{"title":"基于人工大样本和深度学习的粗粒土分级识别","authors":"Yuan-en Pang , Xu Li , Zu-yu Chen","doi":"10.1016/j.sandf.2024.101526","DOIUrl":null,"url":null,"abstract":"<div><div>In earth-rockfill dams, roadbeds, airports, and other embankment projects, gradation information serves as the basis for evaluating the quality and suitability of fill materials. Addressing the limitations of existing image-based contour recognition methods and machine learning approaches in recognizing small particle size ranges, this study establishes the first publicly available coarse-grained soil database including Yellow River Silt and Quartz Sand datasets, with particle sizes ranging from 0.075 to 20 mm, comprising a total of 22,380 images. Subsequently, a novel Convolutional Neural Network (CNN) architecture, the Searcher-Analyzer Network (SaNet), based on the Deep Residual Network (ResNet), was proposed to enhance the accuracy of gradation recognition by taking multiple images under a single gradation as input. Finally, the interpretability of the model was discussed through feature map visualization. The results demonstrate that SaNet achieves <span><math><mrow><mover><mrow><mrow><mi>MAE</mi></mrow></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 1.63 × 10<sup>−2</sup> and <span><math><mrow><mover><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 0.995 for Yellow River Silt, and <span><math><mrow><mover><mrow><mrow><mi>MAE</mi></mrow></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of<!--> <!-->1.21 × 10<sup>−2</sup> and <span><math><mrow><mover><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 0.992 for Quartz Sand. Concurrently, the additional computational time and storage requirements are only 3.5 % and 0.3 % more than those of ResNet, allowing the recognition of a single image to be completed within 10 ms. The findings of this study indicate that the proposed SaNet model can instantly achieve high accuracy in gradation recognition, meeting the demands for real-time, non-destructive gradation testing in related tasks.</div></div>","PeriodicalId":21857,"journal":{"name":"Soils and Foundations","volume":"64 6","pages":"Article 101526"},"PeriodicalIF":3.3000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Recognizing gradations of coarse soils based on big artificial samples and deep learning\",\"authors\":\"Yuan-en Pang , Xu Li , Zu-yu Chen\",\"doi\":\"10.1016/j.sandf.2024.101526\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In earth-rockfill dams, roadbeds, airports, and other embankment projects, gradation information serves as the basis for evaluating the quality and suitability of fill materials. Addressing the limitations of existing image-based contour recognition methods and machine learning approaches in recognizing small particle size ranges, this study establishes the first publicly available coarse-grained soil database including Yellow River Silt and Quartz Sand datasets, with particle sizes ranging from 0.075 to 20 mm, comprising a total of 22,380 images. Subsequently, a novel Convolutional Neural Network (CNN) architecture, the Searcher-Analyzer Network (SaNet), based on the Deep Residual Network (ResNet), was proposed to enhance the accuracy of gradation recognition by taking multiple images under a single gradation as input. Finally, the interpretability of the model was discussed through feature map visualization. The results demonstrate that SaNet achieves <span><math><mrow><mover><mrow><mrow><mi>MAE</mi></mrow></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 1.63 × 10<sup>−2</sup> and <span><math><mrow><mover><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 0.995 for Yellow River Silt, and <span><math><mrow><mover><mrow><mrow><mi>MAE</mi></mrow></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of<!--> <!-->1.21 × 10<sup>−2</sup> and <span><math><mrow><mover><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> of 0.992 for Quartz Sand. Concurrently, the additional computational time and storage requirements are only 3.5 % and 0.3 % more than those of ResNet, allowing the recognition of a single image to be completed within 10 ms. The findings of this study indicate that the proposed SaNet model can instantly achieve high accuracy in gradation recognition, meeting the demands for real-time, non-destructive gradation testing in related tasks.</div></div>\",\"PeriodicalId\":21857,\"journal\":{\"name\":\"Soils and Foundations\",\"volume\":\"64 6\",\"pages\":\"Article 101526\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Soils and Foundations\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0038080624001045\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, GEOLOGICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soils and Foundations","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0038080624001045","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}
Recognizing gradations of coarse soils based on big artificial samples and deep learning
In earth-rockfill dams, roadbeds, airports, and other embankment projects, gradation information serves as the basis for evaluating the quality and suitability of fill materials. Addressing the limitations of existing image-based contour recognition methods and machine learning approaches in recognizing small particle size ranges, this study establishes the first publicly available coarse-grained soil database including Yellow River Silt and Quartz Sand datasets, with particle sizes ranging from 0.075 to 20 mm, comprising a total of 22,380 images. Subsequently, a novel Convolutional Neural Network (CNN) architecture, the Searcher-Analyzer Network (SaNet), based on the Deep Residual Network (ResNet), was proposed to enhance the accuracy of gradation recognition by taking multiple images under a single gradation as input. Finally, the interpretability of the model was discussed through feature map visualization. The results demonstrate that SaNet achieves of 1.63 × 10−2 and of 0.995 for Yellow River Silt, and of 1.21 × 10−2 and of 0.992 for Quartz Sand. Concurrently, the additional computational time and storage requirements are only 3.5 % and 0.3 % more than those of ResNet, allowing the recognition of a single image to be completed within 10 ms. The findings of this study indicate that the proposed SaNet model can instantly achieve high accuracy in gradation recognition, meeting the demands for real-time, non-destructive gradation testing in related tasks.
期刊介绍:
Soils and Foundations is one of the leading journals in the field of soil mechanics and geotechnical engineering. It is the official journal of the Japanese Geotechnical Society (JGS)., The journal publishes a variety of original research paper, technical reports, technical notes, as well as the state-of-the-art reports upon invitation by the Editor, in the fields of soil and rock mechanics, geotechnical engineering, and environmental geotechnics. Since the publication of Volume 1, No.1 issue in June 1960, Soils and Foundations will celebrate the 60th anniversary in the year of 2020.
Soils and Foundations welcomes theoretical as well as practical work associated with the aforementioned field(s). Case studies that describe the original and interdisciplinary work applicable to geotechnical engineering are particularly encouraged. Discussions to each of the published articles are also welcomed in order to provide an avenue in which opinions of peers may be fed back or exchanged. In providing latest expertise on a specific topic, one issue out of six per year on average was allocated to include selected papers from the International Symposia which were held in Japan as well as overseas.