf711b13abd4d4525395f993%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2920286032&rft_id=info:pmid/&rft_ieee_id=10367835&rfr_iscdi=true