Design and Development of Real-Time Vision AI Welding Analyzer
DOI:
https://doi.org/10.54536/ajsts.v5i2.7938Keywords:
Accuracy, Precision, Real-Time Vision AI, Response Time, Welding AnalyzerAbstract
Welding training needs simple, reliable tools that give quick feedback on bead quality to help learners improve skills and meet industry standards. The main purpose of the study was to develop a real-time vision AI welding analyzer, specifically describing its technical features, its accuracy, sensitivity, response time, and acceptability in terms of technical features, composition, operating performance, and safety features. The research used a developmental method, and the evaluation was conducted using a researcher-made questionnaire, validated by the members of the panel. Thirty (30) evaluators, comprising professors, welders, Technology and Livelihood Education (TLE) instructors, and end-users, assessed the developed device, providing valuable insights for its proper utilization in welding training. The device provided real-time feedback on weave and stringer beads via a web dashboard with pass/fail metrics and safety features. The findings showed that the device delivered reliable weld bead evaluation with advanced technical features, strong operating performance, and comprehensive safety measures. It achieved 90% accuracy in classifying acceptable stringer and weave beads, 100% precision with no false positives, and instant response times within the 10 second threshold. It was very acceptable, confirming its effectiveness as a supportive tool for welding education and training.
Downloads
References
Ahmad, Z., & Rofiq, Z. (2020). Development of competency-based assessment model welding practices for vocational school students. American Journal of Educational Research, 8(1), 29–34. https://doi.org/10.12691/education-8-1-5
Alhammadi, M. (2023). Optimising Customer Service Delivery and Response Time through AI-Enhanced Chatbots in Facilities Management-A Mixed-Methods Research. American Journal of Smart Technology and Solutions, 2(2), 43-54. https://doi.org/10.54536/ajsts.v2i2.2206
Alsharabi, N. (2023). Real-time object detection overview: Advancements, challenges, and applications. Journal of Advanced Urban Studies, 3(6), 73. https://doi.org/10.59145/jaust.v3i6.73
Bansal, A., Vettivel, S. C., Kumar, M., & Agarwal, M. (2023). Weld defect identification and characterization in radiographic images using deep learning: Review. Engineering Research Express, 5(4), 042005. https://doi.org/10.1088/2631- 8695/acdf3f
Bhardwaj, S., Ratnayake, C., Efthymios Polatidis, & Čapek, J. (2022). Experimental investigation of residual stress distribution on girth welds fabricated at proximity using neutron diffraction technique. The International Journal of Advanced Manufacturing Technology, 121(5-6), 3703–3715. https://doi.org/10.1007/s00170-022-09574-6
Bureau of Labor Statistics. (2018). Occupational employment projections data: Welders, cutters, solderers, and brazers. U.S. Department of Labor. https://www.bls.gov/emp/tables/occupational-separations-and-openings.htm
Chandra, H., Nukman, & Sianturi, B. (2019). Analysis of fatigue life and crack propagation characterization of gray cast iron under normalizing process. Journal of Physics: Conference Series, 1198(3), 032006. https://doi.org/10.1088/1742-6596/1198/3/032006
Chen, Z., Tan, K., Shi, Y., Liu, M., Yi, L., Chen, T., & Bai, Y. (2026). Computational Discovery of Novel SGLT2 Inhibitors from Eight Selected Medicine Food Homology Herbs Using a Multi-Stage Virtual Screening Pipeline. Pharmaceuticals, 19(2), 246. https://doi.org/10.3390/ph19020246
Dogra, V. (2018). Application of welding process parameters using AI algorithm. Türk Bilgisayar ve Matematik Eğitimi Dergisi, 9(2), 632–642. https://doi.org/10.17762/turcomat.v9i2.13866
Dold, P. M., Bleier, F., Boley, M., & Mikut, R. (2022). Multi-stage inspection of laser welding defects using machine learning. DAGM German Conference on Pattern Recognition (pp. 1–15). https://doi.org/10.58895/ksp/1000151141-3
Dosari, F. H. M. A., & Abouellail, S. I. A. D. (2023). Artificial Intelligence (AI) Techniques for Intelligent Control Systems in Mechanical Engineering. American Journal of Smart Technology and Solutions, 2(2), 55-64. https://doi.org/10.54536/ajsts.v2i2.2188
European Commission. (2020). Council Recommendation on vocational education and training (VET) for sustainable competitiveness, social fairness and resilience (2020/C 417/01). Official Journal of the European Union. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A32020H1202(01)
European Commission. (2020). Vocational education and training modernization. https://ec.europa.eu/social/main.jsp?catId=1415&langId=en
Freeman, J. (2016). Schematic diagram – A complete tutorial with free examples. Edraw Software. https://www.edrawsoft.com/schematic-diagram.html
Jeremić, L., Sedmak, A., Petrovski, B., Đorđević, B., & Sedmak, S. (2020). Structural integrity assessment of welded pipeline designed with reduced safety. Tehnicki Vjesnik, 27(6), 1839–1845. https://doi.org/10.17559/TV-20200413142538
Kesse, M. A., Buah, E., Handroos, H., & Ayetor, G. K. (2020). Development of an artificial intelligence powered TIG welding algorithm for the prediction of bead geometry for TIG welding processes using hybrid deep learning. Metals, 10(4), 451. https://doi.org/10.3390/met10040451
Khorshidikia, S., Rismanchian, M., Popov, G., & Habibi, E. (2026). Determining training needs of welders in equipment manufacturing industry: A systematic approach using Delphi fuzzy method and FAHP for traditional and immersive trainings. WORK: A Journal of Prevention, Assessment & Rehabilitation. https://doi.org/10.1177/1051981525140803
Liang, Y., Yu, B., Ding, M., Hu, W., Jin, Y., & Yuan, Y. (2025). WELD-DETR: A real-time welding defect detection framework with multi-scale feature fusion and multi-kernel perception optimization. Sensors, 25(22), Article 7024. https://doi.org/10.3390/s25227024
Naddaf-Sh, S., Naddaf-Sh, M.-Mahdi, Zargarzadeh, H., Dalton, M., Ramezani, S., Elpers, G., Baburao, V. S., & Kashani, A. R. (2022). Real-time explainable multiclass object detection for quality assessment in 2-dimensional radiography images. Complexity, 2022, 1–17. https://doi.org/10.1155/2022/4637939
Pan, K., Hu, H., & Pan, G. (2023). WD-YOLO: A more accurate YOLO for defect detection in weld X-ray images. Sensors, 23(21), Article 8677. https://doi.org/10.3390/s23218677
Ranganayakulu, S., Burra, S., & Ravi, S. (2017). Characterization of weldment defects through non-destructive evaluation techniques. Indian Journal of Science and Technology, 10(16), 1–9. https://doi.org/10.17485/ijst/2017/v10i16/109603
Sazonova, S. A., Nikolenko, S. D., Osipov, A. A., Zyazina, T. V., & Venevitin, A. A. (2021). Weld defects and automation of methods for their detection. Journal of Physics: Conference Series, 1889, 022078. https://doi.org/10.1088/1742-6596/1889/2/022078
Seabery. (2024). Soldamatic augmented reality welding training: Hyper-realistic simulation with instant feedback. Seabery Augmented Technology. https://www.seabery.com
Szőlősi, J., Szekeres, B., Magyar, P., Adrián, B., Farkas, G., & Andó, M. (2024). Welding defect detection with image processing on a custom small dataset: A comparative study. IET Collaborative Intelligent Manufacturing, 6. https://doi.org/10.1049/cim2.70005
Sun, Y., Xie, Y., Peng, R., Zhang, Y., Chen, W., & Guo, Y. (2025). DEIM-SFA: A multi-module enhanced model for accurate detection of weld surface defects. Sensors, 25(20), 6314. https://doi.org/10.3390/s25206314
TOTC Inc. (2025). How to hire a skilled welder: Challenges and best practices. TOTC Inc. https://www.totc.com.ph/whats-new/blogs/how-to-hire-a-skilled-welder/
United Nations. (2015). Sustainable Development Goal 4: Quality education. https://sdgs.un.org/goals/goal4
Western Visayas Regional Development Council. (2023). Regional development plan 2023–2028. https://pdp.depdev.gov.ph/wp-content/uploads/2023/07/Western-Visayas-RDP.pdf
World Bank. (2020). Strengthening teacher quality in vocational education and training: Professional standards for VET teachers. World Bank Open Knowledge Repository. https://openknowledge.worldbank. org/handle/10986/34588
Yamane, S., Wang, C., Nakamura, T., Nagai, T., & Ishizaki, K. (2025). Detection of molten pool state using ResNet50 and control of molten pool penetration in CO2 gas shielded arc welding. Welding in the World, 69. https://doi.org/10.1007/s40194-025-02020-7
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Crispine D. Besa
This work is licensed under a Creative Commons Attribution 4.0 International License.
