The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning

Manufactured aggregate is a substitute for natural aggregate particles that is formed by mechanically crushing parent rock. Its particle shape has a great impact on the working performance, mechanical performance, and durability for preparing high-performance concrete. Therefore, a particle shape qu...

Full description

Saved in:
Bibliographic Details
Published in:Journal of testing and evaluation 2023-11, Vol.51 (6), p.4476-4492
Main Authors: Zang, Bo, Peng, Xiong, Zhong, Xingu, Zhao, Chao, Zhou, Kun
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-a224t-8e2d2a3b95e67eec0f728205a2c4525ec57acfd4af3444e34d06549f510125853
container_end_page 4492
container_issue 6
container_start_page 4476
container_title Journal of testing and evaluation
container_volume 51
creator Zang, Bo
Peng, Xiong
Zhong, Xingu
Zhao, Chao
Zhou, Kun
description Manufactured aggregate is a substitute for natural aggregate particles that is formed by mechanically crushing parent rock. Its particle shape has a great impact on the working performance, mechanical performance, and durability for preparing high-performance concrete. Therefore, a particle shape quality evaluation method combining deep learning and distance transformation topology is proposed. In this method, the YOLO v4 network is used to locate the particle region, and the centroid point is recognized as the feature point of this region; then, the feature points are used for distance transformation topology to approximately divide the particles area. Based on the divided results, the pixel-level segmentation result is obtained using a local threshold algorithm. The 2–8-mm limestone manufactured aggregate in a 2 million ton (1,000 kg)/year manufactured aggregate production line is carried out to demonstrate the effectiveness of the proposed method, achieving above 90 % precision in the real manufactured aggregate quality evaluation.
doi_str_mv 10.1520/JTE20220529
format article
fullrecord <record><control><sourceid>astm_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1520_JTE20220529</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1520_JTE20220529</sourcerecordid><originalsourceid>FETCH-LOGICAL-a224t-8e2d2a3b95e67eec0f728205a2c4525ec57acfd4af3444e34d06549f510125853</originalsourceid><addsrcrecordid>eNptkM1Lw0AQxRdRsFZP_gN7FCS62Y8me6xt_KJFpPUcpslsuiVNyu5GqBf_dSPtwYOngZnfe7x5hFzH7C5WnN2_LjPOOGeK6xMyiLVUUaKUOCUDxjSLhE7EObnwfsMYS5UWA_K9XCNd2C-kU-uDs6su2LahcwTfOdxiEyg0JV2sYYf0vYPahj3NPqHu4AiGdVvS1tA5NJ2BIvSyko6rymEFAft1QGehpg_g-0MvmSLu6AzBNbapLsmZgdrj1XEOycdjtpw8R7O3p5fJeBYB5zJEKfKSg1hphaMEsWAm4Wn_J_BCKq6wUAkUppRghJQShSzZSEltVMxirlIlhuT24Fu41nuHJt85uwW3z2OW_3aX_-mup28ONPiwzTdt55o-3L_oD9PSbsc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning</title><source>ASTM Journals</source><creator>Zang, Bo ; Peng, Xiong ; Zhong, Xingu ; Zhao, Chao ; Zhou, Kun</creator><contributor>Mitchell, M. R.</contributor><creatorcontrib>Zang, Bo ; Peng, Xiong ; Zhong, Xingu ; Zhao, Chao ; Zhou, Kun ; Mitchell, M. R.</creatorcontrib><description>Manufactured aggregate is a substitute for natural aggregate particles that is formed by mechanically crushing parent rock. Its particle shape has a great impact on the working performance, mechanical performance, and durability for preparing high-performance concrete. Therefore, a particle shape quality evaluation method combining deep learning and distance transformation topology is proposed. In this method, the YOLO v4 network is used to locate the particle region, and the centroid point is recognized as the feature point of this region; then, the feature points are used for distance transformation topology to approximately divide the particles area. Based on the divided results, the pixel-level segmentation result is obtained using a local threshold algorithm. The 2–8-mm limestone manufactured aggregate in a 2 million ton (1,000 kg)/year manufactured aggregate production line is carried out to demonstrate the effectiveness of the proposed method, achieving above 90 % precision in the real manufactured aggregate quality evaluation.</description><identifier>ISSN: 0090-3973</identifier><identifier>EISSN: 1945-7553</identifier><identifier>DOI: 10.1520/JTE20220529</identifier><identifier>CODEN: JTEVAB</identifier><language>eng</language><ispartof>Journal of testing and evaluation, 2023-11, Vol.51 (6), p.4476-4492</ispartof><rights>All rights reserved. This material may not be reproduced or copied, in whole or part, in any printed, mechanical, electronic, film, or other distribution and storage media, without the written consent of the publisher.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-a224t-8e2d2a3b95e67eec0f728205a2c4525ec57acfd4af3444e34d06549f510125853</cites><orcidid>0000-0003-4808-1148</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,9790,27923,27924</link.rule.ids></links><search><contributor>Mitchell, M. R.</contributor><creatorcontrib>Zang, Bo</creatorcontrib><creatorcontrib>Peng, Xiong</creatorcontrib><creatorcontrib>Zhong, Xingu</creatorcontrib><creatorcontrib>Zhao, Chao</creatorcontrib><creatorcontrib>Zhou, Kun</creatorcontrib><title>The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning</title><title>Journal of testing and evaluation</title><description>Manufactured aggregate is a substitute for natural aggregate particles that is formed by mechanically crushing parent rock. Its particle shape has a great impact on the working performance, mechanical performance, and durability for preparing high-performance concrete. Therefore, a particle shape quality evaluation method combining deep learning and distance transformation topology is proposed. In this method, the YOLO v4 network is used to locate the particle region, and the centroid point is recognized as the feature point of this region; then, the feature points are used for distance transformation topology to approximately divide the particles area. Based on the divided results, the pixel-level segmentation result is obtained using a local threshold algorithm. The 2–8-mm limestone manufactured aggregate in a 2 million ton (1,000 kg)/year manufactured aggregate production line is carried out to demonstrate the effectiveness of the proposed method, achieving above 90 % precision in the real manufactured aggregate quality evaluation.</description><issn>0090-3973</issn><issn>1945-7553</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNptkM1Lw0AQxRdRsFZP_gN7FCS62Y8me6xt_KJFpPUcpslsuiVNyu5GqBf_dSPtwYOngZnfe7x5hFzH7C5WnN2_LjPOOGeK6xMyiLVUUaKUOCUDxjSLhE7EObnwfsMYS5UWA_K9XCNd2C-kU-uDs6su2LahcwTfOdxiEyg0JV2sYYf0vYPahj3NPqHu4AiGdVvS1tA5NJ2BIvSyko6rymEFAft1QGehpg_g-0MvmSLu6AzBNbapLsmZgdrj1XEOycdjtpw8R7O3p5fJeBYB5zJEKfKSg1hphaMEsWAm4Wn_J_BCKq6wUAkUppRghJQShSzZSEltVMxirlIlhuT24Fu41nuHJt85uwW3z2OW_3aX_-mup28ONPiwzTdt55o-3L_oD9PSbsc</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Zang, Bo</creator><creator>Peng, Xiong</creator><creator>Zhong, Xingu</creator><creator>Zhao, Chao</creator><creator>Zhou, Kun</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-4808-1148</orcidid></search><sort><creationdate>20231101</creationdate><title>The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning</title><author>Zang, Bo ; Peng, Xiong ; Zhong, Xingu ; Zhao, Chao ; Zhou, Kun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a224t-8e2d2a3b95e67eec0f728205a2c4525ec57acfd4af3444e34d06549f510125853</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zang, Bo</creatorcontrib><creatorcontrib>Peng, Xiong</creatorcontrib><creatorcontrib>Zhong, Xingu</creatorcontrib><creatorcontrib>Zhao, Chao</creatorcontrib><creatorcontrib>Zhou, Kun</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of testing and evaluation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zang, Bo</au><au>Peng, Xiong</au><au>Zhong, Xingu</au><au>Zhao, Chao</au><au>Zhou, Kun</au><au>Mitchell, M. R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning</atitle><jtitle>Journal of testing and evaluation</jtitle><date>2023-11-01</date><risdate>2023</risdate><volume>51</volume><issue>6</issue><spage>4476</spage><epage>4492</epage><pages>4476-4492</pages><issn>0090-3973</issn><eissn>1945-7553</eissn><coden>JTEVAB</coden><abstract>Manufactured aggregate is a substitute for natural aggregate particles that is formed by mechanically crushing parent rock. Its particle shape has a great impact on the working performance, mechanical performance, and durability for preparing high-performance concrete. Therefore, a particle shape quality evaluation method combining deep learning and distance transformation topology is proposed. In this method, the YOLO v4 network is used to locate the particle region, and the centroid point is recognized as the feature point of this region; then, the feature points are used for distance transformation topology to approximately divide the particles area. Based on the divided results, the pixel-level segmentation result is obtained using a local threshold algorithm. The 2–8-mm limestone manufactured aggregate in a 2 million ton (1,000 kg)/year manufactured aggregate production line is carried out to demonstrate the effectiveness of the proposed method, achieving above 90 % precision in the real manufactured aggregate quality evaluation.</abstract><doi>10.1520/JTE20220529</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0003-4808-1148</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0090-3973
ispartof Journal of testing and evaluation, 2023-11, Vol.51 (6), p.4476-4492
issn 0090-3973
1945-7553
language eng
recordid cdi_crossref_primary_10_1520_JTE20220529
source ASTM Journals
title The Size Distribution Measurement and Shape Quality Evaluation Method of Manufactured Aggregate Material Based on Deep Learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T18%3A59%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-astm_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20Size%20Distribution%20Measurement%20and%20Shape%20Quality%20Evaluation%20Method%20of%20Manufactured%20Aggregate%20Material%20Based%20on%20Deep%20Learning&rft.jtitle=Journal%20of%20testing%20and%20evaluation&rft.au=Zang,%20Bo&rft.date=2023-11-01&rft.volume=51&rft.issue=6&rft.spage=4476&rft.epage=4492&rft.pages=4476-4492&rft.issn=0090-3973&rft.eissn=1945-7553&rft.coden=JTEVAB&rft_id=info:doi/10.1520/JTE20220529&rft_dat=%3Castm_cross%3E10_1520_JTE20220529%3C/astm_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a224t-8e2d2a3b95e67eec0f728205a2c4525ec57acfd4af3444e34d06549f510125853%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