{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T21:05:52Z","timestamp":1775077552515,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["RS-2025-25455051"],"award-info":[{"award-number":["RS-2025-25455051"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013129","name":"Ministry of SMEs and Startups","doi-asserted-by":"publisher","award":["RS-2022-00140364"],"award-info":[{"award-number":["RS-2022-00140364"]}],"id":[{"id":"10.13039\/501100013129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Injection-moulding computer-aided engineering simulation is a numerical analysis process with high computational costs, presenting limitations for direct application to real-time simulation-based digital twin technology. To overcome these limitations, this study proposes an accelerated surrogate model that ensures generalisation performance for unseen geometries and process conditions within the same product family, and conducts a feature importance analysis for model interpretability. The model was trained using simulation data generated by randomly sampled combinations of six injection-moulding process conditions across various toothbrush geometries. In addition, seven geometric features based on distance, area, volume, thickness, and curvature were utilised as input features to effectively represent the characteristics of the product geometry. The surrogate model was constructed using a graph attention network that integrates an attention mechanism with a message-passing structure. The proposed model was applied to predict unseen product geometries and process conditions that were not included in the training dataset. The model achieved normalised root mean square errors (NRMSE) of 0.0125, 0.0451, 0.0712, and 0.0373 for fill time, the temperature at the end of filling, the pressure at the velocity-to-pressure switchover point, and the average of the three directional deflection components, respectively, averaged over 400 unseen process-condition combinations. In terms of the average acceleration performance across the four toothbrush geometries, the unseen product geometry preprocessing accounted for approximately 20.68% of the computation time of the conventional simulation, whereas prediction time for unseen process conditions required on average only approximately 0.14%. In addition, the importance of the geometric features for the prediction accuracy of each physical quantity was analysed using permutation feature importance. Based on this analysis, key geometric features were identified, and an ablation study was conducted to further examine their influence on the prediction of injection-moulding physical quantities. These results provide useful insights into geometric feature selection for injection-moulding surrogate models.<\/jats:p>","DOI":"10.1093\/jcde\/qwag026","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:45:10Z","timestamp":1774010710000},"page":"67-81","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of geometric feature importance for enhancing performance of injection-moulding simulation surrogate model"],"prefix":"10.1093","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8969-3004","authenticated-orcid":false,"given":"Kwangho","family":"Lee","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Korea University , Seoul 02841 ,","place":["Republic of Korea"]},{"name":"Digital Manufacturing Division, Korea Institute of Industrial Technology , Bucheon 14441 ,","place":["Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2723-1354","authenticated-orcid":false,"given":"Jongsun","family":"Kim","sequence":"additional","affiliation":[{"name":"Digital Manufacturing Division, Korea Institute of Industrial Technology , Bucheon 14441 ,","place":["Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4817-7932","authenticated-orcid":false,"given":"Gunwoo","family":"Noh","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Korea University , Seoul 02841 ,","place":["Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"2026040114402751400_bib1","doi-asserted-by":"publisher","first-page":"5433","DOI":"10.1038\/s41598-022-09128-6","article-title":"A machine learning model to estimate myocardial stiffness from EDPVR","volume":"12","author":"Babaei","year":"2022","journal-title":"Scientific Reports"},{"key":"2026040114402751400_bib2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.01261","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv preprint arXiv:1806.01261"},{"key":"2026040114402751400_bib3","doi-asserted-by":"publisher","first-page":"6806","DOI":"10.3390\/s23156806","article-title":"On the development of a digital twin for underwater UXO detection using magnetometer-based data in application for the training set generation for machine learning models","volume":"23","author":"Blachnik","year":"2023","journal-title":"Sensors"},{"key":"2026040114402751400_bib4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine learning"},{"key":"2026040114402751400_bib5","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2023-117019","article-title":"Enhancing design guidelines for metal powder bed fusion: Analyzing geometric features to improve part quality","volume-title":"Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, V005T05A011","author":"Bushra","year":"2023"},{"key":"2026040114402751400_bib6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s00158-021-02861-y","article-title":"Springback optimization of deep drawing process based on FEM-ANN-PSO strategy","volume":"64","author":"El\u00a0Mrabti","year":"2021","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"2026040114402751400_bib7","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.matpr.2020.11.967","article-title":"A current state of art applied to injection moulding manufacturing process\u2013a review","volume":"43","author":"Farooque","year":"2021","journal-title":"Materials Today: Proceedings"},{"key":"2026040114402751400_bib8","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1002\/pen.20945","article-title":"Real-time measurement of flow front kinematics using quantitative visualization in injection molding process","volume":"48","author":"Fathi","year":"2008","journal-title":"Polymer Engineering & Science"},{"key":"2026040114402751400_bib9","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.3390\/polym17081012","article-title":"Influence of Injection Molding Parameters and Distance from Gate on the Mechanical Properties of Injection-Molded Polypropylene","volume":"17","author":"Fucikova","year":"2025","journal-title":"Polymers"},{"key":"2026040114402751400_bib10","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Gilmer","year":"2017"},{"key":"2026040114402751400_bib11","doi-asserted-by":"publisher","first-page":"107718","DOI":"10.1016\/j.polymertesting.2022.107718","article-title":"A review of current advancements in high surface quality injection molding: Measurement, influencing factors, prediction, and control","volume":"115","author":"Gim","year":"2022","journal-title":"Polymer Testing"},{"key":"2026040114402751400_bib12","doi-asserted-by":"publisher","first-page":"108340","DOI":"10.1016\/j.compositesa.2024.108340","article-title":"Fast approximation of fiber reinforced injection molding processes using eikonal equations and machine learning","volume":"185","author":"Greif","year":"2024","journal-title":"Composites Part A: Applied Science and Manufacturing"},{"key":"2026040114402751400_bib13","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3390\/jmmp4030092","article-title":"Combining simulation and machine learning as digital twin for the manufacturing of overmolded thermoplastic composites","volume":"4","author":"H\u00fcrkamp","year":"2020","journal-title":"Journal of Manufacturing and Materials Processing"},{"key":"2026040114402751400_bib14","doi-asserted-by":"publisher","first-page":"104333","DOI":"10.1016\/j.compind.2025.104333","article-title":"Developing a Digital Twin of part cooling in an injection moulding process through a Dynamic Mode Decomposition-Kalman Filter approach","volume":"172","author":"Kariminejad","year":"2025","journal-title":"Computers in Industry"},{"key":"2026040114402751400_bib15","doi-asserted-by":"publisher","first-page":"1957","DOI":"10.1007\/s00170-022-10337-6","article-title":"Correction of mould cavity geometry for warpage compensation","volume":"123","author":"Kastelic","year":"2022","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"2026040114402751400_bib16","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3390\/systems12020038","article-title":"A deep-reinforcement-learning-based digital twin for manufacturing process optimization","volume":"12","author":"Khdoudi","year":"2024","journal-title":"Systems"},{"key":"2026040114402751400_bib17","doi-asserted-by":"crossref","unstructured":"Khemani B., Patil S., Kotecha K., Tanwar S. (2024). A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11, 18. 10.1186\/s40537-023-00876-4.","DOI":"10.1186\/s40537-023-00876-4"},{"key":"2026040114402751400_bib18","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.5194\/tc-19-2583-2025","article-title":"Calibrating calving parameterizations using graph neural network emulators: Application to Helheim Glacier, East Greenland","volume":"19","author":"Koo","year":"2025","journal-title":"The Cryosphere"},{"key":"2026040114402751400_bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12541-025-01345-z","article-title":"Graph attention network-based surrogate model for acceleration and generalization of injection molding simulations","author":"Lee","year":"2026","journal-title":"International Journal of Precision Engineering and Manufacturing"},{"key":"2026040114402751400_bib20","doi-asserted-by":"publisher","first-page":"631","DOI":"10.5951\/mathteacher.110.8.0631","article-title":"Shoelace formula: Connecting the area of a polygon and the vector cross product","volume":"110","author":"Lee","year":"2017","journal-title":"Mathematics Teacher"},{"key":"2026040114402751400_bib21","doi-asserted-by":"publisher","first-page":"012077","DOI":"10.1088\/1757-899X\/324\/1\/012077","article-title":"Digital Twin concept for smart injection molding","volume":"324","author":"Liau","year":"2018","journal-title":"IOP Conference Series: Materials Science and Engineering"},{"key":"2026040114402751400_bib22","doi-asserted-by":"publisher","first-page":"027116","DOI":"10.1063\/5.0191290","article-title":"Shape optimization of sound barriers using an isogeometric meshless method","volume":"36","author":"Liu","year":"2024","journal-title":"Physics of Fluids"},{"key":"2026040114402751400_bib23","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.applthermaleng.2015.01.064","article-title":"Evaluation of heat transfer coefficient between polymer and cavity wall for improving cooling and crystallinity results in injection molding simulation","volume":"80","author":"Liu","year":"2015","journal-title":"Applied Thermal Engineering"},{"key":"2026040114402751400_bib24","doi-asserted-by":"crossref","unstructured":"Liu Y., Wang L., Zhu W., Yu X. (2025). Farthest point sampling in property designated chemical feature space as an effective strategy for enhancing the machine learning model performance for small scale chemical dataset. Journal of Materials Informatics, 5, 39. 10.20517\/jmi.2025.10.","DOI":"10.20517\/jmi.2025.10"},{"key":"2026040114402751400_bib25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-05105-4_2","article-title":"Discrete differential-geometry operators for triangulated 2-manifolds","volume-title":"Visualization and Mathematics III (pp. 35\u201357)","author":"Meyer","year":"2003"},{"key":"2026040114402751400_bib26","doi-asserted-by":"publisher","first-page":"103568","DOI":"10.1016\/j.compind.2021.103568","article-title":"Application of the Digital Twin for in process monitoring of the micro injection moulding process quality","volume":"135","author":"Modoni","year":"2022","journal-title":"Computers in Industry"},{"key":"2026040114402751400_bib27","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10845-022-02026-8","article-title":"Investigation and machine learning-based prediction of parametric effects of single point incremental forming on pillow effect and wall profile of AlMn1Mg1 aluminum alloy sheets","volume":"34","author":"Najm","year":"2023","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2026040114402751400_bib28","doi-asserted-by":"publisher","first-page":"8544","DOI":"10.1609\/aaai.v34i05.6376","article-title":"Message passing attention networks for document understanding","volume":"34","author":"Nikolentzos","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026040114402751400_bib29","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1093\/jcde\/qwae102","article-title":"BMO-GNN: Bayesian mesh optimization for graph neural networks to enhance engineering performance prediction","volume":"11","author":"Park","year":"2024","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026040114402751400_bib30","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1002\/pen.27170","article-title":"Machine learning for screw design in single-screw extrusion","volume":"65","author":"Polychronopoulos","year":"2025","journal-title":"Polymer Engineering & Science"},{"key":"2026040114402751400_bib31","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026040114402751400_bib32","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1093\/jcde\/qwaf015","article-title":"Explainable artificial intelligence twin for metaheuristic optimization: Double-skin facade with energy storage in buildings","volume":"12","author":"Tariq","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026040114402751400_bib33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2118\/220757-PA","article-title":"A U-Net enhanced graph neural network to simulate geological carbon sequestration","volume":"30","author":"Tariq","year":"2025","journal-title":"SPE Journal"},{"key":"2026040114402751400_bib34","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s00158-022-03380-0","article-title":"Surrogate modeling for injection molding processes using deep learning","volume":"65","author":"Uglov","year":"2022","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"2026040114402751400_bib35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.10903","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv preprint arXiv:1710.10903"},{"key":"2026040114402751400_bib36","doi-asserted-by":"publisher","first-page":"120842","DOI":"10.1016\/j.engstruct.2025.120842","article-title":"What lies within: Utilizing graph neural networks for subsurface detection in finite element simulations","volume":"341","author":"Yehia","year":"2025","journal-title":"Engineering Structures"},{"key":"2026040114402751400_bib37","doi-asserted-by":"publisher","first-page":"1599","DOI":"10.1002\/pen.760302408","article-title":"Thermal contact resistance in injection molding","volume":"30","author":"Yu","year":"1990","journal-title":"Polymer Engineering & Science"},{"key":"2026040114402751400_bib38","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s00170-022-08859-0","article-title":"Recent progress in minimizing the warpage and shrinkage deformations by the optimization of process parameters in plastic injection molding: A review","volume":"120","author":"Zhao","year":"2022","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"2026040114402751400_bib39","doi-asserted-by":"publisher","first-page":"e56997","DOI":"10.1002\/app.56997","article-title":"Simulation and experimental study of the flow mechanism of injection-molded materials for optical non-spherical cylindrical lens","volume":"142","author":"Zhou","year":"2025","journal-title":"Journal of Applied Polymer Science"}],"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\/qwag026\/67434127\/qwag026.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/4\/67\/67434127\/qwag026.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/4\/67\/67434127\/qwag026.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:40:33Z","timestamp":1775068833000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/13\/4\/67\/8530552"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwag026","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,3,20]]}}}