{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:06:25Z","timestamp":1775012785171,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"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>Weld site inspection is a research area of interest in the manufacturing industry. In this study, a digital twin system for welding robots to examine various weld flaws that might happen during welding using the acoustics of the weld site is presented. Additionally, a wavelet filtering technique is implemented to remove the acoustic signal originating from machine noise. Then, an SeCNN-LSTM model is applied to recognize and categorize weld acoustic signals according to the traits of strong acoustic signal time sequences. The model verification accuracy was found to be 91%. In addition, using numerous indicators, the model was compared with seven other models, namely, CNN-SVM, CNN-LSTM, CNN-GRU, BiLSTM, GRU, CNN-BiLSTM, and LSTM. A deep learning model, and acoustic signal filtering and preprocessing techniques are integrated into the proposed digital twin system. The goal of this work was to propose a systematic on-site weld flaw detection approach encompassing data processing, system modeling, and identification methods. In addition, our proposed method could serve as a resource for pertinent research.<\/jats:p>","DOI":"10.3390\/s23052643","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T02:01:51Z","timestamp":1677549711000},"page":"2643","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Deep Learning-Empowered Digital Twin Using Acoustic Signal for Welding Quality Inspection"],"prefix":"10.3390","volume":"23","author":[{"given":"Tao","family":"Ji","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia"}]},{"given":"Norzalilah","family":"Mohamad Nor","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"ref_1","unstructured":"Zhang, Z., Wen, G., and Chen, S. (2019). Transactions on Intelligent Welding Manufacturing, Springer."},{"key":"ref_2","unstructured":"Xu, J., and Chen, S. (2020). Transactions on Intelligent Welding Manufacturing, Springer."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107966","DOI":"10.1016\/j.measurement.2020.107966","article-title":"Welding penetration recognition based on arc sound and electrical signals in K-TIG welding","volume":"163","author":"Cui","year":"2020","journal-title":"Measurement"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.jmapro.2013.07.002","article-title":"Research evolution on intelligentized technologies for arc welding process","volume":"16","author":"Chen","year":"2014","journal-title":"J. Manuf. Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1080\/10426914.2021.1885711","article-title":"Monitoring of weld defects of visual sensing assisted GMAW process with galvanized steel","volume":"36","author":"Ma","year":"2021","journal-title":"Mater. Manuf. Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.jmapro.2019.06.023","article-title":"Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding","volume":"45","author":"Zhang","year":"2019","journal-title":"J. Manuf. Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1016\/j.jmapro.2021.03.039","article-title":"Modeling of weld penetration control system in GMAW-P using NARMAX methods","volume":"65","author":"Cao","year":"2021","journal-title":"J. Manuf. Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105967","DOI":"10.1016\/j.engfailanal.2021.105967","article-title":"Failure assessment of Mash Seam Weld breakage and development of online weld inspection system for early detection of weld failure","volume":"133","author":"Bonikila","year":"2022","journal-title":"Eng. Fail. Anal."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"267","DOI":"10.5545\/sv-jme.2010.181","article-title":"Monitoring Gas Metal Arc Welding Process by Using Audible Sound Signal","volume":"2011","author":"Horvat","year":"2011","journal-title":"Stroj. Vestnik\u2013 J. Mech. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107475","DOI":"10.1016\/j.measurement.2020.107475","article-title":"Weld bead penetration identification based on human-welder subjective assessment on welding arc sound","volume":"154","author":"Gao","year":"2020","journal-title":"Measurement"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.jmatprotec.2017.07.005","article-title":"Automated control of welding penetration based on audio sensing technology","volume":"250","author":"Lv","year":"2017","journal-title":"J. Mater. Process. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmapro.2021.11.055","article-title":"Quality analysis of CMT lap welding based on welding electronic parameters and welding sound","volume":"74","author":"Liu","year":"2022","journal-title":"J. Manuf. Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.jmapro.2020.12.023","article-title":"Dynamic welding process monitoring based on microphone array technology","volume":"64","author":"Na","year":"2021","journal-title":"J. Manuf. Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106901","DOI":"10.1016\/j.measurement.2019.106901","article-title":"Weld bead penetration state recognition in GMAW process based on a central auditory perception model","volume":"147","author":"Wang","year":"2019","journal-title":"Measurement"},{"key":"ref_15","unstructured":"Boschert, S., and Rosen, R. (2016). Mechatronic Futures, Springer. Book Section Chapter 5."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1038\/d41586-019-02849-1","article-title":"Make more digital twins","volume":"573","author":"Tao","year":"2019","journal-title":"Nature"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.jmsy.2019.10.001","article-title":"Enabling technologies and tools for digital twin","volume":"58","author":"Qi","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103130","DOI":"10.1016\/j.compind.2019.103130","article-title":"Review of digital twin applications in manufacturing","volume":"113","author":"Cimino","year":"2019","journal-title":"Comput. Ind."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101837","DOI":"10.1016\/j.rcim.2019.101837","article-title":"Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues","volume":"61","author":"Lu","year":"2020","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"031015","DOI":"10.1115\/1.4052130","article-title":"Digital twin for the transient temperature prediction during coaxial one-side resistance spot welding of Al5052\/CFRP","volume":"144","author":"Ren","year":"2022","journal-title":"J. Manuf. Sci. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.jmsy.2020.07.013","article-title":"Digital twin-based industrial cloud robotics: Framework, control approach and implementation","volume":"58","author":"Xu","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102075","DOI":"10.1016\/j.rcim.2020.102075","article-title":"The connotation of digital twin, and the construction and application method of shop-floor digital twin","volume":"68","author":"Zhuang","year":"2021","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.jmsy.2020.10.002","article-title":"Deep learning-empowered digital twin for visualized weld joint growth monitoring and penetration control","volume":"57","author":"Wang","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102140","DOI":"10.1016\/j.rcim.2021.102140","article-title":"Generic development methodology for flexible robotic pick-and-place workcells based on Digital Twin","volume":"71","author":"Tipary","year":"2021","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.cirp.2018.04.055","article-title":"Digital twin driven prognostics and health management for complex equipment","volume":"67","author":"Tao","year":"2018","journal-title":"CIRP Ann."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Imran, M.S., Rahman, A.F., Tanvir, S., Kadir, H.H., Iqbal, J., and Mostakim, M. (2021, January 20\u201322). An analysis of audio classification techniques using deep learning architectures. Proceedings of the 2021 6th International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India.","DOI":"10.1109\/ICICT50816.2021.9358774"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"72120","DOI":"10.1109\/ACCESS.2022.3185224","article-title":"Acoustic-Based Train Arrival Detection Using Convolutional Neural Networks with Attention","volume":"10","author":"Tran","year":"2022","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"98","DOI":"10.4018\/IJACI.2017010105","article-title":"Design and implementation of a robust acoustic recognition system for waterbird species using TMS320C6713 DSK","volume":"8","author":"Boulmaiz","year":"2017","journal-title":"Int. J. Ambient Comput. Intell. (IJACI)"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1007\/s40313-021-00727-8","article-title":"Development of optimal feature selection and deep learning toward hungry stomach detection using audio signals","volume":"32","author":"Maria","year":"2021","journal-title":"J. Control Autom. Electr. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Saddam, S.A.W. (2022). Wind Sounds Classification Using Different Audio Feature Extraction Techniques. Informatica, 45.","DOI":"10.31449\/inf.v45i7.3739"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2643\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:43:43Z","timestamp":1760121823000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23052643"],"URL":"https:\/\/doi.org\/10.3390\/s23052643","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]}}}