Yong Ding , Dewen Liu , Yu Jiang , Hongying Cai , Zixiang Zhou , Jianxiong Zhang , Yongbing Sun , Danna Ma
{"title":"一种利用三维扫描和监督学习表征和预测混凝土骨料形态特征的方法","authors":"Yong Ding , Dewen Liu , Yu Jiang , Hongying Cai , Zixiang Zhou , Jianxiong Zhang , Yongbing Sun , Danna Ma","doi":"10.1016/j.conbuildmat.2025.141613","DOIUrl":null,"url":null,"abstract":"<div><div>To achieve refined analysis of intrinsic geometric characteristics of concrete coarse aggregates (CA), this study develops a rapid, accurate testing method. Leveraging advanced three-dimensional (3D) scanning technology, an in-depth investigation into geometric morphological features of concrete CA was conducted. An innovative indicator, \"equivalent particle size (<em>D</em>)\" was introduced to characterize the 3D attributes of aggregates. MATLAB was utilized for comprehensive secondary development to analyze geometric features and compute fractal dimensions (i.e. gradation, surface area, and roughness). The fractal dimension of gradation reflects particle size distribution complexity; the fractal dimension of surface area quantifies texture irregularity; the fractal dimension of roughness describes contour variation. A predictive framework integrating \"3D scanning, secondary development and supervised learning\" was established for accurate estimation of <em>D</em>. Results show superior precision in predicting both total mass (<em>M</em>) and <em>D</em>, and the average prediction error (APE) of <em>D</em> was significantly reduced to 1.78 %. Two-dimensional (2D) indicators dominate <em>M</em> prediction, while 3D indicators are more suitable for predicting <em>D</em>. The proposed prediction model not only provides an efficient and precise solution for concrete aggregate screening but also establishes a theoretical and technical foundation for future optimization design of concrete aggregates. This work highlights the potential and advantages of combining 3D scanning with machine learning.</div></div>","PeriodicalId":288,"journal":{"name":"Construction and Building Materials","volume":"482 ","pages":"Article 141613"},"PeriodicalIF":8.0000,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A method for characterizing and predicting the morphological features of concrete aggregates using 3D scanning and supervised learning\",\"authors\":\"Yong Ding , Dewen Liu , Yu Jiang , Hongying Cai , Zixiang Zhou , Jianxiong Zhang , Yongbing Sun , Danna Ma\",\"doi\":\"10.1016/j.conbuildmat.2025.141613\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>To achieve refined analysis of intrinsic geometric characteristics of concrete coarse aggregates (CA), this study develops a rapid, accurate testing method. Leveraging advanced three-dimensional (3D) scanning technology, an in-depth investigation into geometric morphological features of concrete CA was conducted. An innovative indicator, \\\"equivalent particle size (<em>D</em>)\\\" was introduced to characterize the 3D attributes of aggregates. MATLAB was utilized for comprehensive secondary development to analyze geometric features and compute fractal dimensions (i.e. gradation, surface area, and roughness). The fractal dimension of gradation reflects particle size distribution complexity; the fractal dimension of surface area quantifies texture irregularity; the fractal dimension of roughness describes contour variation. A predictive framework integrating \\\"3D scanning, secondary development and supervised learning\\\" was established for accurate estimation of <em>D</em>. Results show superior precision in predicting both total mass (<em>M</em>) and <em>D</em>, and the average prediction error (APE) of <em>D</em> was significantly reduced to 1.78 %. Two-dimensional (2D) indicators dominate <em>M</em> prediction, while 3D indicators are more suitable for predicting <em>D</em>. The proposed prediction model not only provides an efficient and precise solution for concrete aggregate screening but also establishes a theoretical and technical foundation for future optimization design of concrete aggregates. This work highlights the potential and advantages of combining 3D scanning with machine learning.</div></div>\",\"PeriodicalId\":288,\"journal\":{\"name\":\"Construction and Building Materials\",\"volume\":\"482 \",\"pages\":\"Article 141613\"},\"PeriodicalIF\":8.0000,\"publicationDate\":\"2025-05-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Construction and Building Materials\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0950061825017635\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CONSTRUCTION & BUILDING TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Construction and Building Materials","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950061825017635","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
A method for characterizing and predicting the morphological features of concrete aggregates using 3D scanning and supervised learning
To achieve refined analysis of intrinsic geometric characteristics of concrete coarse aggregates (CA), this study develops a rapid, accurate testing method. Leveraging advanced three-dimensional (3D) scanning technology, an in-depth investigation into geometric morphological features of concrete CA was conducted. An innovative indicator, "equivalent particle size (D)" was introduced to characterize the 3D attributes of aggregates. MATLAB was utilized for comprehensive secondary development to analyze geometric features and compute fractal dimensions (i.e. gradation, surface area, and roughness). The fractal dimension of gradation reflects particle size distribution complexity; the fractal dimension of surface area quantifies texture irregularity; the fractal dimension of roughness describes contour variation. A predictive framework integrating "3D scanning, secondary development and supervised learning" was established for accurate estimation of D. Results show superior precision in predicting both total mass (M) and D, and the average prediction error (APE) of D was significantly reduced to 1.78 %. Two-dimensional (2D) indicators dominate M prediction, while 3D indicators are more suitable for predicting D. The proposed prediction model not only provides an efficient and precise solution for concrete aggregate screening but also establishes a theoretical and technical foundation for future optimization design of concrete aggregates. This work highlights the potential and advantages of combining 3D scanning with machine learning.
期刊介绍:
Construction and Building Materials offers an international platform for sharing innovative and original research and development in the realm of construction and building materials, along with their practical applications in new projects and repair practices. The journal publishes a diverse array of pioneering research and application papers, detailing laboratory investigations and, to a limited extent, numerical analyses or reports on full-scale projects. Multi-part papers are discouraged.
Additionally, Construction and Building Materials features comprehensive case studies and insightful review articles that contribute to new insights in the field. Our focus is on papers related to construction materials, excluding those on structural engineering, geotechnics, and unbound highway layers. Covered materials and technologies encompass cement, concrete reinforcement, bricks and mortars, additives, corrosion technology, ceramics, timber, steel, polymers, glass fibers, recycled materials, bamboo, rammed earth, non-conventional building materials, bituminous materials, and applications in railway materials.