[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123566-en":3,"doc-seo-123566-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123566,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","A machine learning based multi-scale computation framework for granular materials - Abstract - Manuscript","Machine learning models can learn constitutive relationships of granular materials directly from datasets without relying on phenomenological assumptions, and they can be updated when new training samples become available. A coupled finite element method and machine learning (FEM-ML) framework is presented to simulate granular materials by using Gaussian process-based random loading paths and coupled FEM-DEM simulations to generate training data. A parametrisation of deformation history represents historical influences, while uncertainty-level active learning selects informative points and enables effective resampling from large datasets. Two examples validate applicability, and performance is assessed through systematic error analysis and improvement discussions, showing gains in computational efficiency and mechanical response simulation capability.","Manuscript 2nd version Click here to access/download;Manuscript;manuscript_R2 . pdf   \nClick here to view linked References  \n1 A machine learning based multi-scale computation framework for  \n2 granular materials  \n3 Shaoheng Guana,b,c, 1 , Tongming Quc, Y.T. Fengc,2 , Gang Maa,b,3 , Wei Zhoua,b  \n4 a State Key Laboratory of Water Resources and Hydropower Engineering Science,  \n5 Wuhan University, Wuhan 430072, China  \n6 b Key Laboratory of Rock Mechanics in Hydraulic Structural Engineering of Ministry  \n7 of Education, Wuhan University, Wuhan 430072, China  \n8 c Zienkiewicz Centre for Computational Engineering, College of Engineering,  \n9 Swansea University, Swansea, Wales, SA1 8EP, UK  \n10 Abstract  \n11 With the development of experimental measurement technology and high-fidelity numerical  \n12 simulations of granular materials, empirical-based classical constitutive models may not be able to  \n13 take full advantage of the rapidly increasing available datasets. Machine learning-based models  \n14 can inherently avoid phenomenological assumptions to directly learn the constitutive relationship  \n15 from the datasets, and the trained model is sufficiently flexible to be reconstructed once new  \n16 training samples are added. In this work, a coupled finite element method and machine learning  \n17 (FEM-ML) computational framework is proposed for simulating granular materials. Gaussian  \n18 process-based random loading paths and coupled FEM-DEM simulations are used to generate  \n19 training samples. A parametrisation of the material deformation history is used to represent the  \n20 historical influence of granular materials. An uncertainty-level based active learning is utilised to  \n21 evaluate the informativeness of data points for network training and then to establish an effective  \n22 resampling scheme from a massive dataset. Two examples are provided to show the applicability  \n23 of the implemented FEM-ML framework. The performance of the proposed framework is also  \n24 evaluated, the error is systematically analysed, and possible improvements are discussed. The  \n25 results demonstrate that the FEM-ML framework offers considerable improvements in terms of  \n26 computational efficiency and competence to simulate the mechanical responses of granular  \n27 materials.  \n1 Email: [shaohengguan@gmail.com](shaohengguan@gmail.com)  \n2 Corresponding author 1: y.feng@swansea.ac.uk  \n[3](3 Corresponding author 2: magang630@whu.edu.cn)[ Corresponding author 2: magang630@whu.edu.cn](3 Corresponding author 2: magang630@whu.edu.cn)  \n28 1 Introduction  \n29 Granular materials such as gravel, sand, and powders are ubiquitous in industry and geotechnical  \n30 applications, and they are considered to be the second most abundant material on Earth after fluids  \n31 [1] . The discrete nature of granular materials and dissipative interactions among particles give rise  \n32 to a rich and complex bulk behaviour, making them differ significantly from solids, liquids, and  \n33 gases. The complexity of granular media can be partially attributed to its unique features, such as  \n34 inherent anisotropy and heterogeneity [2, 3], pressure and rate-dependence [4–6], continuous  \n35 evolving microstructure and complicated strain localisation phenomenon within unstable granular  \n36 materials [7–11] . Accurately reproducing the mechanical behaviour of granular materials subject  \n37 to various external loads through mathematical equations is intricate but crucial for engineering- 38 scale numerical simulations.  \n39  \n40 In general, the mechanical behaviour of history-dependent granular materials has been described 41 by empirical constitutive laws formulated within continuum thermodynamics and elastoplastic 42 theory. Internal variables characterise the material state according to phenomenological 43 assumptions. Advancements in micro-mechanical simulations and the internal fabric statistical 44 description [12–15] have inspired physics-based internal var","cbCaihWEYxXXDaEc","https://ap.wps.com/l/cbCaihWEYxXXDaEc","pdf",2474479,1,48,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What motivates using machine learning for granular material constitutive modeling?\",\"answer\":\"Classical empirical constitutive models may not fully leverage rapidly growing high-fidelity simulation datasets. Machine learning can learn constitutive relationships directly from data while avoiding phenomenological assumptions.\"},{\"question\":\"How is training data generated in the proposed FEM-ML framework?\",\"answer\":\"Gaussian process-based random loading paths are used together with coupled FEM-DEM simulations to produce training samples.\"},{\"question\":\"What role does active learning play in the framework?\",\"answer\":\"Uncertainty-level active learning measures how informative data points are for training, and it supports an effective resampling scheme from a massive dataset.\"}]","A machine learning based multi-scale computation framework for granular materials - Abstract - Manuscript | PDF",1785817388,121,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-machine-learning-based-multi-scale-computation-framework-for-granular-materials-abstract-manuscript","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-machine-learning-based-multi-scale-computation-framework-for-granular-materials-abstract-manuscript/123566/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What motivates using machine learning for granular material constitutive modeling?","Question",{"text":75,"@type":76},"Classical empirical constitutive models may not fully leverage rapidly growing high-fidelity simulation datasets. Machine learning can learn constitutive relationships directly from data while avoiding phenomenological assumptions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is training data generated in the proposed FEM-ML framework?",{"text":80,"@type":76},"Gaussian process-based random loading paths are used together with coupled FEM-DEM simulations to produce training samples.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does active learning play in the framework?",{"text":84,"@type":76},"Uncertainty-level active learning measures how informative data points are for training, and it supports an effective resampling scheme from a massive dataset.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]