Prediction of Upset Length and Upset Time in Inertia Friction Welding Process Using Deep Neural Network

관성 마찰용접 공정에서 심층 신경망을 이용한 업셋 길이와 업셋 시간의 예측

  • 양영수 (전남대학교 기계공학과) ;
  • 배강열 (경남과학기술대학교 메카트로닉스공학과)
  • Received : 2019.08.30
  • Accepted : 2019.09.12
  • Published : 2019.11.30


A deep neural network (DNN) model was proposed to predict the upset in the inertia friction welding process using a database comprising results from a series of FEM analyses. For the database, the upset length, upset beginning time, and upset completion time were extracted from the results of the FEM analyses obtained with various of axial pressure and initial rotational speed. A total of 35 training sets were constructed to train the proposed DNN with 4 hidden layers and 512 neurons in each layer, which can relate the input parameters to the welding results. The mean of the summation of squared error between the predicted results and the true results can be constrained to within 1.0e-4 after the training. Further, the network model was tested with another 10 sets of welding input parameters and results for comparison with FEM. The test showed that the relative error of DNN was within 2.8% for the prediction of upset. The results of DNN application revealed that the model could effectively provide welding results with respect to the exactness and cost for each combination of the welding input parameters.


Supported by : 경남과학기술대학교


  1. Irachet, O., Bennett, C. J. and Sun, W., "A Sensitivity Study of Parameters Affecting Residual Stress Predictions in Finite Element Modelling of the Inertia Friction Welding Process", International Journal of Solids and Structures, Vol. 71, No. 10, pp. 180-193, 2015.
  2. Li, W. and Wang, F., "Modeling of Continuous Drive Friction Welding of Mild Steel", Materials Science and Engineering A, Vol. 528, pp. 592-5926, 2011.
  3. Liu, W., Wang, F., Yang, X. and Li, W., "Upset Prediction in Friction Welding Using Radial Basis Fuction Neural Network", Advances in Materials Science and Engineering, Vol. 2013, pp. 1-9, 2013.
  4. ABAQUS, Abaqus Example Problems Manual Ver. 6.10, "Inertia Welding", Dassault Systemes, pp. 1.3.18-1-1.3.18-17, 2010.
  5. Anand, K., Barik, B. K., Tamilmannan, K. and Sathiya, P., "Artificial Neural Network Modeling Studies to Predict the Friction Welding Process Parameters of Incoloy 800H Joints", Engineering Science and Technology an International Journal, Vol. 18, pp. 394-407, 2015.
  6. Oh, S. C., "Prediction of Machining Performance using ANN and Training using ACO", Journal of the Korean Society of Manufacturing Process Engineers, Vol. 16, No. 6, pp. 125-132, 2017.
  7. Keshmiri, S., Zheng, X., Feng, L. X., Pang, C. K. and Chew, C. M., "Application of Deep Neural Network in Estimation of the Weld Bead Parameters", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015, Hamburg, Germany, pp. 3518-3523. d
  8. Kim, M. S., Shin, S. M., Kim, D. H. and Rhee, S., "A Study on the Algorithm for Determining Back Bead Generation in GMA Welding Using Deep Learning", Journal of Welding and Joining, Vol. 36, No. 2, 2018, pp. 74-81.
  9. Ajith, P. M., Barik, B. K., Sathiya, P. and Aravindan, S., "Multiobjective Optimization of Friction Welding of UNS S32205 Duplex Stainless Steel", Defence Technology, Vol. 11, pp. 157-165, 2015.
  10. Moal, A. and Massoni, E., "Finite Element Simulation of the Inertia Welding of Two Similar Parts", Engineering Computations, Vol. 12, No. 6, pp. 497-512, 1995.
  11. Oluwasegun, K. M., Olawale, J. O., Ige, O. O, Shittu, M. D., Adeleke, A. A. and Malomo, B. O., "Microstructural Characterization of Thermomechanical and Heat-Affected Zones of an Inertia Friction Welded Astroloy", Journal of Materials Engineering and Performance, Vol. 23, No. 8, pp. 2834-2846, 2014.
  12. Glorot, X. and Bengio, Y., "Understanding the Difficulty of Training Deep Feedforward Neural Networks", Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, Vol. 9, pp. 249-256, 2010.