Loading…

Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes

Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&DR). A novel SFD&DR algorithm with four types of models including...

Full description

Saved in:
Bibliographic Details
Published in:AIChE journal 2019-02, Vol.65 (2), p.629-639
Main Authors: Feng, Jianyuan, Hajizadeh, Iman, Yu, Xia, Rashid, Mudassir, Samadi, Sediqeh, Sevil, Mert, Hobbs, Nicole, Brandt, Rachel, Lazaro, Caterina, Maloney, Zacharie, Littlejohn, Elizabeth, Quinn, Laurie, Cinar, Ali
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-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3
cites cdi_FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3
container_end_page 639
container_issue 2
container_start_page 629
container_title AIChE journal
container_volume 65
creator Feng, Jianyuan
Hajizadeh, Iman
Yu, Xia
Rashid, Mudassir
Samadi, Sediqeh
Sevil, Mert
Hobbs, Nicole
Brandt, Rachel
Lazaro, Caterina
Maloney, Zacharie
Littlejohn, Elizabeth
Quinn, Laurie
Cinar, Ali
description Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&DR). A novel SFD&DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor‐based subspace identification, and approximate linear dependency‐based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose‐insulin metabolism has time‐varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model‐estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019
doi_str_mv 10.1002/aic.16435
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6707739</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2164584838</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3</originalsourceid><addsrcrecordid>eNp1kcFKHDEcxkOp1NX20BcoAS_tYTTJJJOsh8Ky1FZQvLTn8J8ko5HsxCYzle2pj9Bn9EnMOqtYoaeQLz9-fOFD6D0lh5QQdgTeHNKG1-IVmlHBZSXmRLxGM0IIrUpAd9FeztflxqRib9BuTTmXXMkZ-n0-hsHf_fm7itYFnF2fY8IdlBRbNzgz-Nhj6C22MABOzsTe-OBhkx_jBTaQHc7DaNf41g9X-DKMJpZow7l-SA_g1ptxV-TWQ1vM-S3a6SBk92577qMfJ1--L79VZxdfT5eLs8pwRUTViUYaUgvZig4aO6eKdMBaZstdNZw3LQUmQSjOiWxJ56iVhhkAxZnidVvvo8-T92ZsV85OrYK-SX4Faa0jeP3vS--v9GX8pRtJpKznRfBxK0jx5-jyoFc-GxcC9C6OWTNWevJ5w5qCHrxAr-OY-vI9zcpCpaSqVaE-TZRJMefkuqcylOjNorosqh8WLeyH5-2fyMcJC3A0Abc-uPX_TXpxupyU9ySkrdI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2164584838</pqid></control><display><type>article</type><title>Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes</title><source>Wiley-Blackwell Read &amp; Publish Collection</source><creator>Feng, Jianyuan ; Hajizadeh, Iman ; Yu, Xia ; Rashid, Mudassir ; Samadi, Sediqeh ; Sevil, Mert ; Hobbs, Nicole ; Brandt, Rachel ; Lazaro, Caterina ; Maloney, Zacharie ; Littlejohn, Elizabeth ; Quinn, Laurie ; Cinar, Ali</creator><creatorcontrib>Feng, Jianyuan ; Hajizadeh, Iman ; Yu, Xia ; Rashid, Mudassir ; Samadi, Sediqeh ; Sevil, Mert ; Hobbs, Nicole ; Brandt, Rachel ; Lazaro, Caterina ; Maloney, Zacharie ; Littlejohn, Elizabeth ; Quinn, Laurie ; Cinar, Ali</creatorcontrib><description>Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&amp;DR). A novel SFD&amp;DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor‐based subspace identification, and approximate linear dependency‐based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&amp;DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose‐insulin metabolism has time‐varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&amp;DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model‐estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019</description><identifier>ISSN: 0001-1541</identifier><identifier>EISSN: 1547-5905</identifier><identifier>DOI: 10.1002/aic.16435</identifier><identifier>PMID: 31447487</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley &amp; Sons, Inc</publisher><subject>Algorithms ; artificial neural network ; Artificial neural networks ; Case studies ; data reconciliation ; Dependence ; Diabetes ; Diabetes mellitus ; Fault detection ; Fault diagnosis ; Glucose ; Glucose metabolism ; Identification methods ; Information processing ; Insulin ; Kalman filter ; Kalman filters ; kernel filter ; Least squares ; Metabolism ; Neural networks ; Organic chemistry ; Outliers (statistics) ; Pancreas ; partial least squares ; Sensors ; subspace identification</subject><ispartof>AIChE journal, 2019-02, Vol.65 (2), p.629-639</ispartof><rights>2018 American Institute of Chemical Engineers</rights><rights>2019 American Institute of Chemical Engineers</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3</citedby><cites>FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3</cites><orcidid>0000-0002-1607-9943</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31447487$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Feng, Jianyuan</creatorcontrib><creatorcontrib>Hajizadeh, Iman</creatorcontrib><creatorcontrib>Yu, Xia</creatorcontrib><creatorcontrib>Rashid, Mudassir</creatorcontrib><creatorcontrib>Samadi, Sediqeh</creatorcontrib><creatorcontrib>Sevil, Mert</creatorcontrib><creatorcontrib>Hobbs, Nicole</creatorcontrib><creatorcontrib>Brandt, Rachel</creatorcontrib><creatorcontrib>Lazaro, Caterina</creatorcontrib><creatorcontrib>Maloney, Zacharie</creatorcontrib><creatorcontrib>Littlejohn, Elizabeth</creatorcontrib><creatorcontrib>Quinn, Laurie</creatorcontrib><creatorcontrib>Cinar, Ali</creatorcontrib><title>Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes</title><title>AIChE journal</title><addtitle>AIChE J</addtitle><description>Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&amp;DR). A novel SFD&amp;DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor‐based subspace identification, and approximate linear dependency‐based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&amp;DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose‐insulin metabolism has time‐varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&amp;DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model‐estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019</description><subject>Algorithms</subject><subject>artificial neural network</subject><subject>Artificial neural networks</subject><subject>Case studies</subject><subject>data reconciliation</subject><subject>Dependence</subject><subject>Diabetes</subject><subject>Diabetes mellitus</subject><subject>Fault detection</subject><subject>Fault diagnosis</subject><subject>Glucose</subject><subject>Glucose metabolism</subject><subject>Identification methods</subject><subject>Information processing</subject><subject>Insulin</subject><subject>Kalman filter</subject><subject>Kalman filters</subject><subject>kernel filter</subject><subject>Least squares</subject><subject>Metabolism</subject><subject>Neural networks</subject><subject>Organic chemistry</subject><subject>Outliers (statistics)</subject><subject>Pancreas</subject><subject>partial least squares</subject><subject>Sensors</subject><subject>subspace identification</subject><issn>0001-1541</issn><issn>1547-5905</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kcFKHDEcxkOp1NX20BcoAS_tYTTJJJOsh8Ky1FZQvLTn8J8ko5HsxCYzle2pj9Bn9EnMOqtYoaeQLz9-fOFD6D0lh5QQdgTeHNKG1-IVmlHBZSXmRLxGM0IIrUpAd9FeztflxqRib9BuTTmXXMkZ-n0-hsHf_fm7itYFnF2fY8IdlBRbNzgz-Nhj6C22MABOzsTe-OBhkx_jBTaQHc7DaNf41g9X-DKMJpZow7l-SA_g1ptxV-TWQ1vM-S3a6SBk92577qMfJ1--L79VZxdfT5eLs8pwRUTViUYaUgvZig4aO6eKdMBaZstdNZw3LQUmQSjOiWxJ56iVhhkAxZnidVvvo8-T92ZsV85OrYK-SX4Faa0jeP3vS--v9GX8pRtJpKznRfBxK0jx5-jyoFc-GxcC9C6OWTNWevJ5w5qCHrxAr-OY-vI9zcpCpaSqVaE-TZRJMefkuqcylOjNorosqh8WLeyH5-2fyMcJC3A0Abc-uPX_TXpxupyU9ySkrdI</recordid><startdate>201902</startdate><enddate>201902</enddate><creator>Feng, Jianyuan</creator><creator>Hajizadeh, Iman</creator><creator>Yu, Xia</creator><creator>Rashid, Mudassir</creator><creator>Samadi, Sediqeh</creator><creator>Sevil, Mert</creator><creator>Hobbs, Nicole</creator><creator>Brandt, Rachel</creator><creator>Lazaro, Caterina</creator><creator>Maloney, Zacharie</creator><creator>Littlejohn, Elizabeth</creator><creator>Quinn, Laurie</creator><creator>Cinar, Ali</creator><general>John Wiley &amp; Sons, Inc</general><general>American Institute of Chemical Engineers</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7ST</scope><scope>7U5</scope><scope>8FD</scope><scope>C1K</scope><scope>L7M</scope><scope>SOI</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-1607-9943</orcidid></search><sort><creationdate>201902</creationdate><title>Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes</title><author>Feng, Jianyuan ; Hajizadeh, Iman ; Yu, Xia ; Rashid, Mudassir ; Samadi, Sediqeh ; Sevil, Mert ; Hobbs, Nicole ; Brandt, Rachel ; Lazaro, Caterina ; Maloney, Zacharie ; Littlejohn, Elizabeth ; Quinn, Laurie ; Cinar, Ali</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>artificial neural network</topic><topic>Artificial neural networks</topic><topic>Case studies</topic><topic>data reconciliation</topic><topic>Dependence</topic><topic>Diabetes</topic><topic>Diabetes mellitus</topic><topic>Fault detection</topic><topic>Fault diagnosis</topic><topic>Glucose</topic><topic>Glucose metabolism</topic><topic>Identification methods</topic><topic>Information processing</topic><topic>Insulin</topic><topic>Kalman filter</topic><topic>Kalman filters</topic><topic>kernel filter</topic><topic>Least squares</topic><topic>Metabolism</topic><topic>Neural networks</topic><topic>Organic chemistry</topic><topic>Outliers (statistics)</topic><topic>Pancreas</topic><topic>partial least squares</topic><topic>Sensors</topic><topic>subspace identification</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Feng, Jianyuan</creatorcontrib><creatorcontrib>Hajizadeh, Iman</creatorcontrib><creatorcontrib>Yu, Xia</creatorcontrib><creatorcontrib>Rashid, Mudassir</creatorcontrib><creatorcontrib>Samadi, Sediqeh</creatorcontrib><creatorcontrib>Sevil, Mert</creatorcontrib><creatorcontrib>Hobbs, Nicole</creatorcontrib><creatorcontrib>Brandt, Rachel</creatorcontrib><creatorcontrib>Lazaro, Caterina</creatorcontrib><creatorcontrib>Maloney, Zacharie</creatorcontrib><creatorcontrib>Littlejohn, Elizabeth</creatorcontrib><creatorcontrib>Quinn, Laurie</creatorcontrib><creatorcontrib>Cinar, Ali</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Environment Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Environment Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>AIChE journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Feng, Jianyuan</au><au>Hajizadeh, Iman</au><au>Yu, Xia</au><au>Rashid, Mudassir</au><au>Samadi, Sediqeh</au><au>Sevil, Mert</au><au>Hobbs, Nicole</au><au>Brandt, Rachel</au><au>Lazaro, Caterina</au><au>Maloney, Zacharie</au><au>Littlejohn, Elizabeth</au><au>Quinn, Laurie</au><au>Cinar, Ali</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes</atitle><jtitle>AIChE journal</jtitle><addtitle>AIChE J</addtitle><date>2019-02</date><risdate>2019</risdate><volume>65</volume><issue>2</issue><spage>629</spage><epage>639</epage><pages>629-639</pages><issn>0001-1541</issn><eissn>1547-5905</eissn><abstract>Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&amp;DR). A novel SFD&amp;DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor‐based subspace identification, and approximate linear dependency‐based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&amp;DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose‐insulin metabolism has time‐varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&amp;DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model‐estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019</abstract><cop>Hoboken, USA</cop><pub>John Wiley &amp; Sons, Inc</pub><pmid>31447487</pmid><doi>10.1002/aic.16435</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-1607-9943</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0001-1541
ispartof AIChE journal, 2019-02, Vol.65 (2), p.629-639
issn 0001-1541
1547-5905
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6707739
source Wiley-Blackwell Read & Publish Collection
subjects Algorithms
artificial neural network
Artificial neural networks
Case studies
data reconciliation
Dependence
Diabetes
Diabetes mellitus
Fault detection
Fault diagnosis
Glucose
Glucose metabolism
Identification methods
Information processing
Insulin
Kalman filter
Kalman filters
kernel filter
Least squares
Metabolism
Neural networks
Organic chemistry
Outliers (statistics)
Pancreas
partial least squares
Sensors
subspace identification
title Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T10%3A11%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi%E2%80%90model%20sensor%20fault%20detection%20and%20data%20reconciliation:%20A%20case%20study%20with%20glucose%20concentration%20sensors%20for%20diabetes&rft.jtitle=AIChE%20journal&rft.au=Feng,%20Jianyuan&rft.date=2019-02&rft.volume=65&rft.issue=2&rft.spage=629&rft.epage=639&rft.pages=629-639&rft.issn=0001-1541&rft.eissn=1547-5905&rft_id=info:doi/10.1002/aic.16435&rft_dat=%3Cproquest_pubme%3E2164584838%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c4805-f567c0357b5fa6d9180fa2b2db5f86446b1a27a584407b0fe1d7c2caa842843b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2164584838&rft_id=info:pmid/31447487&rfr_iscdi=true