{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:25:42Z","timestamp":1775118342452,"version":"3.50.1"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"content-version":"vor","delay-in-days":5,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2018R1A5A7025409"],"award-info":[{"award-number":["2018R1A5A7025409"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2022-0-00969"],"award-info":[{"award-number":["2022-0-00969"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2022-0-00986"],"award-info":[{"award-number":["2022-0-00986"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["RS-2024-00410810"],"award-info":[{"award-number":["RS-2024-00410810"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Surrogate models are commonly used in engineering design to reduce the computational costs of simulations by approximating design variables and geometric parameters from computer-aided design (CAD) models. However, traditional surrogate models often lose critical information when simplified to lower dimensions and face challenges in handling the complexity of 3D shapes, especially in industrial datasets. To address these limitations, we propose a Bayesian graph neural network (GNN) framework that directly learns geometric features from CAD mesh representations for accurate engineering performance prediction. Our framework leverages Bayesian optimization (BO) to dynamically determine the optimal mesh element size, significantly improving model accuracy while balancing computational efficiency. This approach optimizes mesh resolution to preserve critical geometric features in 3D deep-learning-based surrogate models, adapting mesh size based on the task for high flexibility across various engineering applications. Experimental results demonstrate that mesh quality directly impacts prediction accuracy. The proposed BO-EI GNN model outperforms state-of-the-art models, including 3D CNN, SubdivNet, GCN, and GNN, in predicting mass, rim stiffness, and disk stiffness. Our method also significantly reduces computational costs compared to traditional optimization techniques. The proposed framework shows promising potential for application in finite element analysis (FEA) and other mesh-based simulations, enhancing the utility of surrogate models across various engineering fields.<\/jats:p>","DOI":"10.1093\/jcde\/qwae102","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T10:56:12Z","timestamp":1731495372000},"page":"260-271","source":"Crossref","is-referenced-by-count":11,"title":["BMO-GNN: Bayesian mesh optimization for graph neural networks to enhance engineering performance prediction"],"prefix":"10.1093","volume":"11","author":[{"given":"Jangseop","family":"Park","sequence":"first","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology , Daejeon 34051 ,","place":["Republic of Korea"]},{"name":"Narnia Labs , Daejeon 34051 ,","place":["Republic of Korea"]}]},{"given":"Namwoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology , Daejeon 34051 ,","place":["Republic of Korea"]},{"name":"Narnia Labs , Daejeon 34051 ,","place":["Republic of Korea"]}]}],"member":"286","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"2025041407271950000_bib1","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s00371-010-0523-1","article-title":"3d articulated object retrieval using a graph-based representation","volume":"26","author":"Agathos","year":"2010","journal-title":"The Visual Computer"},{"key":"2025041407271950000_bib2","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s00163-020-00336-7","article-title":"Managing computational complexity using surrogate models: a critical review","volume":"31(3)","author":"Alizadeh","year":"2020","journal-title":"Research in Engineering Design"},{"key":"2025041407271950000_bib3","author":"Altair Engineering, Inc.","year":"2024"},{"key":"2025041407271950000_bib4","doi-asserted-by":"crossref","DOI":"10.1142\/8685","volume-title":"Voronoi Diagrams and Delaunay Triangulations","author":"Aurenhammer","year":"2013"},{"key":"2025041407271950000_bib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CLUSTER.2013.6702683","article-title":"Active-learning-based surrogate models for empirical performance tuning","volume-title":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","author":"Balaprakash","year":"2013"},{"key":"2025041407271950000_bib6","doi-asserted-by":"publisher","first-page":"8279","DOI":"10.1609\/aaai.v33i01.33018279","article-title":"Meshnet: Mesh neural network for 3d shape representation","volume":"33","author":"Feng","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2025041407271950000_bib7","first-page":"869","article-title":"Splinecnn: Fast geometric deep learning with continuous b-spline kernels","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Fey","year":"2018"},{"key":"2025041407271950000_bib9","doi-asserted-by":"publisher","first-page":"778876","DOI":"10.3389\/fceng.2021.778876","article-title":"Increasing superstructure optimization capacity through self-learning surrogate models","volume":"3","author":"Granacher","year":"2021","journal-title":"Frontiers in Chemical Engineering"},{"key":"2025041407271950000_bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322959","article-title":"Meshcnn: a network with an edge","volume":"38(4)","author":"Hanocka","year":"2019","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2025041407271950000_bib11","doi-asserted-by":"publisher","first-page":"102008","DOI":"10.1016\/j.aei.2023.102008","article-title":"Fus-gcn: Efficient b-rep based graph convolutional networks for 3d-cad model classification and retrieval","volume":"56","author":"Hou","year":"2023","journal-title":"Advanced Engineering Informatics"},{"key":"2025041407271950000_bib12","doi-asserted-by":"publisher","first-page":"1\u221216","DOI":"10.1145\/3506694","article-title":"Subdivision-based mesh convolution networks","volume":"41(3)","author":"Hu","year":"2022","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2025041407271950000_bib14","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1109\/TVCG.2020.3016645","article-title":"Surface remeshing: A systematic literature review of methods and research directions","volume":"28","author":"Khan","year":"2020","journal-title":"IEEE transactions on visualization and computer graphics"},{"key":"2025041407271950000_bib15","doi-asserted-by":"publisher","first-page":"2384","DOI":"10.1093\/jcde\/qwad106","article-title":"BRepGAT: Graph neural network to segment machining feature faces in a B-rep model","volume":"10(6)","author":"Lee","year":"2023","journal-title":"Journal of Computational Design and Engineering"},{"key":"2025041407271950000_bib16","doi-asserted-by":"publisher","first-page":"13672","DOI":"10.48550\/arXiv.2109.13672","article-title":"Improved prediction rule ensembling through model-based data generation","volume":"arXiv:2109","author":"Markovitch","year":"2021","journal-title":"arXiv preprint"},{"key":"2025041407271950000_bib17","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1109\/IROS.2015.7353481","article-title":"Voxnet: A 3d convolutional neural network for real-time object recognition","volume-title":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Maturana","year":"2015"},{"key":"2025041407271950000_bib18","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi","year":"2017"},{"key":"2025041407271950000_bib19","first-page":"5105","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Advances in Neural Information Processing Systems","author":"Qi","year":"2017"},{"key":"2025041407271950000_bib8","doi-asserted-by":"publisher","first-page":"101427","DOI":"10.1016\/j.aei.2021.101427","article-title":"3D CAD model retrieval based on sketch and unsupervised variational autoencoder","volume":"51","author":"Qin","year":"2022","journal-title":"Advanced Engineering Informatics"},{"key":"2025041407271950000_bib20","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Transactions on Neural Networks"},{"key":"2025041407271950000_bib13","first-page":"68\u221282","article-title":"Improving imbalanced learning by pre-finetuning with data augmentation","volume-title":"Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications","author":"Shi","year":"2022"},{"key":"2025041407271950000_bib21","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s00158-022-03485-6","article-title":"Wheel impact test by deep learning: prediction of location and magnitude of maximum stress","volume":"66","author":"Shin","year":"2023","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"2025041407271950000_bib22","first-page":"2951","article-title":"Practical bayesian optimization of machine learning algorithms","volume-title":"Advances in Neural Information Processing Systems","author":"Snoek","year":"2012"},{"key":"2025041407271950000_bib23","first-page":"2088","article-title":"Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Tatarchenko","year":"2017"},{"key":"2025041407271950000_bib24","first-page":"369","article-title":"Generic remeshing of 3d triangular meshes with metric-dependent discrete voronoi diagrams","volume-title":"IEEE Transactions on Visualization and Computer Graphics","author":"Valette","year":"2008"},{"key":"2025041407271950000_bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073608","article-title":"O-cnn: Octree-based convolutional neural networks for 3d shape analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"2025041407271950000_bib26","doi-asserted-by":"publisher","first-page":"111701","DOI":"10.1115\/1.4044199","article-title":"Design repository effectiveness for 3d convolutional neural networks: Application to additive manufacturing","volume":"141(11)","author":"Williams","year":"2019","journal-title":"Journal of Mechanical Design"},{"key":"2025041407271950000_bib27","first-page":"1912","article-title":"3d shapenets: A deep representation for volumetric shapes","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu","year":"2015"},{"key":"2025041407271950000_bib28","first-page":"1903","article-title":"Data-driven 3d voxel patterns for object category recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Xiang","year":"2015"},{"key":"2025041407271950000_bib29","doi-asserted-by":"publisher","first-page":"115430","DOI":"10.1016\/j.eswa.2021.115430","article-title":"Explainable artificial intelligence for manufacturing cost estimation and machining feature visualization","volume":"183","author":"Yoo","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"2025041407271950000_bib30","doi-asserted-by":"publisher","first-page":"2725","DOI":"10.1007\/s00158-021-02953-9","article-title":"Integrating deep learning into cad\/cae system: generative design and evaluation of 3d conceptual wheel","volume":"64","author":"Yoo","year":"2021","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"2025041407271950000_bib31","doi-asserted-by":"publisher","first-page":"09847","DOI":"10.48550\/arXiv.1801.09847","article-title":"Open3d: A modern library for 3d data processing","volume":"arXiv:1801","author":"Zhou","year":"2018","journal-title":"arXiv preprint"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwae102\/60630609\/qwae102.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/11\/6\/260\/61212383\/qwae102.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/11\/6\/260\/61212383\/qwae102.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T07:27:36Z","timestamp":1744615656000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/11\/6\/260\/7896417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,11,8]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwae102","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12]]},"published":{"date-parts":[[2024,11,8]]}}}