Document Type : Research Paper


1 Department of Industrial Engineering, Sakarya, Turkey.

2 Aspen Construction and Floor Systems Industry and Trade Inc., Sakarya, Turkey.


In welded constructions, there should be no defects in the welding seams, or defects should have in an acceptable range for obtaining more reliable welding operations. An undercut is one of the most important welding defects occurring on the workpieces produced by butt welding. Determining the correct value of the stress concentration factor (SCF) allows deciding whether it accepts welding defects, in which case. Many characteristics and ranges influence SCF, making it challenging to calculate a more precise SCF. In this study, six different artificial neural networks (ANN) models are developed for predicting SCF. These models differ in terms of the training dataset used (70%-90%) and the number of neurons (5-10-20) in the hidden layer. Developed ANN models consist of three input variables the ratio of Undercut depth (h) and Undercut deep Radius (r), Reinforcement angle (Q1), deep angle of welding seam (Q2), and an output variable as SCF. The prediction performance of 6 developed ANN models in different specifications is compared. The model with a 90% training set and five neurons in the hidden layer performed the best with an accuracy of 0.9834. According to the ANN model with these features, MAE, MAPE, and RMSE values are calculated as 0.0094, 2.50%, and 0.0129, respectively.


Main Subjects

  • Terán, G., Albiter, A., & Cuamatzi-Meléndez, R. (2013). Parametric evaluation of the stress concentration factors in T-butt welded connections. Engineering structures, 56, 1484–1495.
  • Holmstrand, T., Mrdjanov, N., Barsoum, Z., & Åstrand, E. (2014). Fatigue life assessment of improved joints welded with alternative welding techniques. Engineering failure analysis, 42, 10–21.
  • Teng, T.-L., Fung, C.-P., & Chang, P.-H. (2002). Effect of weld geometry and residual stresses on fatigue in butt-welded joints. International journal of pressure vessels and piping, 79(7), 467–482.
  • Dabiri, M., Ghafouri, M., Raftar, H. R. R., & Björk, T. (2017). Neural network-based assessment of the stress concentration factor in a T-welded joint. Journal of constructional steel research, 128, 567–578.
  • Guo, Z., Chen, H., & Yao, G. (2022). Bayesian prediction of the stress concentration effect on high-strength wires with corrosion pits. Engineering failure analysis, 131, 105827.
  • Abbasnia, A., Jafari, M., & Rohani, A. (2021). A novel method for estimation of stress concentration factor of central cutouts located in orthotropic plate. Journal of the Brazilian society of mechanical sciences and engineering, 43(7), 348.
  • Makki, M. M., Ahmed, B., & Chokri, B. (2018). Reliability prediction of the stress concentration factor using response surface method. The international journal of advanced manufacturing technology, 94(1), 817–826.
  • Li, R., Miao, C., & Yu, J. (2020). Effect of characteristic parameters of pitting on strength and stress concentration factor of cable steel wire. Construction and building materials, 240, 117915.
  • Wang, Y., Luo, Y., & Tsutsumi, S. (2020). Parametric formula for stress concentration factor of fillet weld joints with spline bead profile. Materials, 13(20), 4639.
  • Jiang, Y., Yuan, K., & Cui, H. (2018). Prediction of stress concentration factor distribution for multi-planar tubular DT-joints under axial loads. Marine structures, 61, 434–451.
  • Bajić, D., Momčilović, N., Maneski, T., Balać, M., Kozak, D., & Ćulafić, S. (2017). Numerical and experimental determination of stress concentration factor for a pipe branch model. Tehnicki vjesnik - technical gazette, 24(3), 687–692.
  • Wang, B., Zhao, W., Du, Y., Zhang, G., & Yang, Y. (2016). Prediction of fatigue stress concentration factor using extreme learning machine. Computational materials science, 125, 136–145.
  • Ozkan, M. T., & Toktas, I. (2016). Determination of the stress concentration factor (Kt) in a rectangular plate with a hole under tensile stress using different methods. Materials testing, 58(10), 839–847.
  • Ji, J., Zhang, C., Kodikara, J., & Yang, S.-Q. (2015). Prediction of stress concentration factor of corrosion pits on buried pipes by least squares support vector machine. Engineering failure analysis, 55, 131–138.
  • Zappalorto, M., & Carraro, P. A. (2015). An engineering formula for the stress concentration factor of orthotropic composite plates. Composites part B: engineering, 68, 51–58.
  • Darwish, F., Gharaibeh, M., & Tashtoush, G. (2012). A modified equation for the stress concentration factor in countersunk holes. European journal of mechanics - A/solids, 36, 94–103.
  • Cerit, M. (2013). Numerical investigation on torsional stress concentration factor at the semi elliptical corrosion pit. Corrosion science, 67, 225–232.
  • Cerit, M., Kokumer, O., & Genel, K. (2010). Stress concentration effects of undercut defect and reinforcement metal in butt welded joint. Engineering failure analysis, 17(2), 571–578.
  • Arola, D., & Williams, C. L. (2002). Estimating the fatigue stress concentration factor of machined surfaces. International journal of fatigue, 24(9), 923–930.
  • Ida, K., & Uemura, T. (1996). Stress concentration factor formulae widely used in japan. Fatigue & fracture of engineering materials & structures, 19(6), 779–786.
  • Chang, E., & Dover, W. D. (1996). Stress concentration factor parametric equations for tubular X and DT joints. International journal of fatigue, 18(6), 363–387.
  • Guagliano, M., Terranova, A., & Vergani, L. (1993). Theoretical and experimental study of the stress concentration factor in diesel engine crankshafts. Journal of mechanical design, 115(1), 47–52.
  • Özcanli, Y., Kosovali Çavuş, F., & Beken, M. (2016). Comparison of mechanical properties and artificial neural networks modeling of PP/PET blends. Acta physica polonica A, 130(1), 444–446.
  • Jahangiri, M., Farrokhi, A., & Amirabadi, A. (2021). Designing novel ldo voltage regulator implementation on FPGA using neural network. Journal of applied research on industrial engineering, 8(3), 205–212.
  • Erdem, B., Kiraz, A., & Kökümer, O. (2010). Prediction of stress concentration factor in welding seam with artificial neural networks. Proceedings of the 1st international symposium on computing in science & engineering, Aydın.
  • Eberhart, R. C., & Dobbins, R. W. (1990). Neural network PC tools: a practical guide (First Edition.). San Diego: Academic Press.
  • Fausett, L. V. (1993). Fundamentals of neural networks: architectures, algorithms and applications. Englewood Cliffs, NJ.
  • Shukla, R., Khalilian, B., & Partouvi, S. (2021). Academic progress monitoring through neural network. Big data and computing visions, 1(1), 1–6.
  • Çolak, A. B. (2021). An experimental study on the comparative analysis of the effect of the number of data on the error rates of artificial neural networks. International journal of energy research, 45(1), 478–500.
  • Kong, Y., Owusu-Akomeah, M., Antwi, H. A., Hu, X., & Acheampong, P. (2019). Evaluation of the robusticity of mutual fund performance in Ghana using enhanced resilient backpropagation neural network (ERBPNN) and fast adaptive neural network classifier (FANNC). Financial innovation, 5(1), 10.
  • Ghaedi, A. M., & Vafaei, A. (2017). Applications of artificial neural networks for adsorption removal of dyes from aqueous solution: a review. Advances in colloid and interface science, 245, 20–39.