CNN-based calibration of discrete element method parameters for calcareous sand

IF 2.8 4区 环境科学与生态学 Q3 ENVIRONMENTAL SCIENCES
Yangpan Fu, Huawei Tong, Jie Yuan, Yizhao Wang, Jie Cui, Yi Shan
{"title":"CNN-based calibration of discrete element method parameters for calcareous sand","authors":"Yangpan Fu,&nbsp;Huawei Tong,&nbsp;Jie Yuan,&nbsp;Yizhao Wang,&nbsp;Jie Cui,&nbsp;Yi Shan","doi":"10.1007/s12665-025-12138-y","DOIUrl":null,"url":null,"abstract":"<div><p>The selection of appropriate inter-particle parameters in discrete element method (DEM) simulations is crucial, and the commonly used trial-and-error method has been criticised for its uncontrollability and high computational cost. Therefore, this study proposes a new framework based on convolutional neural networks (CNN) as an alternative method for calibrating inter-particle parameters in calcareous sand materials. Firstly, a biaxial test dataset for calcareous sand was generated using DEM simulations. This data set was then used to train a CNN to capture the primary underlying correlation between macroscopic mechanical properties and the inter-particle parameters of the contact model. To demonstrate the powerful performance of CNN, this paper also established a back-propagation neural network (BP) and gated recurrent units (GRUs) as control experiments. The results showed that the CNN had higher prediction accuracy compared to the BP and GRU models. After DEM simulation using the parameters predicted by the CNN, it was found that the stress–strain curves and failure patterns closely matched the results of the laboratory tests. This confirms that the CNN can quickly and accurately determine the inter-particle parameters for DEM simulation and verifies the robustness of the CNN model in predicting laboratory test results, this method provides a reference for the calibration of DEM parameters for calcareous sand, thereby offering strong support for the use of calcareous sand in marine development and construction projects.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 5","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Earth Sciences","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s12665-025-12138-y","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

The selection of appropriate inter-particle parameters in discrete element method (DEM) simulations is crucial, and the commonly used trial-and-error method has been criticised for its uncontrollability and high computational cost. Therefore, this study proposes a new framework based on convolutional neural networks (CNN) as an alternative method for calibrating inter-particle parameters in calcareous sand materials. Firstly, a biaxial test dataset for calcareous sand was generated using DEM simulations. This data set was then used to train a CNN to capture the primary underlying correlation between macroscopic mechanical properties and the inter-particle parameters of the contact model. To demonstrate the powerful performance of CNN, this paper also established a back-propagation neural network (BP) and gated recurrent units (GRUs) as control experiments. The results showed that the CNN had higher prediction accuracy compared to the BP and GRU models. After DEM simulation using the parameters predicted by the CNN, it was found that the stress–strain curves and failure patterns closely matched the results of the laboratory tests. This confirms that the CNN can quickly and accurately determine the inter-particle parameters for DEM simulation and verifies the robustness of the CNN model in predicting laboratory test results, this method provides a reference for the calibration of DEM parameters for calcareous sand, thereby offering strong support for the use of calcareous sand in marine development and construction projects.

求助全文
约1分钟内获得全文 求助全文
来源期刊
Environmental Earth Sciences
Environmental Earth Sciences 环境科学-地球科学综合
CiteScore
5.10
自引率
3.60%
发文量
494
审稿时长
8.3 months
期刊介绍: Environmental Earth Sciences is an international multidisciplinary journal concerned with all aspects of interaction between humans, natural resources, ecosystems, special climates or unique geographic zones, and the earth: Water and soil contamination caused by waste management and disposal practices Environmental problems associated with transportation by land, air, or water Geological processes that may impact biosystems or humans Man-made or naturally occurring geological or hydrological hazards Environmental problems associated with the recovery of materials from the earth Environmental problems caused by extraction of minerals, coal, and ores, as well as oil and gas, water and alternative energy sources Environmental impacts of exploration and recultivation – Environmental impacts of hazardous materials Management of environmental data and information in data banks and information systems Dissemination of knowledge on techniques, methods, approaches and experiences to improve and remediate the environment In pursuit of these topics, the geoscientific disciplines are invited to contribute their knowledge and experience. Major disciplines include: hydrogeology, hydrochemistry, geochemistry, geophysics, engineering geology, remediation science, natural resources management, environmental climatology and biota, environmental geography, soil science and geomicrobiology.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信