{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:35:26Z","timestamp":1761179726819,"version":"build-2065373602"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB4608700"],"award-info":[{"award-number":["2024YFB4608700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei Province Key Industries Innovation and Development Fund"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042024kf0015"],"award-info":[{"award-number":["2042024kf0015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In additive manufacturing (AM), in situ monitoring of the melting pool and plasma arc status is crucial for ensuring workpiece quality. However, existing monitoring algorithms based on image segmentation typically require substantial amounts of high-quality training data. Furthermore, these algorithms lack the versatility necessary for deployment across various types of AM equipment. The recently proposed segment anything model (SAM) demonstrates strong generalization capabilities through its novel interactive image segmentation framework. However, its extensive network parameters hinder direct application in the field of AM in situ monitoring. To solve these problems, this paper presents a lightweight, general-purpose image segmentation algorithm called Light SAM, which is capable of performing cross-process feature extraction. The characteristics of the melt pool in the L-DED (laser directed energy deposition) and L-PBF (laser powder bed fusion) processes, as well as the plasma arc in the PAM process, can be extracted using only 190 training images. Mean intersection over union (MIoU) was chosen as the primary evaluation metric. Under the same training strategy, the four most advanced image segmentation algorithms demonstrated poor generalization compared with alternative methods, whereas Light SAM exhibited strong generalization, achieving an MIoU of 93.02%. Additionally, while its performance is comparable to that of the original SAM, its model size is only 23 MB. Moreover, the Light SAM algorithm can be integrated into the AI edge computing board, achieving an inference time of just 153 ms under Neural-network Processing Unit (NPU) acceleration following model pruning optimization, which meets the requirements of AM real-time monitoring. In addition to meeting the requirements of inference speed and accuracy, the algorithm can simultaneously extract multiple target features by manually inputting several bounding boxes to guide its processing. Furthermore, the algorithm significantly reduces training costs and time, and can be deployed in cross-process AM monitoring systems, thereby facilitating the widespread adoption of in situ monitoring technologies in AM.<\/jats:p>","DOI":"10.1093\/jcde\/qwaf057","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T07:52:14Z","timestamp":1750924334000},"page":"35-48","source":"Crossref","is-referenced-by-count":0,"title":["Universal light SAM algorithm for in situ melting pool monitoring of L-DED\/L-PBF\/PAM processes"],"prefix":"10.1093","volume":"12","author":[{"given":"Jiahong","family":"Chen","sequence":"first","affiliation":[{"name":"Wuhan University School of Power and Mechanical Engineering, , Wuhan, Hubei 430072 ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4404-8845","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University School of Power and Mechanical Engineering, , Wuhan, Hubei 430072 ,","place":["China"]},{"name":"Wuhan University The Institute of Technological Sciences, , Wuhan, Hubei 430074 ,","place":["China"]},{"name":"Ltd Huangshi Innovation Electronic Information Institute Co., , Huangshi, Hubei 435000 ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3964-8475","authenticated-orcid":false,"given":"Shengnan","family":"Shen","sequence":"additional","affiliation":[{"name":"Wuhan University School of Power and Mechanical Engineering, , Wuhan, Hubei 430072 ,","place":["China"]}]},{"given":"Yingjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University The Institute of Technological Sciences, , Wuhan, Hubei 430074 ,","place":["China"]}]},{"given":"Rongzhe","family":"Ma","sequence":"additional","affiliation":[{"name":"Wuhan University School of Power and Mechanical Engineering, , Wuhan, Hubei 430072 ,","place":["China"]}]},{"given":"Haoyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Extra High Voltage Company State Grid Hubei Electric Power Co., Ltd, , Wuhan, Hubei 430050 ,","place":["China"]}]},{"given":"Hong","family":"Yin","sequence":"additional","affiliation":[{"name":"Extra High Voltage Company State Grid Hubei Electric Power Co., Ltd, , Wuhan, Hubei 430050 ,","place":["China"]}]},{"given":"Liwei","family":"Xia","sequence":"additional","affiliation":[{"name":"Extra High Voltage Company State Grid Hubei Electric Power Co., Ltd, , Wuhan, Hubei 430050 ,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"key":"2025102210120731200_bib1","doi-asserted-by":"publisher","first-page":"1687814018822880","DOI":"10.1177\/1687814018822880","article-title":"Additive manufacturing: Challenges, trends, and applications","volume":"11","author":"Abdulhameed","year":"2019","journal-title":"Advances in Mechanical Engineering"},{"key":"2025102210120731200_bib2","first-page":"2","article-title":"OpenCV","volume":"3","author":"Bradski","year":"2000","journal-title":"Dr. Dobb's Journal of Software Tools"},{"key":"2025102210120731200_bib3","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1016\/j.jcde.2019.02.001","article-title":"Maintenance in aeronautics in an Industry 4.0 context: The role of augmented reality and additive manufacturing","volume":"6","author":"Ceruti","year":"2019","journal-title":"Journal of Computational Design and Engineering"},{"key":"2025102210120731200_bib4","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.1038\/s41467-024-47257-w","article-title":"Powder-size driven facile microstructure control in powder-fusion metal additive manufacturing processes","volume":"15","author":"Chandra","year":"2024","journal-title":"Nature Communications"},{"key":"2025102210120731200_bib5","doi-asserted-by":"publisher","first-page":"126735","DOI":"10.1016\/j.ijheatmasstransfer.2025.126735","article-title":"Characterising and modelling plasma transferred arc for additive manufacturing","volume":"241","author":"Chen","year":"2025","journal-title":"International Journal of Heat and Mass Transfer"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"2025102210120731200_bib6"},{"key":"2025102210120731200_bib7","doi-asserted-by":"publisher","first-page":"111655","DOI":"10.1016\/j.measurement.2022.111655","article-title":"Fast vehicle detection algorithm in traffic scene based on improved SSD","volume":"201","author":"Chen","year":"2022","journal-title":"Measurement"},{"key":"2025102210120731200_bib8","doi-asserted-by":"publisher","first-page":"105069","DOI":"10.1016\/j.autcon.2023.105069","article-title":"Efficient railway track region segmentation algorithm based on lightweight neural network and cross-fusion decoder","volume":"155","author":"Chen","year":"2023","journal-title":"Automation in Construction"},{"key":"2025102210120731200_bib9","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s41597-024-02918-9","article-title":"RailFOD23: A dataset for foreign object detection on railroad transmission lines","volume":"11","author":"Chen","year":"2024","journal-title":"Scientific Data"},{"key":"2025102210120731200_bib10","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.addma.2019.03.015","article-title":"Additive manufacturing of medical instruments: A state-of-the-art review","volume":"27","author":"Culmone","year":"2019","journal-title":"Additive Manufacturing"},{"key":"2025102210120731200_bib11","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.matdes.2016.01.099","article-title":"Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing","volume":"95","author":"Everton","year":"2016","journal-title":"Materials & Design"},{"key":"2025102210120731200_bib12","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.jmapro.2021.05.052","article-title":"In-situ capture of melt pool signature in selective laser melting using U-Net-based convolutional neural network","volume":"68","author":"Fang","year":"2021","journal-title":"Journal of Manufacturing Processes"},{"key":"2025102210120731200_bib13","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1007\/s11665-014-0958-z","article-title":"Metal additive manufacturing: A review","volume":"23","author":"Frazier","year":"2014","journal-title":"Journal of Materials Engineering and Performance"},{"key":"2025102210120731200_bib14","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"2025102210120731200_bib15","doi-asserted-by":"publisher","first-page":"105262","DOI":"10.1016\/j.autcon.2023.105262","article-title":"3D vision technologies for a self-developed structural external crack damage recognition robot","volume":"159","author":"Hu","year":"2024","journal-title":"Automation in Construction"},{"key":"2025102210120731200_bib16","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/s40516-019-00096-w","article-title":"Experimental microstructure evaluation of Rene 80 in laser cladding","volume":"6","author":"Huarte-Mendicoa","year":"2019","journal-title":"Lasers in Manufacturing and Materials Processing"},{"key":"2025102210120731200_bib17","doi-asserted-by":"publisher","first-page":"20384","DOI":"10.1038\/s41598-022-24828-9","article-title":"Spattering mechanism of laser powder bed fusion additive manufacturing on heterogeneous surfaces","volume":"12","author":"Ikeshoji","year":"2022","journal-title":"Scientific Reports"},{"key":"2025102210120731200_bib18","first-page":"4015","volume-title":"Segment anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kirillov","year":"2023"},{"key":"2025102210120731200_bib19","doi-asserted-by":"publisher","first-page":"107941","DOI":"10.1016\/j.knosys.2021.107941","article-title":"Deep embedded hybrid CNN\u2013LSTM network for lane detection on NVIDIA Jetson Xavier NX","volume":"240","author":"Kortli","year":"2022","journal-title":"Knowledge-based Systems"},{"key":"2025102210120731200_bib20","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10845-022-02029-5","article-title":"Machine learning techniques in additive manufacturing: A state of the art review on design, processes and production control","volume":"34","author":"Kumar","year":"2023","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2025102210120731200_bib21","doi-asserted-by":"publisher","first-page":"109802","DOI":"10.1016\/j.engappai.2024.109802","volume":"141","author":"Kuriachen","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"2025102210120731200_bib22","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.3390\/mi13081366","article-title":"A review of spatter in laser powder bed fusion additive manufacturing: In situ detection, generation, effects, and countermeasures","volume":"13","author":"Li","year":"2022","journal-title":"Micromachines"},{"key":"2025102210120731200_bib23","first-page":"14420","article-title":"Efficientvit: Memory efficient vision transformer with cascaded group attention","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2023"},{"key":"2025102210120731200_bib24","doi-asserted-by":"publisher","first-page":"111727","DOI":"10.1016\/j.optlastec.2024.111727","article-title":"In-situ video frame interpolation and super resolution reconstruction for accurate monitoring of L-PBF process","volume":"181","author":"Ma","year":"2025","journal-title":"Optics & Laser Technology"},{"key":"2025102210120731200_bib25","doi-asserted-by":"publisher","first-page":"102058","DOI":"10.1016\/j.addma.2021.102058","article-title":"In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: A review","volume":"45","author":"McCann","year":"2021","journal-title":"Additive Manufacturing"},{"key":"2025102210120731200_bib26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10845-021-01820-0","article-title":"In-situ monitoring laser based directed energy deposition process with deep convolutional neural network","author":"Mi","year":"2023","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2025102210120731200_bib27","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015: 18th International Conference","author":"Ronneberger","year":"2015"},{"key":"2025102210120731200_bib28","doi-asserted-by":"publisher","first-page":"103732","DOI":"10.1016\/j.advengsoft.2024.103732","article-title":"Enhancing lecture capture with deep learning","volume":"196","author":"Sales","year":"2024","journal-title":"Advances in Engineering Software"},{"key":"2025102210120731200_bib29","doi-asserted-by":"publisher","first-page":"2297051","DOI":"10.1080\/26889277.2023.2297051","article-title":"Computational welding simulation of a plasma wire arc additive manufacturing process for high-strength steel","volume":"4","author":"Sch\u00f6negger","year":"2024","journal-title":"European Journal of Materials"},{"key":"2025102210120731200_bib30","doi-asserted-by":"publisher","first-page":"12224","DOI":"10.1038\/s41598-021-91039-z","article-title":"A critical look at the prediction of the temperature field around a laser-induced melt pool on metallic substrates","volume":"11","author":"Shu","year":"2021","journal-title":"Scientific Reports"},{"key":"2025102210120731200_bib31","doi-asserted-by":"publisher","first-page":"106347","DOI":"10.1016\/j.optlastec.2020.106347","article-title":"Neural network based image segmentation for spatter extraction during laser-based powder bed fusion processing","volume":"130","author":"Tan","year":"2020","journal-title":"Optics & Laser Technology"},{"key":"2025102210120731200_bib32","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025102210120731200_bib33","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1109\/JAS.2023.123618","article-title":"A brief overview of ChatGPT: The history, status quo and potential future development","volume":"10","author":"Wu","year":"2023","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"2025102210120731200_bib34","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","article-title":"Wider or deeper: Revisiting the resnet model for visual recognition","volume":"90","author":"Wu","year":"2019","journal-title":"Pattern Recognition"},{"key":"2025102210120731200_bib35","doi-asserted-by":"publisher","first-page":"9940881","DOI":"10.1155\/2023\/9940881","article-title":"Enhanced precision in dam crack width measurement: Leveraging advanced lightweight network identification for pixel-level accuracy","volume":"2023","author":"Wu","year":"2023","journal-title":"International Journal of Intelligent Systems"},{"key":"2025102210120731200_bib36","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.neucom.2022.05.053","article-title":"\u03c9-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution","volume":"500","author":"Xu","year":"2022","journal-title":"Neurocomputing"},{"key":"2025102210120731200_bib37","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1109\/TCSVT.2022.3202574","article-title":"Solve the puzzle of instance segmentation in videos: A weakly supervised framework with spatio-temporal collaboration","volume":"33","author":"Yan","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2025102210120731200_bib38","doi-asserted-by":"publisher","first-page":"106371","DOI":"10.1016\/j.optlastec.2020.106371","article-title":"In situ capture of spatter signature of SLM process using maximum entropy double threshold image processing method based on genetic algorithm","volume":"131","author":"Yang","year":"2020","journal-title":"Optics & Laser Technology"},{"key":"2025102210120731200_bib39","doi-asserted-by":"publisher","first-page":"200199","DOI":"10.1016\/j.amf.2025.200199","article-title":"High-precision and ultraspeed monitoring of melt-pool morphology in laser-directed energy deposition using deep learning","author":"Yang","year":"2025","journal-title":"Additive Manufacturing Frontiers"},{"key":"2025102210120731200_bib40","doi-asserted-by":"publisher","first-page":"041701","DOI":"10.1115\/1.4032504","article-title":"A cost-driven design methodology for additive manufactured variable platforms in product families","volume":"138","author":"Yao","year":"2016","journal-title":"Journal of Mechanical Design"},{"key":"2025102210120731200_bib41","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1007\/s00170-022-08929-3","article-title":"In situ monitoring plasma arc additive manufacturing process with a fully convolutional network","volume":"120","author":"Zhang","year":"2022","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"2025102210120731200_bib42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00170-022-10178-3","article-title":"Review of in situ and real-time monitoring of metal additive manufacturing based on image processing","volume":"123","author":"Zhang","year":"2022","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"2025102210120731200_bib43","first-page":"2881","article-title":"Pyramid scene parsing network","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2017"},{"key":"2025102210120731200_bib44","doi-asserted-by":"publisher","first-page":"110423","DOI":"10.1016\/j.optlastec.2023.110423","article-title":"In-situ monitoring additive manufacturing process with AI edge computing","volume":"171","author":"Zhu","year":"2024","journal-title":"Optics & Laser Technology"}],"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\/qwaf057\/63607409\/qwaf057.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/12\/7\/35\/63607409\/qwaf057.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/12\/7\/35\/63607409\/qwaf057.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T14:12:15Z","timestamp":1761142335000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/12\/7\/35\/8176681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":44,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7,11]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwaf057","relation":{},"ISSN":["2288-5048"],"issn-type":[{"type":"electronic","value":"2288-5048"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,6,27]]}}}