[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124795-en":3,"doc-seo-124795-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},124795,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine Learning Assisted Mechanical Metamaterial Design for Additive Manufacturing","Metamaterials with counterintuitive mechanics, such as negative Poisson’s ratio, negative refraction, and negative thermal expansion, enable advanced multiscale structural design. Conventional mechanical metamaterial design often depends on topology sizing optimization over fixed layouts or on slow inverse homogenisation. This work explores neural-network-driven inverse design to discover metamaterial topology and broaden property bounds for design for additive manufacturing, using NNs/DCNNs for inverse property-to-design mapping and GAN generators for diverse microstructures, aiming to reduce generation cost.","Machine Learning Assisted Mechanical Metamaterial Design for Additive Manufacturing  \nJier Wang*, Ajit Panesar*  \n*IDEA Lab, Department of Aeronautics, Imperial College London, UK  \nAbstract  \nMetamaterials, widely studied for its counterintuitive property such as negative Poisson’s ratio, negative refraction, negative thermal expansion, and employed in various fields, are recognised to provide foundation for superior multiscale structural designs. However, current mechanical metamaterial design methods usually relay on performing sizing optimisations on predefined topology or implementing time-consuming inverse homogenisation methods. Machine Learning (ML), as a powerful self-learning tool, is considered to have the potential of discovering metamaterial topology and extending its property bounds. This work considers the use of Neural Networks (NNs),(De-Convolutional Neural Networks) DCNNs and Generative Adversarial Networks (GANs) to speed up the generation of new topologies for metamaterials. NNs and DCNNs are trained to inversely generate metamaterial designs based on the input target effective macroscale properties, whilst the generator in GANs is expected to output diverse metamaterial microstructures with random noise inputs. This work highlights the potential of data-driven approaches in Design for Additive Manufacturing (DfAM) as an alternative to the time-consuming, conventional methods.  \nIntroduction  \nMetamaterials are structures that are designed to exhibit extraordinary mechanical, electromagnetic, optical, or other properties not found in natural materials. Auxetic materials are a category of mechanical metamaterials which have negative Poisson's ratios [1](i.e. materials would expand under tension, while compact under compression [2]) . Auxetic metamaterials can be potentially applied in various fields, like aerospace, biomedical, sport wears, automobile, vehicles, etc. Additive Manufacturing (AM) provides larger manufacturing flexibility and facilitates the complex design of structures [3]–[6]. Metamaterials, which usually rely on complex microscale architectures to achieve unusual properties at the macro-scale, would benefit from AM.  \nA few classes of auxetic metamaterials have been reviewed in [1][7], including re-entrant models [8]–[10], rotating polygonal models [11][12], chiral models [13], crumpled sheets models [14], perforated sheets models, etc. Apart from existed templates, an automated way using a numerical topology optimisation method to design periodic microstructures possessing prescribed elastic properties was proposed in [15] . The design objective of this topology optimisation method is to minimise the error between obtained elastic properties and prescribed properties with a constraint on material volume.  \nMachine Learning (ML) as a fast-developing technique, has attracted immense attention in the past few years. Several different roles of ML in structural design have been discussed in [16] . ML, in contrast to physicsbased methods, has demonstrated its superior efficacy in exploring and extending microstructure design domain. For instance, ML showed its capability of automatically discovering microstructures which exhibit extremal elastic macroscale properties in [17]. Similarly, a self-learning algorithm for a given hierarchical material to honeon superior microstructure designs which can achieve higher strength and toughness was proposed [18] .  \nK-means clustering was adopted to cluster the elements to 3 or 4 cell clusters based on elemental densities before the subsequent micro-structure optimisation of each cluster [19] . Autoencoder was employed to predict mechanical properties of a micro-lattice using the encoder and to generate micro-lattices from the desired mechanical properties using the decoder [20] . Neural Networks (NNs) were deployed to establish relations between regular triangular lattice structure and its elasticity properties for the design of architectured lattices with","cbCaisoIHMRlTxbb","https://ap.wps.com/l/cbCaisoIHMRlTxbb","pdf",1058604,1,"English","en",105,"# Introduction\n## Metamaterials and auxetic behavior\n## Additive manufacturing and design motivation\n## Prior work on topology optimization and ML\n## ML model approaches in structural design\n# Methodology\n## Auxetic metamaterial candidate\n## Data collection and dataset overview\n## Inverse generation models (NNs, DCNNs, GANs)\n# Results and comparison\n## Accuracy metrics and computational cost","[{\"question\":\"Why do mechanical metamaterial designs benefit from additive manufacturing?\",\"answer\":\"Additive manufacturing enables complex microscale architectures that are difficult to fabricate otherwise, helping metamaterials achieve unusual macro-scale properties.\"},{\"question\":\"How do the neural-network models generate metamaterial topologies?\",\"answer\":\"Neural networks and DCNNs are trained to inversely generate metamaterial designs from target effective macroscale properties, while GANs aim to output diverse microstructures using random noise inputs.\"},{\"question\":\"What is the main advantage claimed over conventional inverse homogenisation methods?\",\"answer\":\"The data-driven approach is presented as a faster alternative, reducing the time cost of generating new topologies compared with conventional, computationally intensive methods.\"}]","Machine Learning Assisted Mechanical Metamaterial Design for Additive Manufacturing | PDF",1785894698,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-assisted-mechanical-metamaterial-design-for-additive-manufacturing","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-assisted-mechanical-metamaterial-design-for-additive-manufacturing/124795/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do mechanical metamaterial designs benefit from additive manufacturing?","Question",{"text":74,"@type":75},"Additive manufacturing enables complex microscale architectures that are difficult to fabricate otherwise, helping metamaterials achieve unusual macro-scale properties.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How do the neural-network models generate metamaterial topologies?",{"text":79,"@type":75},"Neural networks and DCNNs are trained to inversely generate metamaterial designs from target effective macroscale properties, while GANs aim to output diverse microstructures using random noise inputs.",{"name":81,"@type":72,"acceptedAnswer":82},"What is the main advantage claimed over conventional inverse homogenisation methods?",{"text":83,"@type":75},"The data-driven approach is presented as a faster alternative, reducing the time cost of generating new topologies compared with conventional, computationally intensive methods.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]