Loading…

Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models

This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2021-12, Vol.22 (1), p.160
Main Authors: Zhang, Xuelin, Zhang, Donghao, Leye, Alexander, Scott, Adrian, Visser, Luke, Ge, Zongyuan, Bonnington, Paul
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-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743
cites cdi_FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743
container_end_page
container_issue 1
container_start_page 160
container_title Sensors (Basel, Switzerland)
container_volume 22
creator Zhang, Xuelin
Zhang, Donghao
Leye, Alexander
Scott, Adrian
Visser, Luke
Ge, Zongyuan
Bonnington, Paul
description This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time.
doi_str_mv 10.3390/s22010160
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_65186ba26cbc487b8a3ab53f383890aa</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_65186ba26cbc487b8a3ab53f383890aa</doaj_id><sourcerecordid>2618268997</sourcerecordid><originalsourceid>FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743</originalsourceid><addsrcrecordid>eNpdkUtLxDAUhYMovhf-ASm40cVoXk2TjSDja8DHQl2H5DYdO7TNmLSC_96Mo4MKgVzO_ThczkHogOBTxhQ-i5RigonAa2ibcMpHMgnrv-YttBPjDGPKGJObaIvlGKsC8230cDH0vvOtH2I26aAuXddnl6530Ne-y9J7mqc5-DZpIWYvse6mCXDzbOy7d98MC8402b0vXRP30EZlmuj2v_9d9HJ99Ty-Hd093kzGF3cj4EL1IwEYKlJQynJb5lwpoMSCKIEYnDNRMk4ra6mEwhCLmaVQYcqlLUFxkAVnu2iy9C29mel5qFsTPrQ3tf4SfJhqE_oaGqdFTqSwhgqwwGVhpWHG5qxikkmFjUle50uv-WBbV0JKIJjmj-nfTVe_6ql_1-kQlVOVDI6_DYJ_G1zsdVtHcE1jOpdy1VQQqQihRZHQo3_ozA8h5bekqJBKLaiTJQXBxxhctTqGYL1oXK8aT-zh7-tX5E_F7BO--qXz</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2618268997</pqid></control><display><type>article</type><title>Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models</title><source>Open Access: PubMed Central</source><source>Publicly Available Content Database</source><creator>Zhang, Xuelin ; Zhang, Donghao ; Leye, Alexander ; Scott, Adrian ; Visser, Luke ; Ge, Zongyuan ; Bonnington, Paul</creator><creatorcontrib>Zhang, Xuelin ; Zhang, Donghao ; Leye, Alexander ; Scott, Adrian ; Visser, Luke ; Ge, Zongyuan ; Bonnington, Paul</creatorcontrib><description>This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s22010160</identifier><identifier>PMID: 35009704</identifier><language>eng</language><publisher>Switzerland: MDPI AG</publisher><subject>Accuracy ; Analytical chemistry ; Automation ; Beading ; Cameras ; Chambers ; Chemical industry ; Chemistry ; Computer vision ; Deep learning ; Fault diagnosis ; Flooding ; Frames per second ; machine vision ; Manufacturing ; Neural networks ; Neural Networks, Computer ; object detection ; Offset printing ; Product quality ; Productivity ; Real time ; Sensors ; Spectrometers ; Vision systems ; Vision, Ocular</subject><ispartof>Sensors (Basel, Switzerland), 2021-12, Vol.22 (1), p.160</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743</citedby><cites>FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743</cites><orcidid>0000-0002-5880-8673 ; 0000-0002-9171-6949</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2618268997/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2618268997?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,25753,27924,27925,37012,37013,44590,53791,53793,75126</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35009704$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Xuelin</creatorcontrib><creatorcontrib>Zhang, Donghao</creatorcontrib><creatorcontrib>Leye, Alexander</creatorcontrib><creatorcontrib>Scott, Adrian</creatorcontrib><creatorcontrib>Visser, Luke</creatorcontrib><creatorcontrib>Ge, Zongyuan</creatorcontrib><creatorcontrib>Bonnington, Paul</creatorcontrib><title>Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models</title><title>Sensors (Basel, Switzerland)</title><addtitle>Sensors (Basel)</addtitle><description>This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time.</description><subject>Accuracy</subject><subject>Analytical chemistry</subject><subject>Automation</subject><subject>Beading</subject><subject>Cameras</subject><subject>Chambers</subject><subject>Chemical industry</subject><subject>Chemistry</subject><subject>Computer vision</subject><subject>Deep learning</subject><subject>Fault diagnosis</subject><subject>Flooding</subject><subject>Frames per second</subject><subject>machine vision</subject><subject>Manufacturing</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>object detection</subject><subject>Offset printing</subject><subject>Product quality</subject><subject>Productivity</subject><subject>Real time</subject><subject>Sensors</subject><subject>Spectrometers</subject><subject>Vision systems</subject><subject>Vision, Ocular</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpdkUtLxDAUhYMovhf-ASm40cVoXk2TjSDja8DHQl2H5DYdO7TNmLSC_96Mo4MKgVzO_ThczkHogOBTxhQ-i5RigonAa2ibcMpHMgnrv-YttBPjDGPKGJObaIvlGKsC8230cDH0vvOtH2I26aAuXddnl6530Ne-y9J7mqc5-DZpIWYvse6mCXDzbOy7d98MC8402b0vXRP30EZlmuj2v_9d9HJ99Ty-Hd093kzGF3cj4EL1IwEYKlJQynJb5lwpoMSCKIEYnDNRMk4ra6mEwhCLmaVQYcqlLUFxkAVnu2iy9C29mel5qFsTPrQ3tf4SfJhqE_oaGqdFTqSwhgqwwGVhpWHG5qxikkmFjUle50uv-WBbV0JKIJjmj-nfTVe_6ql_1-kQlVOVDI6_DYJ_G1zsdVtHcE1jOpdy1VQQqQihRZHQo3_ozA8h5bekqJBKLaiTJQXBxxhctTqGYL1oXK8aT-zh7-tX5E_F7BO--qXz</recordid><startdate>20211227</startdate><enddate>20211227</enddate><creator>Zhang, Xuelin</creator><creator>Zhang, Donghao</creator><creator>Leye, Alexander</creator><creator>Scott, Adrian</creator><creator>Visser, Luke</creator><creator>Ge, Zongyuan</creator><creator>Bonnington, Paul</creator><general>MDPI AG</general><general>MDPI</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-5880-8673</orcidid><orcidid>https://orcid.org/0000-0002-9171-6949</orcidid></search><sort><creationdate>20211227</creationdate><title>Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models</title><author>Zhang, Xuelin ; Zhang, Donghao ; Leye, Alexander ; Scott, Adrian ; Visser, Luke ; Ge, Zongyuan ; Bonnington, Paul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Analytical chemistry</topic><topic>Automation</topic><topic>Beading</topic><topic>Cameras</topic><topic>Chambers</topic><topic>Chemical industry</topic><topic>Chemistry</topic><topic>Computer vision</topic><topic>Deep learning</topic><topic>Fault diagnosis</topic><topic>Flooding</topic><topic>Frames per second</topic><topic>machine vision</topic><topic>Manufacturing</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>object detection</topic><topic>Offset printing</topic><topic>Product quality</topic><topic>Productivity</topic><topic>Real time</topic><topic>Sensors</topic><topic>Spectrometers</topic><topic>Vision systems</topic><topic>Vision, Ocular</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Xuelin</creatorcontrib><creatorcontrib>Zhang, Donghao</creatorcontrib><creatorcontrib>Leye, Alexander</creatorcontrib><creatorcontrib>Scott, Adrian</creatorcontrib><creatorcontrib>Visser, Luke</creatorcontrib><creatorcontrib>Ge, Zongyuan</creatorcontrib><creatorcontrib>Bonnington, Paul</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health &amp; Medical Collection (Proquest)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>Medical 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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Directory of Open Access Journals</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Xuelin</au><au>Zhang, Donghao</au><au>Leye, Alexander</au><au>Scott, Adrian</au><au>Visser, Luke</au><au>Ge, Zongyuan</au><au>Bonnington, Paul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><addtitle>Sensors (Basel)</addtitle><date>2021-12-27</date><risdate>2021</risdate><volume>22</volume><issue>1</issue><spage>160</spage><pages>160-</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time.</abstract><cop>Switzerland</cop><pub>MDPI AG</pub><pmid>35009704</pmid><doi>10.3390/s22010160</doi><orcidid>https://orcid.org/0000-0002-5880-8673</orcidid><orcidid>https://orcid.org/0000-0002-9171-6949</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1424-8220
ispartof Sensors (Basel, Switzerland), 2021-12, Vol.22 (1), p.160
issn 1424-8220
1424-8220
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_65186ba26cbc487b8a3ab53f383890aa
source Open Access: PubMed Central; Publicly Available Content Database
subjects Accuracy
Analytical chemistry
Automation
Beading
Cameras
Chambers
Chemical industry
Chemistry
Computer vision
Deep learning
Fault diagnosis
Flooding
Frames per second
machine vision
Manufacturing
Neural networks
Neural Networks, Computer
object detection
Offset printing
Product quality
Productivity
Real time
Sensors
Spectrometers
Vision systems
Vision, Ocular
title Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T21%3A58%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Autonomous%20Incident%20Detection%20on%20Spectrometers%20Using%20Deep%20Convolutional%20Models&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Zhang,%20Xuelin&rft.date=2021-12-27&rft.volume=22&rft.issue=1&rft.spage=160&rft.pages=160-&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s22010160&rft_dat=%3Cproquest_doaj_%3E2618268997%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c469t-6c0cf172235bd5499c21bc6dc1a0536d342fbb28c7a1b03b2cf0248bdc94c8743%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2618268997&rft_id=info:pmid/35009704&rfr_iscdi=true