Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder
This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-05 |
---|---|
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 | Naito, Susumu Taguchi, Yasunori Nakata, Kouta Kato, Yuichi |
description | This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need for anomaly detection techniques is increasing in order to reduce the cost of operation and maintenance, in view of a decline in the number of skilled engineers and a shortage of manpower. However, considering the complex behavior of high-dimensional signals and the demand for interpretability, the techniques constitute a major challenge. We introduce a Two-Stage AutoEncoder (TSAE) as an anomaly detection method suitable for such plants. This is a simple autoencoder architecture that makes anomaly detection more interpretable and more accurate, in which based on the premise that plant signals can be separated into two behaviors that have almost no correlation with each other, the signals are separated into long-term and short-term components in a stepwise manner, and the two components are trained independently to improve the inference capability for normal signals. Through experiments on two publicly available datasets of water treatment systems, we have confirmed the high detection performance, the validity of the premise, and that the model behavior was as intended, i.e., the technical effectiveness of TSAE. |
doi_str_mv | 10.48550/arxiv.2205.09924 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2205_09924</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2667957336</sourcerecordid><originalsourceid>FETCH-LOGICAL-a526-7ff2332da9338c69eb7da32739d94bbdbc38c5958b26b63cf673ab7d11fcdd523</originalsourceid><addsrcrecordid>eNotkNFKwzAUhoMgOOYewCsDXnemSZM2l2M6J0wUrNfltElLRpfMJJ3u7e02r87h_B-Hnw-hu5TMs4Jz8gj-1xzmlBI-J1LS7ApNKGNpUmSU3qBZCFtCCBU55ZxNkF1Yt4P-iJ901E00zuLWefw29NEcwBuIGpdmp_Gn9kYHPOYb8J1OQgO9xqt-MAqvware2A5_9GAj_gqnvfxxSYjQabwYotO2cUr7W3TdQh_07H9OUbl6LpfrZPP-8rpcbBLgVCR5246VqQLJWNEIqetcAaM5k0pmda3qZjxzyYuailqwphU5g5FJ07ZRilM2RfeXt2cZ1d6bHfhjdZJSnaWMxMOF2Hv3PegQq60bvB07VVSIXPKcMcH-AFSAZdw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2667957336</pqid></control><display><type>article</type><title>Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Naito, Susumu ; Taguchi, Yasunori ; Nakata, Kouta ; Kato, Yuichi</creator><creatorcontrib>Naito, Susumu ; Taguchi, Yasunori ; Nakata, Kouta ; Kato, Yuichi</creatorcontrib><description>This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need for anomaly detection techniques is increasing in order to reduce the cost of operation and maintenance, in view of a decline in the number of skilled engineers and a shortage of manpower. However, considering the complex behavior of high-dimensional signals and the demand for interpretability, the techniques constitute a major challenge. We introduce a Two-Stage AutoEncoder (TSAE) as an anomaly detection method suitable for such plants. This is a simple autoencoder architecture that makes anomaly detection more interpretable and more accurate, in which based on the premise that plant signals can be separated into two behaviors that have almost no correlation with each other, the signals are separated into long-term and short-term components in a stepwise manner, and the two components are trained independently to improve the inference capability for normal signals. Through experiments on two publicly available datasets of water treatment systems, we have confirmed the high detection performance, the validity of the premise, and that the model behavior was as intended, i.e., the technical effectiveness of TSAE.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2205.09924</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Anomalies ; Chemical industry ; Computer Science - Learning ; Multivariate analysis ; Time series ; Water treatment</subject><ispartof>arXiv.org, 2022-05</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><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,782,883,27914</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2205.09924$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/ICDMW53433.2021.00072$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Naito, Susumu</creatorcontrib><creatorcontrib>Taguchi, Yasunori</creatorcontrib><creatorcontrib>Nakata, Kouta</creatorcontrib><creatorcontrib>Kato, Yuichi</creatorcontrib><title>Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder</title><title>arXiv.org</title><description>This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need for anomaly detection techniques is increasing in order to reduce the cost of operation and maintenance, in view of a decline in the number of skilled engineers and a shortage of manpower. However, considering the complex behavior of high-dimensional signals and the demand for interpretability, the techniques constitute a major challenge. We introduce a Two-Stage AutoEncoder (TSAE) as an anomaly detection method suitable for such plants. This is a simple autoencoder architecture that makes anomaly detection more interpretable and more accurate, in which based on the premise that plant signals can be separated into two behaviors that have almost no correlation with each other, the signals are separated into long-term and short-term components in a stepwise manner, and the two components are trained independently to improve the inference capability for normal signals. Through experiments on two publicly available datasets of water treatment systems, we have confirmed the high detection performance, the validity of the premise, and that the model behavior was as intended, i.e., the technical effectiveness of TSAE.</description><subject>Anomalies</subject><subject>Chemical industry</subject><subject>Computer Science - Learning</subject><subject>Multivariate analysis</subject><subject>Time series</subject><subject>Water treatment</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><sourceid>GOX</sourceid><recordid>eNotkNFKwzAUhoMgOOYewCsDXnemSZM2l2M6J0wUrNfltElLRpfMJJ3u7e02r87h_B-Hnw-hu5TMs4Jz8gj-1xzmlBI-J1LS7ApNKGNpUmSU3qBZCFtCCBU55ZxNkF1Yt4P-iJ901E00zuLWefw29NEcwBuIGpdmp_Gn9kYHPOYb8J1OQgO9xqt-MAqvware2A5_9GAj_gqnvfxxSYjQabwYotO2cUr7W3TdQh_07H9OUbl6LpfrZPP-8rpcbBLgVCR5246VqQLJWNEIqetcAaM5k0pmda3qZjxzyYuailqwphU5g5FJ07ZRilM2RfeXt2cZ1d6bHfhjdZJSnaWMxMOF2Hv3PegQq60bvB07VVSIXPKcMcH-AFSAZdw</recordid><startdate>20220520</startdate><enddate>20220520</enddate><creator>Naito, Susumu</creator><creator>Taguchi, Yasunori</creator><creator>Nakata, Kouta</creator><creator>Kato, Yuichi</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220520</creationdate><title>Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder</title><author>Naito, Susumu ; Taguchi, Yasunori ; Nakata, Kouta ; Kato, Yuichi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a526-7ff2332da9338c69eb7da32739d94bbdbc38c5958b26b63cf673ab7d11fcdd523</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Anomalies</topic><topic>Chemical industry</topic><topic>Computer Science - Learning</topic><topic>Multivariate analysis</topic><topic>Time series</topic><topic>Water treatment</topic><toplevel>online_resources</toplevel><creatorcontrib>Naito, Susumu</creatorcontrib><creatorcontrib>Taguchi, Yasunori</creatorcontrib><creatorcontrib>Nakata, Kouta</creatorcontrib><creatorcontrib>Kato, Yuichi</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 (ProQuest)</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>Publicly Available Content Database</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Naito, Susumu</au><au>Taguchi, Yasunori</au><au>Nakata, Kouta</au><au>Kato, Yuichi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder</atitle><jtitle>arXiv.org</jtitle><date>2022-05-20</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need for anomaly detection techniques is increasing in order to reduce the cost of operation and maintenance, in view of a decline in the number of skilled engineers and a shortage of manpower. However, considering the complex behavior of high-dimensional signals and the demand for interpretability, the techniques constitute a major challenge. We introduce a Two-Stage AutoEncoder (TSAE) as an anomaly detection method suitable for such plants. This is a simple autoencoder architecture that makes anomaly detection more interpretable and more accurate, in which based on the premise that plant signals can be separated into two behaviors that have almost no correlation with each other, the signals are separated into long-term and short-term components in a stepwise manner, and the two components are trained independently to improve the inference capability for normal signals. Through experiments on two publicly available datasets of water treatment systems, we have confirmed the high detection performance, the validity of the premise, and that the model behavior was as intended, i.e., the technical effectiveness of TSAE.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2205.09924</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-05 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2205_09924 |
source | arXiv.org; Free E- Journals |
subjects | Anomalies Chemical industry Computer Science - Learning Multivariate analysis Time series Water treatment |
title | Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T08%3A06%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Anomaly%20Detection%20for%20Multivariate%20Time%20Series%20on%20Large-scale%20Fluid%20Handling%20Plant%20Using%20Two-stage%20Autoencoder&rft.jtitle=arXiv.org&rft.au=Naito,%20Susumu&rft.date=2022-05-20&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2205.09924&rft_dat=%3Cproquest_arxiv%3E2667957336%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2667957336&rft_id=info:pmid/&rfr_iscdi=true |