Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning

This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-08
Hauptverfasser: Surina, Gabriel, Georgalis, Georgios, Aphale, Siddhant S, Patra, Abani, DesJardin, Paul E
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 Surina, Gabriel
Georgalis, Georgios
Aphale, Siddhant S
Patra, Abani
DesJardin, Paul E
description This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel regression rates. A DSLR camera with a high intensity flash is used to capture images throughout the burn and the images are then used to find the fuel boundary to calculate the regression rate. A U-net convolutional neural network architecture is explored to segment the fuel from the experimental images. A Monte-Carlo Dropout process is used to quantify the regression rate uncertainty produced from the network. The U-net computed regression rates are compared with values from other techniques from literature and show error less than 10%. An oxidizer flux dependency study is performed and shows the U-net predictions of regression rates are accurate and independent of the oxidizer flux, when the images in the training set are not over-saturated. Training with monochrome images is explored and is not successful at predicting the fuel regression rate from images with high noise. The network is superior at filtering out noise introduced by soot, pitting, and wax deposition on the chamber glass as well as the flame when compared to traditional image processing techniques, such as threshold binary conversion and spatial filtering. U-net consistently provides low error image segmentations to allow accurate computation of the regression rate of the fuel.
doi_str_mv 10.48550/arxiv.2108.11276
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2108_11276</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2564690473</sourcerecordid><originalsourceid>FETCH-LOGICAL-a523-e14ebc759fe4f98c0432f37c52a2f12fadbaf963107cc709aff8efd605ccf18d3</originalsourceid><addsrcrecordid>eNotkNFLwzAYxIMgOOb-AJ8M-NyZfEma9lGnc8JE2PYqJU2_jM6umUkr7r-3bj4dPziOuyPkhrOpzJRi9yb81N9T4Cybcg46vSAjEIInmQS4IpMYd4wxSDUoJUbk4w1N7APuse2od3RxLENd0ZW3n9jRtW8GmPfY0BVuA8ZY-5auTIfU-UANXTempI99aDHQPtbtlj4hHugSTWgHuiaXzjQRJ_86Jpv582a2SJbvL6-zh2ViFIgEucTSapU7lC7PLJMCnNBWgQHHwZmqNC5PBWfaWs1y41yGrkqZstbxrBJjcnuOPW0vDqHem3As_j4oTh8Mjruz4xD8V4-xK3Z-aD10KkClMs2Z1EL8AnHNX24</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2564690473</pqid></control><display><type>article</type><title>Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Surina, Gabriel ; Georgalis, Georgios ; Aphale, Siddhant S ; Patra, Abani ; DesJardin, Paul E</creator><creatorcontrib>Surina, Gabriel ; Georgalis, Georgios ; Aphale, Siddhant S ; Patra, Abani ; DesJardin, Paul E</creatorcontrib><description>This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel regression rates. A DSLR camera with a high intensity flash is used to capture images throughout the burn and the images are then used to find the fuel boundary to calculate the regression rate. A U-net convolutional neural network architecture is explored to segment the fuel from the experimental images. A Monte-Carlo Dropout process is used to quantify the regression rate uncertainty produced from the network. The U-net computed regression rates are compared with values from other techniques from literature and show error less than 10%. An oxidizer flux dependency study is performed and shows the U-net predictions of regression rates are accurate and independent of the oxidizer flux, when the images in the training set are not over-saturated. Training with monochrome images is explored and is not successful at predicting the fuel regression rate from images with high noise. The network is superior at filtering out noise introduced by soot, pitting, and wax deposition on the chamber glass as well as the flame when compared to traditional image processing techniques, such as threshold binary conversion and spatial filtering. U-net consistently provides low error image segmentations to allow accurate computation of the regression rate of the fuel.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2108.11276</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Boundary layer combustion ; Computer architecture ; Computer Science - Computer Vision and Pattern Recognition ; Deep learning ; Fuel regression ; Image processing ; Monte Carlo simulation ; Noise prediction ; Oxidizing agents ; Rocket propellants ; Rockets ; Solid fuels ; Soot ; Spatial filtering ; Training</subject><ispartof>arXiv.org, 2021-08</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2108.11276$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1016/j.actaastro.2021.09.046$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Surina, Gabriel</creatorcontrib><creatorcontrib>Georgalis, Georgios</creatorcontrib><creatorcontrib>Aphale, Siddhant S</creatorcontrib><creatorcontrib>Patra, Abani</creatorcontrib><creatorcontrib>DesJardin, Paul E</creatorcontrib><title>Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning</title><title>arXiv.org</title><description>This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel regression rates. A DSLR camera with a high intensity flash is used to capture images throughout the burn and the images are then used to find the fuel boundary to calculate the regression rate. A U-net convolutional neural network architecture is explored to segment the fuel from the experimental images. A Monte-Carlo Dropout process is used to quantify the regression rate uncertainty produced from the network. The U-net computed regression rates are compared with values from other techniques from literature and show error less than 10%. An oxidizer flux dependency study is performed and shows the U-net predictions of regression rates are accurate and independent of the oxidizer flux, when the images in the training set are not over-saturated. Training with monochrome images is explored and is not successful at predicting the fuel regression rate from images with high noise. The network is superior at filtering out noise introduced by soot, pitting, and wax deposition on the chamber glass as well as the flame when compared to traditional image processing techniques, such as threshold binary conversion and spatial filtering. U-net consistently provides low error image segmentations to allow accurate computation of the regression rate of the fuel.</description><subject>Artificial neural networks</subject><subject>Boundary layer combustion</subject><subject>Computer architecture</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Deep learning</subject><subject>Fuel regression</subject><subject>Image processing</subject><subject>Monte Carlo simulation</subject><subject>Noise prediction</subject><subject>Oxidizing agents</subject><subject>Rocket propellants</subject><subject>Rockets</subject><subject>Solid fuels</subject><subject>Soot</subject><subject>Spatial filtering</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotkNFLwzAYxIMgOOb-AJ8M-NyZfEma9lGnc8JE2PYqJU2_jM6umUkr7r-3bj4dPziOuyPkhrOpzJRi9yb81N9T4Cybcg46vSAjEIInmQS4IpMYd4wxSDUoJUbk4w1N7APuse2od3RxLENd0ZW3n9jRtW8GmPfY0BVuA8ZY-5auTIfU-UANXTempI99aDHQPtbtlj4hHugSTWgHuiaXzjQRJ_86Jpv582a2SJbvL6-zh2ViFIgEucTSapU7lC7PLJMCnNBWgQHHwZmqNC5PBWfaWs1y41yGrkqZstbxrBJjcnuOPW0vDqHem3As_j4oTh8Mjruz4xD8V4-xK3Z-aD10KkClMs2Z1EL8AnHNX24</recordid><startdate>20210825</startdate><enddate>20210825</enddate><creator>Surina, Gabriel</creator><creator>Georgalis, Georgios</creator><creator>Aphale, Siddhant S</creator><creator>Patra, Abani</creator><creator>DesJardin, Paul E</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>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210825</creationdate><title>Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning</title><author>Surina, Gabriel ; Georgalis, Georgios ; Aphale, Siddhant S ; Patra, Abani ; DesJardin, Paul E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a523-e14ebc759fe4f98c0432f37c52a2f12fadbaf963107cc709aff8efd605ccf18d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Artificial neural networks</topic><topic>Boundary layer combustion</topic><topic>Computer architecture</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Deep learning</topic><topic>Fuel regression</topic><topic>Image processing</topic><topic>Monte Carlo simulation</topic><topic>Noise prediction</topic><topic>Oxidizing agents</topic><topic>Rocket propellants</topic><topic>Rockets</topic><topic>Solid fuels</topic><topic>Soot</topic><topic>Spatial filtering</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Surina, Gabriel</creatorcontrib><creatorcontrib>Georgalis, Georgios</creatorcontrib><creatorcontrib>Aphale, Siddhant S</creatorcontrib><creatorcontrib>Patra, Abani</creatorcontrib><creatorcontrib>DesJardin, Paul E</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; 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>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>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>Surina, Gabriel</au><au>Georgalis, Georgios</au><au>Aphale, Siddhant S</au><au>Patra, Abani</au><au>DesJardin, Paul E</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning</atitle><jtitle>arXiv.org</jtitle><date>2021-08-25</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel regression rates. A DSLR camera with a high intensity flash is used to capture images throughout the burn and the images are then used to find the fuel boundary to calculate the regression rate. A U-net convolutional neural network architecture is explored to segment the fuel from the experimental images. A Monte-Carlo Dropout process is used to quantify the regression rate uncertainty produced from the network. The U-net computed regression rates are compared with values from other techniques from literature and show error less than 10%. An oxidizer flux dependency study is performed and shows the U-net predictions of regression rates are accurate and independent of the oxidizer flux, when the images in the training set are not over-saturated. Training with monochrome images is explored and is not successful at predicting the fuel regression rate from images with high noise. The network is superior at filtering out noise introduced by soot, pitting, and wax deposition on the chamber glass as well as the flame when compared to traditional image processing techniques, such as threshold binary conversion and spatial filtering. U-net consistently provides low error image segmentations to allow accurate computation of the regression rate of the fuel.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2108.11276</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-08
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2108_11276
source arXiv.org; Free E- Journals
subjects Artificial neural networks
Boundary layer combustion
Computer architecture
Computer Science - Computer Vision and Pattern Recognition
Deep learning
Fuel regression
Image processing
Monte Carlo simulation
Noise prediction
Oxidizing agents
Rocket propellants
Rockets
Solid fuels
Soot
Spatial filtering
Training
title Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T20%3A47%3A03IST&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=Measurement%20of%20Hybrid%20Rocket%20Solid%20Fuel%20Regression%20Rate%20for%20a%20Slab%20Burner%20using%20Deep%20Learning&rft.jtitle=arXiv.org&rft.au=Surina,%20Gabriel&rft.date=2021-08-25&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2108.11276&rft_dat=%3Cproquest_arxiv%3E2564690473%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=2564690473&rft_id=info:pmid/&rfr_iscdi=true