[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-463313-105":59,"doc-detail-463313-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","physics-informed-neural-network-based-generation-of-composite-representative-volume-elements-with-non-uniform-distribution-and-high-volume-fractions","Physics-Informed Neural-Network-Based Generation of Composite Representative Volume Elements with Non-Uniform Distribution and High-Volume Fractions","","To reduce dependence on large training datasets for representative volume element (RVE) generation, this work proposes a physics-informed neural network (PINN) framework for unidirectional fiber-reinforced composites with non-uniform fiber distributions and high fiber volume fractions. Physical constraints—fiber non-overlap, target volume fraction, and boundary conditions—are embedded into the neural loss function. The approach reaches volume fractions above 0.8, exceeding conventional jamming-limit methods, and statistical checks across multiple scales match local microstructural patterns while preserving randomness globally. Finite element analysis then predicts elastic and damage responses, including interfacial debonding and nonlinear matrix damage, showing agreement with experiments.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/physics-informed-neural-network-based-generation-of-composite-representative-volume-elements-with-non-uniform-distribution-and-high-volume-fractions/463313/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/physics-informed-neural-network-based-generation-of-composite-representative-volume-elements-with-non-uniform-distribution-and-high-volume-fractions/463313.png","ImageObject",300,407,{"name":92,"@type":93},"SANS","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does the PINN method reduce reliance on large training datasets for RVE generation?","Question",{"text":112,"@type":113},"It embeds physical constraints directly into the neural network’s loss function, including fiber non-overlap, volume fraction requirements, and boundary conditions, avoiding the need for large datasets typically used in traditional machine learning approaches.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What volume fraction range does the proposed method achieve, and why is it important?",{"text":117,"@type":113},"It generates volume fractions exceeding 0.8, surpassing the jamming limit of conventional generation techniques, enabling realistic modeling of high-fiber-fraction composites.",{"name":119,"@type":110,"acceptedAnswer":120},"How are the generated RVEs validated and used to predict material behavior?",{"text":121,"@type":113},"Exhaustive statistical measurements at different scales verify that the method reproduces local fiber distribution patterns while maintaining randomness at larger scales. Finite element analysis then predicts elastic properties and damage behavior, including interfacial debonding and nonlinear matrix damage.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},463313,1791136833,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},962090760505,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Article  \nPhysics-Informed Neural-Network-Based Generation of Composite Representative Volume Elements with Non-Uniform Distribution and High-Volume Fractions  \nTianlu Zheng, Chaocan Cai *, Fan Yang, Rongguo Wang and Wenbo Liu  \nAcademic Editor: Martin Kröger  \nReceived: 27 November 2025  \nRevised: 22 December 2025  \nAccepted: 25 December 2025  \nPublished: 29 December 2025  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments, Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, China  \n* Correspondence: [c39008@163.com](c39008@163.com)  \nAbstract  \nTo reduce the reliance on large training sets for representative volume element (RVE) generation using machine learning, this work presents a novel approach based on physicsinformed neural network (PINN) to generate RVEs for unidirectional fiber-reinforced composites with non-uniform fiber distributions and high-volume fractions. The method embeds physical constraints including fiber non-overlap, volume fraction, and boundary conditions directly into the neural network’s loss function. This integration eliminates the need for large training datasets, which is typically required by traditional machine learning methods. Moreover, it achieves volume fractions exceeding 0.8, surpassing the jamming limit of conventional generation techniques. Exhaustive statistical measurements taken at different scales confirm that the proposed method could accurately reproduce local fiber distribution patterns in realistic microstructures while maintaining complete randomness at larger scales. Finite element analysis was employed on the generated RVEs to predict the elastic properties and damage behavior that taking into account the interfacial debonding and nonlinear damage in matrix. The predictions of both macroscopic mechanical properties (elastic properties and strength) and microscopic damage patterns show good agreement with experimental results. The proposed PINN-based framework provides an efficient and reliable tool for computational micromechanics of polymer matrix composites.  \nKeywords: representative volume element; polymer composite materials; physics-informed neural network; non-uniform distribution; statistical analysis; micromechanical analysis; damage behavior analysis  \n1. Introduction  \nThe remarkable mechanical properties of fiber-reinforced composites—notably, their high specific strength and stiffness, low density, and versatile design options—have led to their widespread adoption in numerous industrial applications [1,2] . With the expanding market for these materials, there is an urgent need for methods that are both economical and accurate to predict their mechanical behavior. In recent years, micromechanics computation based on representative volume element (RVE) has been an efficient method to address this issue. Shahid et al. [3] developed three-dimensional RVE models for single-fiber, hybrid, and multi-fiber systems to predict their effective elastic properties. Zhang et al. [4] proposed an algorithm for generating RVE to mitigate microstructural inhomogeneities in  \nfiber-reinforced composites. Ghayoor et al. [5] developed an algorithm to generate random RVE with varying volume fractions and minimum distances between fibers. In general, aerospace-grade high-strength fiber-reinforced composites feature a fiber volume fraction ranging from 60% to 70%, with the fibers being randomly distributed. This distribution nature plays a vital role in defining the overall mechanical behavior of fiber-reinforced composites, specifically influencing local stress transfer mechanisms and crack damage initiation phenomena (e.g., interfacial debonding, matrix cracking) . Therefore, constructing an RVE ","cbCailwYRBp8davJ","https://ap.wps.com/l/cbCailwYRBp8davJ","pdf",2079456,17,"English","# Introduction\n## Motivation and background of RVE-based micromechanics\n## Existing RVE generation methods and limitations\n# Proposed PINN-based framework\n## Physics-informed loss constraints\n## High-volume-fraction capability and validation\n# Finite element prediction of elastic and damage behavior\n## Interfacial debonding and nonlinear matrix damage","[{\"question\":\"How does the PINN method reduce reliance on large training datasets for RVE generation?\",\"answer\":\"It embeds physical constraints directly into the neural network’s loss function, including fiber non-overlap, volume fraction requirements, and boundary conditions, avoiding the need for large datasets typically used in traditional machine learning approaches.\"},{\"question\":\"What volume fraction range does the proposed method achieve, and why is it important?\",\"answer\":\"It generates volume fractions exceeding 0.8, surpassing the jamming limit of conventional generation techniques, enabling realistic modeling of high-fiber-fraction composites.\"},{\"question\":\"How are the generated RVEs validated and used to predict material behavior?\",\"answer\":\"Exhaustive statistical measurements at different scales verify that the method reproduces local fiber distribution patterns while maintaining randomness at larger scales. Finite element analysis then predicts elastic properties and damage behavior, including interfacial debonding and nonlinear matrix damage.\"}]","Physics-Informed Neural-Network-Based Generation of Composite Representative Volume Elements with Non-Uniform Distribution and High-Volume Fractions | PDF",1790766389,43,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/217493b6f25652d2cb5a57471f814e1c.webp",983,1390,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/56002a0bc030f721d3629a328bfd3f23.webp",982,1388,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/141c489bbbeab683ecfd04bd5750079b.webp",981,1387,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/ba96a3f6f43bcced1065cab0286b85dc.webp",980,1385]