Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems

The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. The proposal integrates a centroid-based approach with the real-time identification technique Recursive Least Squares. In order to find anomalies, the approach...

Full description

Saved in:
Bibliographic Details
Published in:Logic journal of the IGPL 2024-05
Main Authors: Michelena, Álvaro, Zayas-Gato, Francisco, Jove, Esteban, Casteleiro-Roca, José-Luis, Quintián, Héctor, Fontenla-Romero, Óscar, Luis Calvo-Rolle, José
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c164t-38b6cc6ee2518a213de3ff1c860a7ae6441a4b8362c18670a43b394c670ed08a3
container_end_page
container_issue
container_start_page
container_title Logic journal of the IGPL
container_volume
creator Michelena, Álvaro
Zayas-Gato, Francisco
Jove, Esteban
Casteleiro-Roca, José-Luis
Quintián, Héctor
Fontenla-Romero, Óscar
Luis Calvo-Rolle, José
description The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. The proposal integrates a centroid-based approach with the real-time identification technique Recursive Least Squares. In order to find anomalies, the approach compares the present system dynamics with the average (centroid) of the dynamics found in earlier states for a given setpoint. The system labels the dynamics difference as an anomaly if it rises over a determinate threshold. To validate the proposal, two different datasets obtained from a level control plant operation have been used, to which anomalies have been artificially added. The results shown have determined a satisfactory performance of the method, especially in those processes with low noise.
doi_str_mv 10.1093/jigpal/jzae070
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1093_jigpal_jzae070</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1093_jigpal_jzae070</sourcerecordid><originalsourceid>FETCH-LOGICAL-c164t-38b6cc6ee2518a213de3ff1c860a7ae6441a4b8362c18670a43b394c670ed08a3</originalsourceid><addsrcrecordid>eNotkF1LwzAYhYMoOKe3XucPdEuaLE0vZfgFQ2_01vIueTsz2qQksVB_vZvb1XngwOHwEHLP2YKzWiz3bjdAt9z_ArKKXZAZF0oXta7l5T9XBatW_JrcpLRnjEldrmbk6y2M2FGwMGQ3IoVhiAHMN21DpOBDD91ELWY02QVPnac--M55hGNtaXY9FiPEyfndobU_KUcHHU1TytinW3LVQpfw7pxz8vn0-LF-KTbvz6_rh01huJK5EHqrjFGI5YprKLmwKNqWG60YVIBKSg5yq4UqDdeqYiDFVtTSHBAt0yDmZHHaNTGkFLFthuj6w62Gs-ZopznZac52xB9Cm10O</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems</title><source>Oxford Journals Online</source><creator>Michelena, Álvaro ; Zayas-Gato, Francisco ; Jove, Esteban ; Casteleiro-Roca, José-Luis ; Quintián, Héctor ; Fontenla-Romero, Óscar ; Luis Calvo-Rolle, José</creator><creatorcontrib>Michelena, Álvaro ; Zayas-Gato, Francisco ; Jove, Esteban ; Casteleiro-Roca, José-Luis ; Quintián, Héctor ; Fontenla-Romero, Óscar ; Luis Calvo-Rolle, José</creatorcontrib><description>The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. The proposal integrates a centroid-based approach with the real-time identification technique Recursive Least Squares. In order to find anomalies, the approach compares the present system dynamics with the average (centroid) of the dynamics found in earlier states for a given setpoint. The system labels the dynamics difference as an anomaly if it rises over a determinate threshold. To validate the proposal, two different datasets obtained from a level control plant operation have been used, to which anomalies have been artificially added. The results shown have determined a satisfactory performance of the method, especially in those processes with low noise.</description><identifier>ISSN: 1367-0751</identifier><identifier>EISSN: 1368-9894</identifier><identifier>DOI: 10.1093/jigpal/jzae070</identifier><language>eng</language><ispartof>Logic journal of the IGPL, 2024-05</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c164t-38b6cc6ee2518a213de3ff1c860a7ae6441a4b8362c18670a43b394c670ed08a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids></links><search><creatorcontrib>Michelena, Álvaro</creatorcontrib><creatorcontrib>Zayas-Gato, Francisco</creatorcontrib><creatorcontrib>Jove, Esteban</creatorcontrib><creatorcontrib>Casteleiro-Roca, José-Luis</creatorcontrib><creatorcontrib>Quintián, Héctor</creatorcontrib><creatorcontrib>Fontenla-Romero, Óscar</creatorcontrib><creatorcontrib>Luis Calvo-Rolle, José</creatorcontrib><title>Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems</title><title>Logic journal of the IGPL</title><description>The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. The proposal integrates a centroid-based approach with the real-time identification technique Recursive Least Squares. In order to find anomalies, the approach compares the present system dynamics with the average (centroid) of the dynamics found in earlier states for a given setpoint. The system labels the dynamics difference as an anomaly if it rises over a determinate threshold. To validate the proposal, two different datasets obtained from a level control plant operation have been used, to which anomalies have been artificially added. The results shown have determined a satisfactory performance of the method, especially in those processes with low noise.</description><issn>1367-0751</issn><issn>1368-9894</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNotkF1LwzAYhYMoOKe3XucPdEuaLE0vZfgFQ2_01vIueTsz2qQksVB_vZvb1XngwOHwEHLP2YKzWiz3bjdAt9z_ArKKXZAZF0oXta7l5T9XBatW_JrcpLRnjEldrmbk6y2M2FGwMGQ3IoVhiAHMN21DpOBDD91ELWY02QVPnac--M55hGNtaXY9FiPEyfndobU_KUcHHU1TytinW3LVQpfw7pxz8vn0-LF-KTbvz6_rh01huJK5EHqrjFGI5YprKLmwKNqWG60YVIBKSg5yq4UqDdeqYiDFVtTSHBAt0yDmZHHaNTGkFLFthuj6w62Gs-ZopznZac52xB9Cm10O</recordid><startdate>20240514</startdate><enddate>20240514</enddate><creator>Michelena, Álvaro</creator><creator>Zayas-Gato, Francisco</creator><creator>Jove, Esteban</creator><creator>Casteleiro-Roca, José-Luis</creator><creator>Quintián, Héctor</creator><creator>Fontenla-Romero, Óscar</creator><creator>Luis Calvo-Rolle, José</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240514</creationdate><title>Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems</title><author>Michelena, Álvaro ; Zayas-Gato, Francisco ; Jove, Esteban ; Casteleiro-Roca, José-Luis ; Quintián, Héctor ; Fontenla-Romero, Óscar ; Luis Calvo-Rolle, José</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c164t-38b6cc6ee2518a213de3ff1c860a7ae6441a4b8362c18670a43b394c670ed08a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Michelena, Álvaro</creatorcontrib><creatorcontrib>Zayas-Gato, Francisco</creatorcontrib><creatorcontrib>Jove, Esteban</creatorcontrib><creatorcontrib>Casteleiro-Roca, José-Luis</creatorcontrib><creatorcontrib>Quintián, Héctor</creatorcontrib><creatorcontrib>Fontenla-Romero, Óscar</creatorcontrib><creatorcontrib>Luis Calvo-Rolle, José</creatorcontrib><collection>CrossRef</collection><jtitle>Logic journal of the IGPL</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Michelena, Álvaro</au><au>Zayas-Gato, Francisco</au><au>Jove, Esteban</au><au>Casteleiro-Roca, José-Luis</au><au>Quintián, Héctor</au><au>Fontenla-Romero, Óscar</au><au>Luis Calvo-Rolle, José</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems</atitle><jtitle>Logic journal of the IGPL</jtitle><date>2024-05-14</date><risdate>2024</risdate><issn>1367-0751</issn><eissn>1368-9894</eissn><abstract>The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. The proposal integrates a centroid-based approach with the real-time identification technique Recursive Least Squares. In order to find anomalies, the approach compares the present system dynamics with the average (centroid) of the dynamics found in earlier states for a given setpoint. The system labels the dynamics difference as an anomaly if it rises over a determinate threshold. To validate the proposal, two different datasets obtained from a level control plant operation have been used, to which anomalies have been artificially added. The results shown have determined a satisfactory performance of the method, especially in those processes with low noise.</abstract><doi>10.1093/jigpal/jzae070</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1367-0751
ispartof Logic journal of the IGPL, 2024-05
issn 1367-0751
1368-9894
language eng
recordid cdi_crossref_primary_10_1093_jigpal_jzae070
source Oxford Journals Online
title Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T15%3A02%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Novel%20adaptive%20approach%20for%20anomaly%20detection%20in%20nonlinear%20and%20time-varying%20industrial%20systems&rft.jtitle=Logic%20journal%20of%20the%20IGPL&rft.au=Michelena,%20%C3%81lvaro&rft.date=2024-05-14&rft.issn=1367-0751&rft.eissn=1368-9894&rft_id=info:doi/10.1093/jigpal/jzae070&rft_dat=%3Ccrossref%3E10_1093_jigpal_jzae070%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c164t-38b6cc6ee2518a213de3ff1c860a7ae6441a4b8362c18670a43b394c670ed08a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true