Advanced ANN Techniques for Precise Detection and Classification of Welding Defects
DOI:
https://doi.org/10.59890/ijist.v2i5.1907Keywords:
Defects, ANN, Classification, Welding, ReLuAbstract
The implementation of the artificial neural network (ANN) algorithm for detecting and classifying welding defects is detailed in this study. A total of 558 welding workpiece images were processed using techniques such as resizing, auto-orientation, flipping, rotation, and annotation, ultimately expanding the dataset to 1,288 images. Feature extraction identified 24 traits across 12,000 data points, which were then condensed to 5,735 data points for the ANN model. The model employed 100 hidden layers, the ReLU activation function, and the L-BFGS-B solver, running for 200 iterations. The configuration achieved near-perfect results, with metrics such as the area under the curve (AUC), classification accuracy, and F1 score averaging a precision of 0.97. These outcomes demonstrate the ANN model's high efficacy in detecting and classifying welding defects, underscoring its potential application for quality assurance in the welding industry. Further investigation into specific defect types, including porosity, spatter, cracks, and undercuts, could further improve detection accuracy.
References
Ajmi, C., Zapata, J., Elferchichi, S., Zaafouri, A., & Laabidi, K. (2020). Deep Learning Technology for Weld Defects Classification Based on Transfer Learning and Activation Features. Advances in Materials Science and Engineering. https://api.semanticscholar.org/CorpusID:221690506
Alkhatib, R. (2021). Artificial Neural Network Activation Functions in Exact Analytical Form (Heaviside, ReLU, PReLU, ELU, SELU, ELiSH). https://api.semanticscholar.org/CorpusID:238776182
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00444-8
Carrington, A. M., Manuel, D. G., Fieguth, P. W., Ramsay, T., Osmani, V., Wernly, B., Bennett, C. L., Hawken, S., Magwood, O., Sheikh, Y., McInnes, M.
D. F., & Holzinger, A. (2021). Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 329–341. https://api.semanticscholar.org/CorpusID:232307175
Efa, D. A., Gutema, E. M., Lemu, H. G., & Gopal, M. (2024). Friction stir-welding of AZ31B Mg and 6061-T6 Al alloys optimization using Box-Behnken design (BBD) and Artificial Neural network (ANN). Research on Engineering Structures and Materials, 10(1), 413–430. https://doi.org/10.17515/resm2023.50ma0703rs
Faza. (2024). Visual Welding Defect Dataset. In Roboflow Universe. Roboflow. https://universe.roboflow.com/faza/visual-welding-defect
Gundewar, S., Kane, P., Behara, S., & Kumar, U. (2022). Welding defect detection using artificial neural network and support vector machine. IOP Conference Series: Materials Science and Engineering, 1259(1), 012029. https://doi.org/10.1088/1757-899x/1259/1/012029
Guo, W., Huang, L., & Liang, L. (2020). A weld seam dataset and automatic detection of welding defects using convolutional neural network. Advances in Intelligent Systems and Computing, 905, 434–443. https://doi.org/10.1007/978-3-030-14680-1_48
Jo, D. S., Kahhal, P., & Kim, J. H. (2023). Optimization of Friction Stir Spot Welding Process Using Bonding Criterion and Artificial Neural Network. Materials, 16(10). https://doi.org/10.3390/ma16103757
Kim, C., Cha, S.-H., An, Y. J., & Wilson, N. (2017). On ROC Curve Analysis of Artificial Neural Network Classifiers. The Florida AI Research Society.
Kumaresan, S., Aultrin, K. S. J., Kumar, S. S., & Anand, M. D. (2023). Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning. International Journal on Interactive Design and Manufacturing, 17(6), 2999–3010. https://doi.org/10.1007/s12008-023-01327-3
Livieris, I. E. (2019). Improving the classification efficiency of an ANN utilizing a new training methodology. Informatics, 6(1). https://doi.org/10.3390/INFORMATICS6010001
Pesch, I. S., Bestelink, E., de Sagazan, O., Mehonic, A., & Sporea, R. A. (2022). Multimodal transistors as ReLU activation functions in physical neural network classifiers. Scientific Reports, 12. https://api.semanticscholar.org/CorpusID:245909752
S, K., M. S, N., & G, P. (2023). Classification of weld defects using machine vision using convolutional neural network. The Scientific Temper, 14(01), 172–177. https://doi.org/10.58414/scientifictemper.2023.14.1.20
Tripicchio, P., & D’Avella, S. (2022). Welding Defect Detection with Deep Learning Architectures. In Engineering Principles - Welding and Residual Stresses. IntechOpen. https://doi.org/10.5772/intechopen.101951
Tyystjärvi, T., Fridolf, P., Rosell, A., & Virkkunen, I. (2024). Deploying Machine Learning for Radiography of Aerospace Welds. Journal of Nondestructive Evaluation, 43(1). https://doi.org/10.1007/s10921-023-01041-w
Wu, X. (2022). Analyzing Welding Performance of Metal Using Artificial Neural Network. Mobile Information Systems. https://api.semanticscholar.org/CorpusID:250008964
Yang, L., & Jiang, H. (2021). Weld defect classification in radiographic images using unified deep neural network with multi-level features. Journal of Intelligent Manufacturing, 32(2), 459–469. https://doi.org/10.1007/s10845-020-01581-2
Yang, Y., He, Y., Guo, H., Chen, Z., & Zhang, L. (2022). Semantic segmentation supervised deep-learning algorithm for welding-defect detection of new energy batteries. Neural Computing and Applications, 34(22), 19471–19484. https://doi.org/10.1007/S00521-022-07474-0/METRICS
Yemelyanova, M., & Smailova, S. (2024). APPLICATION OF MACHINE LEARNING FOR RECOGNIZING SURFACE WELDING DEFECTS IN VIDEO SEQUENCES. Scientific Journal of Astana IT University. https://doi.org/10.37943/16ryge2979
