Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems
Anomaly detection in large industrial cooling systems is very challenging due to the high data dimensionality, inconsistent sensor recordings, and lack of labels. The state of the art for automated anomaly detection in these systems typically relies on expert knowledge and thresholds. However, data...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-10 |
---|---|
Hauptverfasser: | , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Holly, Stephanie Heel, Robin Katic, Denis Schoeffl, Leopold Stiftinger, Andreas Holzner, Peter Kaufmann, Thomas Haslhofer, Bernhard Schall, Daniel Heitzinger, Clemens Kemnitz, Jana |
description | Anomaly detection in large industrial cooling systems is very challenging due to the high data dimensionality, inconsistent sensor recordings, and lack of labels. The state of the art for automated anomaly detection in these systems typically relies on expert knowledge and thresholds. However, data is viewed isolated and complex, multivariate relationships are neglected. In this work, we present an autoencoder based end-to-end workflow for anomaly detection suitable for multivariate time series data in large industrial cooling systems, including explained fault localization and root cause analysis based on expert knowledge. We identify system failures using a threshold on the total reconstruction error (autoencoder reconstruction error including all sensor signals). For fault localization, we compute the individual reconstruction error (autoencoder reconstruction error for each sensor signal) allowing us to identify the signals that contribute most to the total reconstruction error. Expert knowledge is provided via look-up table enabling root-cause analysis and assignment to the affected subsystem. We demonstrated our findings in a cooling system unit including 34 sensors over a 8-months time period using 4-fold cross validation approaches and automatically created labels based on thresholds provided by domain experts. Using 4-fold cross validation, we reached a F1-score of 0.56, whereas the autoencoder results showed a higher consistency score (CS of 0.92) compared to the automatically created labels (CS of 0.62) -- indicating that the anomaly is recognized in a very stable manner. The main anomaly was found by the autoencoder and automatically created labels and was also recorded in the log files. Further, the explained fault localization highlighted the most affected component for the main anomaly in a very consistent manner. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2725747938</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2725747938</sourcerecordid><originalsourceid>FETCH-proquest_journals_27257479383</originalsourceid><addsrcrecordid>eNqNjkEKwjAQAIMgKNo_LHgWalJtPYpaFLzpvaxtlJR0V5sErK-3iA_wNIeZwwzEWCq1mGeJlCMROVfHcSxXqVwu1VhcN8GzppIr3cIVna5gQ9yg7WCnvS69YQKkCvavh0VDvc8xWA8nLtGaN34DQ3CkKjjfGrSwZbaG7nDunNeNm4rhDa3T0Y8TMcv3l-1h_mj5GbTzRc2hpV4Vsr9Kk3StMvVf9QGoYEYG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2725747938</pqid></control><display><type>article</type><title>Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems</title><source>Free E- Journals</source><creator>Holly, Stephanie ; Heel, Robin ; Katic, Denis ; Schoeffl, Leopold ; Stiftinger, Andreas ; Holzner, Peter ; Kaufmann, Thomas ; Haslhofer, Bernhard ; Schall, Daniel ; Heitzinger, Clemens ; Kemnitz, Jana</creator><creatorcontrib>Holly, Stephanie ; Heel, Robin ; Katic, Denis ; Schoeffl, Leopold ; Stiftinger, Andreas ; Holzner, Peter ; Kaufmann, Thomas ; Haslhofer, Bernhard ; Schall, Daniel ; Heitzinger, Clemens ; Kemnitz, Jana</creatorcontrib><description>Anomaly detection in large industrial cooling systems is very challenging due to the high data dimensionality, inconsistent sensor recordings, and lack of labels. The state of the art for automated anomaly detection in these systems typically relies on expert knowledge and thresholds. However, data is viewed isolated and complex, multivariate relationships are neglected. In this work, we present an autoencoder based end-to-end workflow for anomaly detection suitable for multivariate time series data in large industrial cooling systems, including explained fault localization and root cause analysis based on expert knowledge. We identify system failures using a threshold on the total reconstruction error (autoencoder reconstruction error including all sensor signals). For fault localization, we compute the individual reconstruction error (autoencoder reconstruction error for each sensor signal) allowing us to identify the signals that contribute most to the total reconstruction error. Expert knowledge is provided via look-up table enabling root-cause analysis and assignment to the affected subsystem. We demonstrated our findings in a cooling system unit including 34 sensors over a 8-months time period using 4-fold cross validation approaches and automatically created labels based on thresholds provided by domain experts. Using 4-fold cross validation, we reached a F1-score of 0.56, whereas the autoencoder results showed a higher consistency score (CS of 0.92) compared to the automatically created labels (CS of 0.62) -- indicating that the anomaly is recognized in a very stable manner. The main anomaly was found by the autoencoder and automatically created labels and was also recorded in the log files. Further, the explained fault localization highlighted the most affected component for the main anomaly in a very consistent manner.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Anomalies ; Cooling ; Cooling systems ; Fault location ; Labels ; Localization ; Lookup tables ; Multivariate analysis ; Reconstruction ; Root cause analysis ; Sensors ; Subsystems ; System failures ; Thresholds ; Workflow</subject><ispartof>arXiv.org, 2022-10</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Holly, Stephanie</creatorcontrib><creatorcontrib>Heel, Robin</creatorcontrib><creatorcontrib>Katic, Denis</creatorcontrib><creatorcontrib>Schoeffl, Leopold</creatorcontrib><creatorcontrib>Stiftinger, Andreas</creatorcontrib><creatorcontrib>Holzner, Peter</creatorcontrib><creatorcontrib>Kaufmann, Thomas</creatorcontrib><creatorcontrib>Haslhofer, Bernhard</creatorcontrib><creatorcontrib>Schall, Daniel</creatorcontrib><creatorcontrib>Heitzinger, Clemens</creatorcontrib><creatorcontrib>Kemnitz, Jana</creatorcontrib><title>Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems</title><title>arXiv.org</title><description>Anomaly detection in large industrial cooling systems is very challenging due to the high data dimensionality, inconsistent sensor recordings, and lack of labels. The state of the art for automated anomaly detection in these systems typically relies on expert knowledge and thresholds. However, data is viewed isolated and complex, multivariate relationships are neglected. In this work, we present an autoencoder based end-to-end workflow for anomaly detection suitable for multivariate time series data in large industrial cooling systems, including explained fault localization and root cause analysis based on expert knowledge. We identify system failures using a threshold on the total reconstruction error (autoencoder reconstruction error including all sensor signals). For fault localization, we compute the individual reconstruction error (autoencoder reconstruction error for each sensor signal) allowing us to identify the signals that contribute most to the total reconstruction error. Expert knowledge is provided via look-up table enabling root-cause analysis and assignment to the affected subsystem. We demonstrated our findings in a cooling system unit including 34 sensors over a 8-months time period using 4-fold cross validation approaches and automatically created labels based on thresholds provided by domain experts. Using 4-fold cross validation, we reached a F1-score of 0.56, whereas the autoencoder results showed a higher consistency score (CS of 0.92) compared to the automatically created labels (CS of 0.62) -- indicating that the anomaly is recognized in a very stable manner. The main anomaly was found by the autoencoder and automatically created labels and was also recorded in the log files. Further, the explained fault localization highlighted the most affected component for the main anomaly in a very consistent manner.</description><subject>Anomalies</subject><subject>Cooling</subject><subject>Cooling systems</subject><subject>Fault location</subject><subject>Labels</subject><subject>Localization</subject><subject>Lookup tables</subject><subject>Multivariate analysis</subject><subject>Reconstruction</subject><subject>Root cause analysis</subject><subject>Sensors</subject><subject>Subsystems</subject><subject>System failures</subject><subject>Thresholds</subject><subject>Workflow</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjkEKwjAQAIMgKNo_LHgWalJtPYpaFLzpvaxtlJR0V5sErK-3iA_wNIeZwwzEWCq1mGeJlCMROVfHcSxXqVwu1VhcN8GzppIr3cIVna5gQ9yg7WCnvS69YQKkCvavh0VDvc8xWA8nLtGaN34DQ3CkKjjfGrSwZbaG7nDunNeNm4rhDa3T0Y8TMcv3l-1h_mj5GbTzRc2hpV4Vsr9Kk3StMvVf9QGoYEYG</recordid><startdate>20221014</startdate><enddate>20221014</enddate><creator>Holly, Stephanie</creator><creator>Heel, Robin</creator><creator>Katic, Denis</creator><creator>Schoeffl, Leopold</creator><creator>Stiftinger, Andreas</creator><creator>Holzner, Peter</creator><creator>Kaufmann, Thomas</creator><creator>Haslhofer, Bernhard</creator><creator>Schall, Daniel</creator><creator>Heitzinger, Clemens</creator><creator>Kemnitz, Jana</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20221014</creationdate><title>Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems</title><author>Holly, Stephanie ; Heel, Robin ; Katic, Denis ; Schoeffl, Leopold ; Stiftinger, Andreas ; Holzner, Peter ; Kaufmann, Thomas ; Haslhofer, Bernhard ; Schall, Daniel ; Heitzinger, Clemens ; Kemnitz, Jana</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27257479383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Anomalies</topic><topic>Cooling</topic><topic>Cooling systems</topic><topic>Fault location</topic><topic>Labels</topic><topic>Localization</topic><topic>Lookup tables</topic><topic>Multivariate analysis</topic><topic>Reconstruction</topic><topic>Root cause analysis</topic><topic>Sensors</topic><topic>Subsystems</topic><topic>System failures</topic><topic>Thresholds</topic><topic>Workflow</topic><toplevel>online_resources</toplevel><creatorcontrib>Holly, Stephanie</creatorcontrib><creatorcontrib>Heel, Robin</creatorcontrib><creatorcontrib>Katic, Denis</creatorcontrib><creatorcontrib>Schoeffl, Leopold</creatorcontrib><creatorcontrib>Stiftinger, Andreas</creatorcontrib><creatorcontrib>Holzner, Peter</creatorcontrib><creatorcontrib>Kaufmann, Thomas</creatorcontrib><creatorcontrib>Haslhofer, Bernhard</creatorcontrib><creatorcontrib>Schall, Daniel</creatorcontrib><creatorcontrib>Heitzinger, Clemens</creatorcontrib><creatorcontrib>Kemnitz, Jana</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Holly, Stephanie</au><au>Heel, Robin</au><au>Katic, Denis</au><au>Schoeffl, Leopold</au><au>Stiftinger, Andreas</au><au>Holzner, Peter</au><au>Kaufmann, Thomas</au><au>Haslhofer, Bernhard</au><au>Schall, Daniel</au><au>Heitzinger, Clemens</au><au>Kemnitz, Jana</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems</atitle><jtitle>arXiv.org</jtitle><date>2022-10-14</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Anomaly detection in large industrial cooling systems is very challenging due to the high data dimensionality, inconsistent sensor recordings, and lack of labels. The state of the art for automated anomaly detection in these systems typically relies on expert knowledge and thresholds. However, data is viewed isolated and complex, multivariate relationships are neglected. In this work, we present an autoencoder based end-to-end workflow for anomaly detection suitable for multivariate time series data in large industrial cooling systems, including explained fault localization and root cause analysis based on expert knowledge. We identify system failures using a threshold on the total reconstruction error (autoencoder reconstruction error including all sensor signals). For fault localization, we compute the individual reconstruction error (autoencoder reconstruction error for each sensor signal) allowing us to identify the signals that contribute most to the total reconstruction error. Expert knowledge is provided via look-up table enabling root-cause analysis and assignment to the affected subsystem. We demonstrated our findings in a cooling system unit including 34 sensors over a 8-months time period using 4-fold cross validation approaches and automatically created labels based on thresholds provided by domain experts. Using 4-fold cross validation, we reached a F1-score of 0.56, whereas the autoencoder results showed a higher consistency score (CS of 0.92) compared to the automatically created labels (CS of 0.62) -- indicating that the anomaly is recognized in a very stable manner. The main anomaly was found by the autoencoder and automatically created labels and was also recorded in the log files. Further, the explained fault localization highlighted the most affected component for the main anomaly in a very consistent manner.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2725747938 |
source | Free E- Journals |
subjects | Anomalies Cooling Cooling systems Fault location Labels Localization Lookup tables Multivariate analysis Reconstruction Root cause analysis Sensors Subsystems System failures Thresholds Workflow |
title | Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A14%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Autoencoder%20based%20Anomaly%20Detection%20and%20Explained%20Fault%20Localization%20in%20Industrial%20Cooling%20Systems&rft.jtitle=arXiv.org&rft.au=Holly,%20Stephanie&rft.date=2022-10-14&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2725747938%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2725747938&rft_id=info:pmid/&rfr_iscdi=true |