{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T04:30:44Z","timestamp":1728534644831},"reference-count":24,"publisher":"Walter de Gruyter GmbH","issue":"10","funder":[{"name":"Bundesministerium f\u00fcr Bildung und Forschung \u2013 BMBF) as part of the programme \u2018Anwendung von Methoden der K\u00fcnstlichen Intelligenz in der Praxis\u2019","award":["01IS20001F"],"award-info":[{"award-number":["01IS20001F"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"abstract":"<jats:title>Zusammenfassung<\/jats:title>\n               <jats:p>Die additive Fertigung mittels DED-Arc-Verfahren ist durch die hohen Fertigungszeiten ein kostenintensiver Prozess. Die klassischen Qualit\u00e4tspr\u00fcfverfahren, die der Fertigung nachgelagert sind, geben erst nach Fertigstellung des Werkst\u00fcckes Aufschluss \u00fcber die erreichte Qualit\u00e4t. Nacharbeiten sind h\u00e4ufig ausgeschlossen, sodass bei unzureichender Qualit\u00e4t das Bauteil dem Ausschuss zugef\u00fchrt wird. Die Anwendung von <jats:italic>in situ<\/jats:italic> Qualit\u00e4tskontrollen erm\u00f6glicht es, Unregelm\u00e4\u00dfigkeiten fr\u00fchzeitig bereits w\u00e4hrend des eigentlichen Aufbauprozess zu erkennen und eine direkte Nacharbeit kann stattfinden. Die akustischen Emissionen werden bereits erfolgreich von erfahrenen Schwei\u00dfern als Qualit\u00e4tsmerkmal f\u00fcr den Prozess eingesetzt. In diesem Beitrag soll mit Hilfe der akustischen Signale, die w\u00e4hrend des Schwei\u00dfens entstehen, die Prozessqualit\u00e4t vorhergesagt werden. Dabei liegt der Fokus auf der Erkennung des Schutzgasflusses und eventuell vorhandener Oberfl\u00e4chenverunreinigung durch \u00d6l. Dies kann ma\u00dfgeblich zur Bildung von Poren innerhalb der entstehenden Schwei\u00dfraupen beitragen. Zur Erkennung dieser Parameter wird die Verwendung eines Convolutional Neural Networks (CNN) zur Auswertung des emittierten Luftschalls diskutiert. Als wesentliches Merkmal zur Klassifizierung werden die, in der Sprecher- und Spracherkennung verbreiteten, Mel-Cepstralkoeffizienten (MFCC) herangezogen. Des Weiteren wird der Einfluss der Netzwerkparameter des CNN auf die Klassifizierungsg\u00fcte des resultierenden Netzwerkes dargestellt. Es zeigt sich, dass die ausschlie\u00dfliche Verwendung der MFCC dem CNN erm\u00f6glicht Prozessabweichungen zu detektieren. Aufgrund der hohen Informationsdichte der MFCC gegen\u00fcber dem STFT-Spektrum bieten erstere die M\u00f6glichkeit die Gr\u00f6\u00dfe des verwendeten CNN erheblich zu reduzieren.<\/jats:p>","DOI":"10.1515\/auto-2024-0030","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T16:27:12Z","timestamp":1728491232000},"page":"991-1001","source":"Crossref","is-referenced-by-count":0,"title":["Detektion von Prozessunregelm\u00e4\u00dfigkeiten beim MSG-Schwei\u00dfen durch Analyse des Luftschallsignals mittels Convolutional Neural Network (CNN)"],"prefix":"10.1515","volume":"72","author":[{"given":"Julian","family":"Br\u00fcckner","sequence":"first","affiliation":[{"name":"Fachgebiet Fertigungstechnik, Fakult\u00e4t f\u00fcr Maschinenbau , TU Ilmenau , Gustav-Kirchhoff-Platz 2, 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Rohe","sequence":"additional","affiliation":[{"name":"Fachgebiet Fertigungstechnik, Fakult\u00e4t f\u00fcr Maschinenbau , TU Ilmenau , Gustav-Kirchhoff-Platz 2, 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik","family":"Walther","sequence":"additional","affiliation":[{"name":"Fachgebiet Data-intensive Systems and Visualization Group (dAI.SY), Fakult\u00e4t Informatik und Automatisierung , TU Ilmenau , Helmholtzplatz 5 , 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00f6rg","family":"Hildebrand","sequence":"additional","affiliation":[{"name":"Fachgebiet Fertigungstechnik, Fakult\u00e4t f\u00fcr Maschinenbau , TU Ilmenau , Gustav-Kirchhoff-Platz 2, 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean Pierre","family":"Bergmann","sequence":"additional","affiliation":[{"name":"Fachgebiet Fertigungstechnik, Fakult\u00e4t f\u00fcr Maschinenbau , TU Ilmenau , Gustav-Kirchhoff-Platz 2, 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"M\u00e4der","sequence":"additional","affiliation":[{"name":"Fachgebiet Data-intensive Systems and Visualization Group (dAI.SY), Fakult\u00e4t Informatik und Automatisierung , TU Ilmenau , Helmholtzplatz 5 , 98693 Ilmenau , Deutschland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2024,10,9]]},"reference":[{"key":"2024100916475776276_j_auto-2024-0030_ref_001","doi-asserted-by":"crossref","unstructured":"J. C. Najmon, S. Raeisi, and A. Tovar, \u201c2 \u2013 review of additive manufacturing technologies and applications in the aerospace industry,\u201d Addit. Manuf. Aerosp. Ind., pp. 7\u201331, 2019. https:\/\/doi.org\/10.1016\/B978-0-12-814062-8.00002-9.","DOI":"10.1016\/B978-0-12-814062-8.00002-9"},{"key":"2024100916475776276_j_auto-2024-0030_ref_002","doi-asserted-by":"crossref","unstructured":"A. Lopez, R. Bacelar, I. Pires, T. G. Santos, J. P. Sousa, and L. Quintino, \u201cNon-destructive testing application of radiography and ultrasound for wire and arc additive manufacturing,\u201d Addit. Manuf., vol. 21, pp. 298\u2013306, 2018. https:\/\/doi.org\/10.1016\/j.addma.2018.03.020.","DOI":"10.1016\/j.addma.2018.03.020"},{"key":"2024100916475776276_j_auto-2024-0030_ref_003","doi-asserted-by":"crossref","unstructured":"M. Kusch, K.-J. Matthes, and W. Schneider, Eds. Schwei\u00dftechnik: Schwei\u00dfen von metallischen Konstruktionswerkstoffen, 7th ed. M\u00fcnchen, Hanser, 2022.","DOI":"10.3139\/9783446470002"},{"key":"2024100916475776276_j_auto-2024-0030_ref_004","doi-asserted-by":"crossref","unstructured":"L. Cai, J. Gao, and D. Zhao, \u201cA review of the application of deep learning in medical image classification and segmentation,\u201d Ann. Trans. Med., vol.\u00a08, no.\u00a011, p.\u00a0713, 2020. https:\/\/doi.org\/10.21037\/atm.2020.02.44.","DOI":"10.21037\/atm.2020.02.44"},{"key":"2024100916475776276_j_auto-2024-0030_ref_005","doi-asserted-by":"crossref","unstructured":"M. Pak and S. Kim, \u201cA review of deep learning in image recognition,\u201d in Proceedings of the 2017 4th International Conference on Computer Applications and Information Processing Technology (CAIPT): August 8\u201310, 2017, Kuta Bali, Indonesia, Kuta Bali, 2017, pp.\u00a01\u20133.","DOI":"10.1109\/CAIPT.2017.8320684"},{"key":"2024100916475776276_j_auto-2024-0030_ref_006","doi-asserted-by":"crossref","unstructured":"F. Karim, S. Majumdar, H. Darabi, and S. Chen, \u201cLSTM fully convolutional networks for time series classification,\u201d IEEE Access, vol. 6, pp. 1662\u20131669, 2018. https:\/\/doi.org\/10.1109\/ACCESS.2017.2779939.","DOI":"10.1109\/ACCESS.2017.2779939"},{"key":"2024100916475776276_j_auto-2024-0030_ref_007","doi-asserted-by":"crossref","unstructured":"B. D. Fulcher and N. S. Jones, \u201cHighly comparative feature-based time-series classification,\u201d IEEE Trans. Knowl. Data Eng., vol.\u00a026, no.\u00a012, pp.\u00a03026\u20133037, 2014. https:\/\/doi.org\/10.1109\/TKDE.2014.2316504.","DOI":"10.1109\/TKDE.2014.2316504"},{"key":"2024100916475776276_j_auto-2024-0030_ref_008","unstructured":"S. Bai, J. Z. Kolter, and V. Koltun, \u201cAn empirical evaluation of generic convolutional and recurrent networks for sequence modeling,\u201d 2018 [Online]. Available at: http:\/\/arxiv.org\/pdf\/1803.01271.pdf."},{"key":"2024100916475776276_j_auto-2024-0030_ref_009","unstructured":"I. Goodfellow, Y. Bengio, and A. Courville, Deep learning: Das umfassende Handbuch : Grundlagen, aktuelle Verfahren und Algorithmen, neue Forschungsans\u00e4tze, 1st ed. Frechen, mitp, 2018."},{"key":"2024100916475776276_j_auto-2024-0030_ref_010","unstructured":"K. O\u2019Shea and R. Nash, \u201cAn introduction to convolutional neural networks,\u201d 2015. https:\/\/arxiv.org\/abs\/1511.08458."},{"key":"2024100916475776276_j_auto-2024-0030_ref_011","doi-asserted-by":"crossref","unstructured":"D. T. Thekkuden and A.-H. I. Mourad, \u201cInvestigation of feed-forward back propagation ANN using voltage signals for the early prediction of the welding defect,\u201d SN Appl. Sci., vol.\u00a01, no.\u00a012, pp.\u00a01\u201317, 2019. https:\/\/doi.org\/10.1007\/s42452-019-1660-4.","DOI":"10.1007\/s42452-019-1660-4"},{"key":"2024100916475776276_j_auto-2024-0030_ref_012","doi-asserted-by":"crossref","unstructured":"E. H. Cayo and S. C. A. Alfaro, \u201cA non-intrusive GMA welding process quality monitoring system using acoustic sensing,\u201d Sensors, vol.\u00a09, no.\u00a09, pp.\u00a07150\u20137166, 2009. https:\/\/doi.org\/10.3390\/s90907150.","DOI":"10.3390\/s90907150"},{"key":"2024100916475776276_j_auto-2024-0030_ref_013","unstructured":"Y. Arata, K. Inoue, M. Futamata, and T. Toh, \u201cInvestigation on welding arc sound (report I): effect of welding method and welding condition of welding arc sound(welding physics, processes & instruments),\u201d Trans. JWRI, vol.\u00a08, no.\u00a01, pp.\u00a025\u201331, 1979. https:\/\/doi.org\/10.18910\/9846."},{"key":"2024100916475776276_j_auto-2024-0030_ref_014","doi-asserted-by":"crossref","unstructured":"T. Hauser, R. T. Reisch, T. Kamps, A. F. H. Kaplan, and J. Volpp, \u201cAcoustic emissions in directed energy deposition processes,\u201d Int. J. Adv. Manuf. Technol., vol.\u00a0119, nos. 5\u20136, pp.\u00a03517\u20133532, 2022. https:\/\/doi.org\/10.1007\/s00170-021-08598-8.","DOI":"10.1007\/s00170-021-08598-8"},{"key":"2024100916475776276_j_auto-2024-0030_ref_015","doi-asserted-by":"crossref","unstructured":"A. Ramalho, T. G. Santos, B. Bevans, Z. Smoqi, P. Rao, and J. P. Oliveira, \u201cEffect of contaminations on the acoustic emissions during wire and arc additive manufacturing of 316L stainless steel,\u201d Addit. Manuf., vol. 51, p. 102585, 2022. https:\/\/doi.org\/10.1016\/j.addma.2021.102585.","DOI":"10.1016\/j.addma.2021.102585"},{"key":"2024100916475776276_j_auto-2024-0030_ref_016","doi-asserted-by":"crossref","unstructured":"B. Bevans, et al.., \u201cMonitoring and flaw detection during wire-based directed energy deposition using in-situ acoustic sensing and wavelet graph signal analysis,\u201d Mater. Des., vol. 225, p. 111480, 2023. https:\/\/doi.org\/10.1016\/j.matdes.2022.111480.","DOI":"10.1016\/j.matdes.2022.111480"},{"key":"2024100916475776276_j_auto-2024-0030_ref_017","doi-asserted-by":"crossref","unstructured":"P. Galani, et al.., \u201cOnline sound based arc-welding defect detection using artificial neural networks,\u201d in 2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposium on Robotics (SBR) and 2019 Workshop on Robotics in Education (WRE), Rio Grande, Brazil, 2019, pp.\u00a0263\u2013268.","DOI":"10.1109\/LARS-SBR-WRE48964.2019.00053"},{"key":"2024100916475776276_j_auto-2024-0030_ref_018","unstructured":"S. Zelazny and M. Kolek, Analysis of the Welding Process Sound Using Convolutional Neural Networks for Penetration State Recognition, Aalborg, Aalborg Universitet, 2020."},{"key":"2024100916475776276_j_auto-2024-0030_ref_019","doi-asserted-by":"crossref","unstructured":"M. Rohe, B. N. Stoll, J. Hildebrand, J. Reimann, and J. P. Bergmann, \u201cDetecting process anomalies in the GMAW process by acoustic sensing with a convolutional neural network (CNN) for classification,\u201d JMMP, vol.\u00a05, no.\u00a04, p.\u00a0135, 2021. https:\/\/doi.org\/10.3390\/jmmp5040135.","DOI":"10.3390\/jmmp5040135"},{"key":"2024100916475776276_j_auto-2024-0030_ref_020","doi-asserted-by":"crossref","unstructured":"S. Gourishetti, et al.., \u201cD7.2 \u2013 arc welding process monitoring using neural networks and audio signal analysis,\u201d in Lectures, N\u00fcrnberg, 2023, pp.\u00a0249\u2013250.","DOI":"10.5162\/SMSI2023\/D7.2"},{"key":"2024100916475776276_j_auto-2024-0030_ref_021","doi-asserted-by":"crossref","unstructured":"Y. Cui, Y. Shi, T. Zhu, and S. Cui, \u201cWelding penetration recognition based on arc sound and electrical signals in K-TIG welding,\u201d Measurement, vol.\u00a0163, p.\u00a0107966, 2020, https:\/\/doi.org\/10.1016\/j.measurement.2020.107966.","DOI":"10.1016\/j.measurement.2020.107966"},{"key":"2024100916475776276_j_auto-2024-0030_ref_022","doi-asserted-by":"crossref","unstructured":"N. A. Surovi, A. G. Dharmawan, and G. S. Soh, \u201cA study on the acoustic signal based frameworks for the real-time identification of geometrically defective wire arc bead,\u201d in ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference Volume 3A: 47th Design Automation Conference (DAC), Virtual, Online, 2021.","DOI":"10.1115\/DETC2021-69573"},{"key":"2024100916475776276_j_auto-2024-0030_ref_023","doi-asserted-by":"crossref","unstructured":"N. A. Surovi and G. S. Soh, \u201cAcoustic feature based geometric defect identification in wire arc additive manufacturing,\u201d Virtual and Physical Prototyping, vol. 18, no. 1, 2023. https:\/\/doi.org\/10.1080\/17452759.2023.2210553.","DOI":"10.1080\/17452759.2023.2210553"},{"key":"2024100916475776276_j_auto-2024-0030_ref_024","unstructured":"D. P. Kingma and J. Ba, \u201cAdam: a method for stochastic optimization,\u201d 2014. https:\/\/arxiv.org\/abs\/1412.6980."}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2024-0030\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2024-0030\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T16:49:05Z","timestamp":1728492545000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2024-0030\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":24,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,9]]},"published-print":{"date-parts":[[2024,10,28]]}},"alternative-id":["10.1515\/auto-2024-0030"],"URL":"https:\/\/doi.org\/10.1515\/auto-2024-0030","relation":{},"ISSN":["0178-2312","2196-677X"],"issn-type":[{"value":"0178-2312","type":"print"},{"value":"2196-677X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]}}}