{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T11:04:10Z","timestamp":1789470250827,"version":"build-2803163510"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    With the fifth industrial revolution, additive manufacturing (AM) is being extensively employed in industries including manufacturing, automotive, aerospace, medical, and energy. It is now accepted as a state-of-the-art and innovative way of producing complex parts that can exhibit enhanced mechanical properties and fewer design constraints. However, AM creates unique challenges in maintaining the quality and reliability of manufactured components. Addressing the detection and classification of defects induced by AM processes including cracking, porosity, lack of fusion, delamination and surface irregularities, during and after manufacturing is therefore critical. Traditional non-destructive testing (NDT) techniques including ultrasound testing, X-ray computed tomography (XCT), optical or microscopy based methods and thermography, provide reliable defect detection but are often slow, operator dependent, and poorly suited to\n                    <jats:italic>in-situ<\/jats:italic>\n                    , layer-by-layer monitoring. Over the past decade, the consolidation of data-driven i.e., machine learning (ML) and deep learning (DL) models with these NDT modalities have emerged as a promising route toward faster, more automated, real-time\n                    <jats:italic>in-situ<\/jats:italic>\n                    monitoring and control, predictive analytics for maintenance and qualification decisions. This review synthesizes 50 studies spanning thermographic, ultrasonic, acoustic, optical, and computed tomography-based NDT approaches combined with ML models ranging from convolutional neural networks (CNNs) to physics-informed learning frameworks. A structured methodology, classification table, and comparative performance analysis of ML algorithms are presented, followed by a discussion of advantages, limitations, and open research gaps. This review finds that thermography-based approaches dominate the literature, the CNN-based deep learning models generally report the highest classification accuracies (90%\u221299%), and physics-informed and hybrid ML approaches offer improved generalization for process control. The challenges include limited standardized datasets, inconsistent qualification frameworks and the computational demands of real-time deployment. This review concludes with recommendations for standardized benchmark datasets, multi-modal fusion, physics-informed and explainable AI models, and real-time closed-loop process control, all aimed at advancing data-driven NDT from laboratory demonstration toward industrial qualification of additively manufactured components.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1914473","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:20:21Z","timestamp":1789467621000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Data driven algorithmic advances in defect detection of additively manufactured materials using non-destructive testing: a review"],"prefix":"10.3389","volume":"9","author":[{"given":"Smita","family":"Pawar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, MIT School of Computing, MIT Art, Design and Technology University","place":["Pune, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramachandra","family":"Pujeri","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, MIT School of Computing, MIT Art, Design and Technology University","place":["Pune, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachin","family":"Pawar","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, MIT School of Engineering and Sciences, MIT Art, Design and Technology University","place":["Pune, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suvarna","family":"Pawar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, MIT School of Computing, MIT Art, Design and Technology University","place":["Pune, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daria","family":"Derusova","sequence":"additional","affiliation":[{"name":"School of Non-destructive Testing, Tomsk Polytechnic University","place":["Tomsk, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"111063","DOI":"10.1016\/j.matdes.2022.111063","article-title":"In-situ monitoring of sub-surface and internal defects in additive manufacturing: a review","volume":"222","author":"AbouelNour","year":"2022","journal-title":"Mater. Des."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e13401","DOI":"10.5121\/ijaia.2022.13401","article-title":"A deep learning approach for defect detection and segmentation in X-ray computed tomography slices of additively manufactured components","volume":"13","author":"Acharya","year":"2022","journal-title":"Int. J. Artif. Intell. Appl."},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.1520\/ISO\/ASTMTR52905-EB","volume-title":"Additive Manufacturing of Metals - Nondestructive Testing and Evaluation - Defect Detection in Parts","author":"ASTM International","year":"2023"},{"key":"B4","article-title":"\u201cStandard terminology for additive manufacturing technologies,\u201d","volume-title":"ASTM F2792 - 10e1","year":"2012"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704633","article-title":"A Comprehensive survey on machine learning driven material defect detection","volume":"57","author":"Bai","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"B6","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s40964-019-00108-3","article-title":"A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring","volume":"5","author":"Baumgartl","year":"2020","journal-title":"Prog. Addit. Manuf."},{"key":"B7","doi-asserted-by":"publisher","first-page":"8944","DOI":"10.1038\/s41598-022-12503-y","article-title":"Integration of thermal imaging and neural networks for mechanical strength analysis and fracture prediction in 3D-printed plastic parts","volume":"12","author":"Boiko","year":"2022","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/j.promfg.2020.05.091","article-title":"Real-time defect correction in large-scale polymer additive manufacturing via thermal imaging and laser profilometer","volume":"48","author":"Borish","year":"2020","journal-title":"Proc. Manuf."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1080\/10589759.2025.2500552","article-title":"Evaluation of electromechanical impedance, modal and X-ray testing as non-destructive methods for additively manufactured plastics","volume":"41","author":"\u00c7akir","year":"2026","journal-title":"Nondestruct. Test. Eval."},{"key":"B10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.prostr.2017.12.016","article-title":"Defect detection in additively manufactured components: laser ultrasound and laser thermography comparison","volume":"8","author":"Cerniglia","year":"2018","journal-title":"Proc. Struct. Integr."},{"key":"B11","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1007\/s11837-021-04757-0","article-title":"Artificial neural networks framework for detection of defects in 3D-printed fiber reinforcement composites","volume":"73","author":"Chen","year":"2021","journal-title":"JOM"},{"key":"B12","doi-asserted-by":"publisher","first-page":"103547","DOI":"10.1016\/j.addma.2023.103547","article-title":"In-situ crack and keyhole pore detection in laser directed energy deposition through acoustic signal and deep learning","volume":"69","author":"Chen","year":"2023","journal-title":"Addit. Manuf."},{"key":"B13","first-page":"1497","author":"Chen","year":"2019"},{"key":"B14","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1080\/17452759.2021.2018938","article-title":"A review on qualification and certification for metal additive manufacturing","volume":"17","author":"Chen","year":"2022","journal-title":"Virtual Phys. Prototyping"},{"key":"B15","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.procir.2022.08.037","article-title":"Defect detection in L-PBF metal additive manufacturing using on-line and off-line inspection processes","volume":"111","author":"Chicote","year":"2022","journal-title":"Proc. CIRP"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2571","DOI":"10.1007\/s00170-018-3046-y","article-title":"Laser ultrasonic inspection of additive manufactured components","volume":"102","author":"Davis","year":"2019","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1007\/s00170-024-14191-6","article-title":"Deep learning-based image segmentation for defect detection in additive manufacturing: an overview","volume":"134","author":"Deshpande","year":"2024","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"103262","DOI":"10.1016\/j.infrared.2020.103262","article-title":"Effects of crack surface roughness on crack heat generation characteristics of ultrasonic infrared thermography","volume":"106","author":"Dong","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"B19","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":"Mater. Des."},{"key":"B20","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s40964-024-00612-1","article-title":"Physics-informed machine learning for metal additive manufacturing","volume":"10","author":"Farrag","year":"2025","journal-title":"Prog. Addit. Manuf."},{"key":"B21","doi-asserted-by":"publisher","first-page":"014001","DOI":"10.1088\/2051-672X\/3\/1\/014001","article-title":"Characterization of typical surface effects in additive manufacturing with confocal microscopy","volume":"3","author":"Grimm","year":"2015","journal-title":"Surf. Topogr. Metrol. Prop."},{"key":"B22","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.jmsy.2021.11.003","article-title":"Machine learning for metal additive manufacturing: towards a physics-informed data-driven paradigm","volume":"62","author":"Guo","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"B23","volume-title":"Detection of Defects in Additively Manufactured Metallic Materials with Machine Learning of Pulsed Thermography Images (No. ANL-20\/57).","author":"Heifetz","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","first-page":"115100","DOI":"10.1109\/ACCESS.2021.3105362","article-title":"DLAM: deep learning based real-time porosity prediction for additive manufacturing using thermal images of the melt pool","volume":"9","author":"Ho","year":"2021","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"4695","DOI":"10.1007\/s11837-020-04438-4","article-title":"Physics-informed and hybrid machine learning in additive manufacturing: application to fused filament fabrication: Kapusuzoglu and Mahadevan","volume":"72","author":"Kapusuzoglu","year":"2020","journal-title":"Jom"},{"key":"B26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.15394\/ijaaa.2022.1708","article-title":"3D printing technology in aerospace industry\u2013a review","volume":"9","author":"Karkun","year":"2022","journal-title":"Int. J. Aviat. Aeronaut. Aerosp."},{"key":"B27","author":"Klamert","year":"2025","journal-title":"Machine learning approaches for process monitoring in powder bed fusion of polymers."},{"key":"B28","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.infrared.2012.01.001","article-title":"Quantification of defects in composites and rubber materials using active thermography","volume":"55","author":"Lahiri","year":"2012","journal-title":"Infrared Phys. Technol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1007\/s10845-025-02641-1","article-title":"Physics-informed machine learning in intelligent manufacturing: a review","volume":"37","author":"Leng","year":"2026","journal-title":"J. Intell. Manuf."},{"key":"B30","doi-asserted-by":"publisher","first-page":"121314","DOI":"10.1109\/ACCESS.2023.3328619","article-title":"Quality assessment of metal additive manufactured parts by a multiscale convolutional fuzzy neural network using ultrasound images as input data","volume":"11","author":"Lin","year":"2023","journal-title":"IEEE Access"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1007\/s00170-021-06640-3","article-title":"A physics-informed machine learning model for porosity analysis in laser powder bed fusion additive manufacturing","volume":"113","author":"Liu","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.addma.2018.03.020","article-title":"Non-destructive testing application of radiography and ultrasound for wire and arc additive manufacturing","volume":"21","author":"Lopez","year":"2018","journal-title":"Addit. Manuf."},{"key":"B33","doi-asserted-by":"publisher","first-page":"3263","DOI":"10.3390\/s20113263","article-title":"Thermography-based deterioration detection in concrete bridge girders strengthened with carbon fiber-reinforced polymer","volume":"20","author":"Mac","year":"2020","journal-title":"Sensors"},{"key":"B34","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.prostr.2018.11.098","article-title":"Defect detection in additively manufactured titanium prosthesis by flying laser scanning thermography","volume":"12","author":"Montinaro","year":"2018","journal-title":"Proc. Struct. Integr."},{"key":"B35","author":"Newcome","year":"2021","journal-title":"Non-destructive evaluation of 3D-printed parts using algorithm-aided infrared thermography."},{"key":"B36","first-page":"11","article-title":"\u201cComputer vision methods for non-destructive quality assessment in additive manufacturing,\u201d","volume-title":"International Conference on Computer Recognition Systems","author":"Okarma","year":"2019"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1007\/s10845-023-02117-0","article-title":"A deep learning framework for defect prediction based on thermographic in-situ monitoring in laser powder bed fusion","volume":"35","author":"Oster","year":"","journal-title":"J. Intell. Manuf."},{"key":"B38","doi-asserted-by":"publisher","first-page":"104502","DOI":"10.1016\/j.addma.2024.104502","article-title":"Local porosity prediction in metal powder bed fusion using in-situ thermography: a comparative study of machine learning techniques","volume":"95","author":"Oster","year":"","journal-title":"Addit. Manuf."},{"key":"B39","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1080\/17452759.2021.1966166","article-title":"Semi-supervised Monitoring of Laser powder bed fusion process based on acoustic emissions","volume":"16","author":"Pandiyan","year":"2021","journal-title":"Virt. Phys. Prototyping"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.3390\/pr8111464","article-title":"Real-time 3D printing remote defect detection (stringing) with computer vision and artificial intelligence","volume":"8","author":"Paraskevoudis","year":"2020","journal-title":"Processes"},{"key":"B41","doi-asserted-by":"publisher","first-page":"112140","DOI":"10.1016\/j.measurement.2022.112140","article-title":"Step heating thermography supported by machine learning and simulation for internal defect size measurement in additive manufacturing","volume":"205","author":"Rodr\u00edguez-Mart\u00edn","year":"2022","journal-title":"Measurement"},{"key":"B42","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/a16020095","article-title":"Defect detection methods for industrial products using deep learning techniques: a review","volume":"16","author":"Saberironaghi","year":"2023","journal-title":"Algorithms"},{"key":"B43","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s11837-015-1810-0","article-title":"Overview of materials qualification needs for metal additive manufacturing","volume":"68","author":"Seifi","year":"2016","journal-title":"Jom"},{"key":"B44","doi-asserted-by":"publisher","first-page":"3727","DOI":"10.3390\/ma15103727","article-title":"An evaluation of 3D-printed materials' structural properties using active infrared thermography and deep neural networks trained on the numerical data","volume":"15","author":"Szymanik","year":"2022","journal-title":"Materials"},{"key":"B45","doi-asserted-by":"publisher","first-page":"4168","DOI":"10.3390\/ma14154168","article-title":"Detection and identification of defects in 3D-printed dielectric structures via thermographic inspection and deep neural networks","volume":"14","author":"Szymanik","year":"2021","journal-title":"Materials"},{"key":"B46","first-page":"201","article-title":"\u201cThe role of computed tomography in additive manufacturing,\u201d","author":"Villarraga-G\u00f3mez","year":"2018","journal-title":"American Society for Precision Engineering, 2018 ASPE and EUSPEN Summer Topical Meeting: Advancing Precision in Additive Manufacturing, Vol. 69"},{"key":"B47","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.addma.2018.03.019","article-title":"Scanning optical microscopy for porosity quantification of additively manufactured components","volume":"21","author":"Wang","year":"2018","journal-title":"Addit. Manuf."},{"key":"B48","doi-asserted-by":"publisher","first-page":"14865","DOI":"10.1038\/s41598-024-64214-1","article-title":"Unsupervised learning-enabled pulsed infrared thermographic microscopy of subsurface defects in stainless steel","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"B49","doi-asserted-by":"publisher","first-page":"4682","DOI":"10.1007\/s11837-020-04408-w","article-title":"Quality control of additively manufactured metallic structures with machine learning of thermography images","volume":"72","author":"Zhang","year":"","journal-title":"Jom"},{"key":"B50","doi-asserted-by":"publisher","first-page":"4244","DOI":"10.1007\/s11837-020-04428-6","article-title":"Detection of defects in additively manufactured stainless steel 316L with compact infrared camera and machine learning algorithms","volume":"72","author":"Zhang","year":"","journal-title":"JOM"},{"key":"B51","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/EIT51626.2021.9491844","article-title":"\u201cSpatial temporal denoised thermal source separation in images of compact pulsed thermography system for qualification of additively manufactured metals,\u201d","author":"Zhang","year":"2021","journal-title":"IEEE, 2021 IEEE international conference on electro information technology (EIT)"},{"key":"B52","doi-asserted-by":"publisher","first-page":"166","DOI":"10.3390\/pr8111464","article-title":"Machine vision-based surface defect detection study for ceramic 3D printing","volume":"12","author":"Zhou","year":"2024","journal-title":"Machines"},{"key":"B53","doi-asserted-by":"publisher","first-page":"101183","DOI":"10.1016\/j.addma.2020.101183","article-title":"Unravelling pore evolution in post-processing of binder jetting materials: X-ray computed tomography, computer vision, and machine learning","volume":"34","author":"Zhu","year":"2020","journal-title":"Addit. Manuf."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1914473\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:20:23Z","timestamp":1789467623000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1914473\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":53,"alternative-id":["10.3389\/frai.2026.1914473"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1914473","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"article-number":"1914473"}}