{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:36:26Z","timestamp":1791570986756,"version":"4.3.4"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This study investigates the feasibility of acoustic signal analysis for the assessment of weld bead quality in the shielded metal arc welding (SMAW) process. The work focuses on comparing time-domain acoustic signals and time\u2013frequency spectrogram representations for the classification of welds as accepted or rejected according to standard welding inspection criteria. Two key acoustic descriptors, the fundamental frequency (F0) and the harmonics-to-noise ratio (HNR), were extracted and analyzed to evaluate statistical differences between the two weld quality classes. Statistical tests, including Anderson\u2013Darling, Levene, ANOVA, and Kruskal\u2013Wallis (\u03b1 = 0.05), revealed significant differences between accepted and rejected welds. Accepted welds exhibited a bimodal HNR distribution associated with transient arc instability at the beginning and end of the bead, whereas rejected welds showed more uniform acoustic behavior throughout the process. Subsequently, the acoustic data were represented using both audio signals and spectrograms and used as inputs for ten supervised machine learning models, including Support Vector Classifier (SVC), Logistic Regression (LR), k-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), and Na\u00efve Bayes (NB). The results demonstrate that spectrogram-based representations significantly outperform time-domain signals, achieving accuracies of 0.95\u20130.96, ROC-AUC values above 0.95, and false positive and false negative rates below 6%. These findings indicate that, while scalar acoustic descriptors provide statistically significant insight into weld quality, time\u2013frequency representations combined with machine learning enable a more robust and reliable framework for automated non-destructive evaluation, particularly in manual SMAW processes under realistic operating conditions.<\/jats:p>","DOI":"10.3390\/s26082357","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:29:29Z","timestamp":1776065369000},"page":"2357","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Time\u2013Frequency and Spectral Analysis of Welding Arc Sound for Automated SMAW Quality Classification"],"prefix":"10.3390","volume":"26","author":[{"given":"Alejandro","family":"Garc\u00eda Rodr\u00edguez","sequence":"first","affiliation":[{"name":"Facultad de Mec\u00e1nica, Escuela Tecnol\u00f3gica Instituto T\u00e9cnico Central, Calle 13 No. 16-74, Bogot\u00e1 111411, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian Camilo","family":"Barriga Castellanos","sequence":"additional","affiliation":[{"name":"Departamento de Ingenier\u00eda Industrial, Universidad Nacional de Colombia, Carrera 45 No. 26-85, Bogot\u00e1 111321, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jair Eduardo","family":"Rocha-Gonzalez","sequence":"additional","affiliation":[{"name":"Departamento de Ingenier\u00eda Industrial, Universidad Nacional de Colombia, Carrera 45 No. 26-85, Bogot\u00e1 111321, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1523-1579","authenticated-orcid":false,"given":"Everardo","family":"B\u00e1rcenas","sequence":"additional","affiliation":[{"name":"Facultad de Ingenier\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico (UNAM), Ciudad Universitaria, Ciudad de M\u00e9xico 04510, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"9133","DOI":"10.1007\/s40964-025-01181-7","article-title":"Predicting ultimate tensile and break strength of SLS PA 12 parts using machine learning on tensile load\u2013displacement data","volume":"10","author":"Mora","year":"2025","journal-title":"Prog. Addit. Manuf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1016\/j.cirp.2024.04.101","article-title":"Artificial Intelligence in manufacturing: State of the art, perspectives, and future directions","volume":"73","author":"Gao","year":"2024","journal-title":"CIRP Ann."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e10159","DOI":"10.1002\/amp2.10159","article-title":"A review of artificial intelligence applications in manufacturing operations","volume":"5","author":"Plathottam","year":"2023","journal-title":"J. Adv. Manuf. Process."},{"key":"ref_4","first-page":"2326526","article-title":"Machine learning-supported manufacturing: A review and directions for future research","volume":"12","author":"Borgianni","year":"2024","journal-title":"Prod. Manuf. Res."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., Shahrior, F., Iqbal, K., and Abushaiba, A.A. (2025). Enabling Intelligent Industrial Automation: A Review of Machine Learning Applications with Digital Twin and Edge AI Integration. Automation, 6.","DOI":"10.20944\/preprints202506.2041.v1"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"115490","DOI":"10.1016\/j.compstruct.2022.115490","article-title":"A comprehensive review on structural joining techniques in the marine industry","volume":"289","author":"Delzendehrooy","year":"2022","journal-title":"Compos. Struct."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/BF03266625","article-title":"Share of Spot Welding and Other Joining Methods in Automotive Production","volume":"52","author":"Janota","year":"2008","journal-title":"Weld. World"},{"key":"ref_8","unstructured":"Nelson, J.P., Biddle, J.B., and Shapira, P. (2023). Applications and Societal Implications of Artificial Intelligence in Manufacturing: A Systematic Review. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103027","DOI":"10.1016\/j.rcim.2025.103027","article-title":"Teaching robots to weld by leveraging human expertise","volume":"95","author":"Zhou","year":"2025","journal-title":"Robot. Comput. Manuf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.jmapro.2013.09.004","article-title":"A tutorial on learning human welder\u2019s behavior: Sensing, modeling, and control","volume":"16","author":"Liu","year":"2014","journal-title":"J. Manuf. Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/j.procir.2020.04.109","article-title":"Systematic review on machine learning (ML) methods for manufacturing processes\u2014Identifying artificial intelligence (AI) methods for field application","volume":"93","author":"Fahle","year":"2020","journal-title":"Procedia CIRP"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.jmsy.2023.05.025","article-title":"Time-Series Pattern Recognition in Smart Manufacturing Systems: A Literature Review and Ontology","volume":"69","author":"Farahani","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wu, D., Zhang, P., Ye, X., Shi, H., Cai, X., and Tian, Y. (2023). Laser Welding Penetration Monitoring Based on Time-Frequency Characterization of Acoustic Emission and CNN-LSTM Hybrid Network. Materials, 16.","DOI":"10.3390\/ma16041614"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"042052","DOI":"10.2351\/7.0000796","article-title":"Interpreting acoustic emissions to determine the weld depth during laser beam welding","volume":"34","author":"Tomcic","year":"2022","journal-title":"J. Laser Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rohe, M., Stoll, B.N., Hildebrand, J., Reimann, J., and Bergmann, J.P. (2021). Detecting process anomalies in the gmaw process by acoustic sensing with a convolutional neural network (Cnn) for classification. J. Manuf. Mater. Process., 5.","DOI":"10.3390\/jmmp5040135"},{"key":"ref_16","unstructured":"Stemmer, G., Lopez, J.A., Del Hoyo Ontiveros, J.A., Raju, A., Thimmanaik, T., and Biswas, S. (2024). Unsupervised Welding Defect Detection Using Audio And Video. arXiv."},{"key":"ref_17","first-page":"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":"ref_18","doi-asserted-by":"crossref","unstructured":"Evgrafov, A.N. (2023). Non-destructive Testing of Welding Defects Using Machine Learning Algorithms Based on Acoustic Emission Data. Advances in Mechanical Engineering, Springer Nature.","DOI":"10.1007\/978-3-031-30027-1"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s13198-023-02178-7","article-title":"Application of Continuous Wavelet Transform based on Fast Fourier Transform for the Quality Analysis of Arc Welding Process","volume":"15","author":"Kumar","year":"2021","journal-title":"Int. J. Syst. Assur. Eng. Manag."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Noguez Imm, R., Mu\u00f1oz-Benitez, J., Medina, D., Barcenas, E., Molero-Castillo, G., Reyes-Ortega, P., Hughes-Cano, J.A., Medrano-Gracia, L., Miranda-Anaya, M., and Rojas-Piloni, G. (2023). Preventable risk factors for type 2 diabetes can be detected using noninvasive spontaneous electroretino-gram signals. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0278388"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"8490","DOI":"10.15282\/jmes.15.4.2021.03.0669","article-title":"Acoustic methods in real-time welding process monitoring: Application and future potential advancement","volume":"15","author":"Yusof","year":"2021","journal-title":"J. Mech. Eng. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.ultras.2018.06.011","article-title":"Arc welding noise assessment from the measured ultrasound pressure levels: Part I: The metal active gas welding","volume":"90","author":"Marczak","year":"2018","journal-title":"Ultrasonics"},{"key":"ref_23","first-page":"116559","article-title":"Classification of weld penetration condition through synchrosqueezed-wavelet analysis of sound signal acquired from pulse mode laser welding process","volume":"279","author":"Yusof","year":"2020","journal-title":"J. Mech. Work. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2853","DOI":"10.1007\/s40194-024-01836-z","article-title":"Monitoring the gas metal arc additive manufacturing process using unsupervised machine learning","volume":"68","author":"Mattera","year":"2024","journal-title":"Weld. World"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"714","DOI":"10.3390\/acoustics5030043","article-title":"Investigating the Detection Capability of Acoustic Emission Monitoring to Identify Imperfections Produced by the Metal Active Gas (MAG) Welding Process","volume":"5","author":"Griffin","year":"2023","journal-title":"Acoustics"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"22120","DOI":"10.1038\/s41598-024-73797-8","article-title":"Use of a structure-borne sound-based in-process sensor system to identify Weld seam irregularities during electron beam welding","volume":"14","author":"Wolf","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_27","unstructured":"Bergstr\u00f6m, J. (2026, March 17). Transfer Learning on Ultrasound Spectrograms of Weld Joints for Predictive Maintenance. Available online: https:\/\/www.diva-portal.org\/smash\/get\/diva2:1500814\/FULLTEXT01.pdf."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"23355","DOI":"10.1038\/s41598-025-06324-y","article-title":"A monitoring network SIMNet for weld penetration status based on mul-timodal fusion","volume":"15","author":"Jiang","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2357\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:38:22Z","timestamp":1776065902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,11]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26082357"],"URL":"https:\/\/doi.org\/10.3390\/s26082357","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,11]]}}}