Prediction of Residual Stresses by Radial Basis Neural Network in HSLA-65 Steel Weldments


Department of Mechanical Engineering, Aligudarz Branch, Islamic Azad University, Aligudarz, Iran


This paper investigates the residual stress fields in the vicinity of weld bead in HSLA-65 steel weldments using a neural network. This study consists of two cases: (i) the experimental analysis was carried out on the measurement of residual stresses by XRD technique. Many different specimens that were subjected to different conditions were studied. The values and distributions of residual stresses occurring in welding of HSLA-65 plate under various conditions were determined. (ii) The mathematical modeling analysis has proposed the use of radial basis (RB) NN to determine the residual stresses based on the welding conditions. The input of RBNN are welding current, welding voltage, welding heat input, travel speed of welding, wire feed speed and distance from weld. The best fitting training data set was obtained with 18 neurons in the hidden layer, which made it possible to predict residual stresses with accuracy of at least as good as the experimental error, over the whole experimental range. After training, it was found that the regression values (R2) are 0.999664 and 0.999322 for newrbe and newrb functions respectively. Similarly, these values for testing data are 0.999425 and 0.998505, respectively. Based on the verification errors, it was shown that the radial basis function of neural network with newrbe function is superior in this particular case, and has the average error of 7.70% in predicting the residual stresses in HSLA-65. This method is conceptually straightforward, and it is also applicable to other type of welding for practical purposes.


[1]      Montemarano, T. W., Sack, B. P., Gudas, J. P., Vassilaros, M. G., and Vanderveldt, H. H., “High Strength Low Alloy Steels in Naval Construction”, Journal of Ship Production, Vol. 2, No. 3, 1986, pp. 145–162.
[2]      Czyryca, E. J., Link, R. E., Wong, R. J., Aylor, D. A., Montemarano, T. W., and Gudas, J. P., “Development and Certification of HSLA-100 Steel for Naval Ship Construction”, Naval Engineers Journal, Vol. 102, No. 3, 1990, pp. 63–82.
[3]      DeLoach, J. J., Null, C., Flore, S., and Konkol, P., “The Right Welding Wire Could Help the U.S. Navy Save Millions”, Welding Journal, Vol. 78, No.6, 1999, pp. 55–58.
[4]      Sampath, K., “An Understanding of HSLA-65 Plate Steels”, Journal of Materials Engineering and Performance, Vol. 15, No. 1, 2006, pp. 32-40.
[5]      Barnes, S. J., Bhatti, A. R., Steuwer, A., Johnson, R., Altenkirch, J., and Withers, P. J., “Friction Stir Welding in HSLA-65 Steel: Part I. Influence of Weld Speed and Tool Material on Microstructural Development”, Metallurgical and Materials Transactions A., Vol. 43, No.7, 2012, pp. 2342-2355.
[6]      Steuwer, A., Barnes, S. J., Altenkirch, J., Johnson, R., and Withers P. J., “Friction Stir Welding of HSLA-65 Steel: Part II. The Influence of Weld Speed and Tool Material on the Residual Stress Distribution and Tool Wear”, Metallurgical and Materials Transactions A, Vol. 43, No.7, 2012, pp. 2356-2365.
[7]      Wei, L., Nelson, T. W., “Influence of Heat Input on Post Weld Microstructure and Mechanical Properties of Friction Stir Welded HSLA-65 Steel”, Materials Science and Engineering: A. Vol. 556, 2012, pp. 51–59.
[8]      Nasser, S. N., Guo, W. G., “Thermo Mechanical Response of HSLA-65 Steel Plates: Experiments and Modeling”, Mechanics of Materials. Vol. 37, No. 2, 2005, pp. 379–405.
[9]      Czyryca, E. J., Link, R. E., and Wong, R. J., “Evaluation of HSLA-100 Steel for Surface Combatant Structural Certification”, DTRC/SME-89/15, Bethesda, Maryland, 1989, pp. 1.
[10]   Spanos, G., Fonda, R. W., Vandermeer, R. A., and Matuszski, A., “Microstrucral Change in HSLA-100 Steel Thermally Cycled Simulate the Heat–Affected Zone During Welding”, Metallurgical and Materials Transactions, Vol. 26, No.12, 1995, pp. 3277-3293.
[11]   Blackburn, J. M. “An Overview of Some Current Research on the Welding Residual Stresses and Distortion in the U.S. Navy”, 1996, IIW Doc. X-1359-96.
[12]   Ahmadzadeh, M., Hoseinifard, A., Saranjam, B., and Salimi, H. R., “Prediction of Residual Stresses in Gas arc Welding by Back Propagation Neural Network”, NDT & E International, Vol. 52, 2012, pp. 136–143.
[13]   Zhang, J., Dong, P., and Brust, F., “Residual Stress Analysis and Fracture Assessment of Weld Joints in Moment Frames ASME. PVP-Fracture”, Fatigue and Weld Residual Stress, Vol. 393, 1999, pp. 201-207.
[14]   Preston, R., Smith, S., Shercliff, H.,and Withers, P., “An Investigation in to the Residual Stresses in Aanaluminum 2024 Test Weld”,  ASME. PVP—Fracture, Fatigue and Weld Residual Stress. Vol. 393, 1999, pp. 265-7.
[15]   Dong, P., Hong, J., Bynum, J., and Rogers, P., “Analysis of residual stresses in Al–Li alloy repair welds”, ASME, PVP—Approximate Methods Des Anal Press Vessels Pip Compon, Vol. 347, 1997, pp. 61–75.
[16]   Karlsson, R. I., Josefson, B. L., “Three-Dimensional Finite Element Analysis of Temperatures and Stresses in a Single-Pass Butt-Welded Pipe”, ASME J Pressure Vessel Technol, Vol. 112, 1990, pp. 76-84.
[17]   Goldak, J., Chakravarti, A., and Bibby, M. A. “New Finite Element Model for Welding Heat Sources”, Metall Trans B, Vol. 15B, 1984, pp. 299-305.
[18]   Goldak, J., “Distortion and Residual Stress in Welds: the Next Generation”, 8th Trends in Welding Research, 2009, pp. 45–52.
[19]   Junek, L., Slovacek, M., Magula, V., and Ochodek, V., “Residual Stress Simulation Incorporating Weld HAZ Microstructure”, ASME PVP—Fracture, Fatigue and Weld Residual Stress. Vol. 393, 1999, pp. 179-92.
[20]   Xu, S., Wang, W., “Numerical Investigation on Weld Residual Stresses in Tube to Tube Sheet Joint of a Heat Exchanger”, International Journal of Pressure Vessels and Piping, Vol. 101, 2013, pp. 37-44.
[21]   Lee, C. H., Chang, K. H., “Prediction of Residual Stresses in High Strength Carbon Steel Pipe Weld Considering Solid-State Phase Transformation Effects”, Computers & Structures, Vol. 89, 2011, pp. 256-265.
[22]   Pearce, S. V., Linton, V. M., and Oliver, E. C., “Residual Stress in a Thick Section High Strength T-Butt Weld. Materials Science and Engineering: A”, Vol. 480, 2008, pp. 411-418.
[23]   Brown, T. B., Dauda, T. A., Truman, C. E., Smith, D. J., Memhard, D., and Pfeiffer, W., “Predictions and Measurements of Residual Stress in Repair Welds in Plates”, International Journal of Pressure Vessels and Piping, Vol. 83, 2006, pp. 809-818.
[24]   Bae, I. H., Lim, D. H., Gyun, M. N, and Kim, J. W., “Prediction of Residual Stress in the Welding Zone of Dissimilar Metals Using Data-Based Models and Uncertainty Analysis”, Nuclear Engineering and Design, Vol. 240, 2010, pp. 2555–2564.
[25]   Yajiang, L., Juan, W., Maoai, C., and Xiaoqin, S., “Finite Element Analysis of Residual Stress in the Welded Zone of a High Strength Steel”, Bull. Mater. Sci., Vol. 27, No. 2, 2004, pp. 127–132.
[26]   Withers, P., Turski, M., Edwards, L., Bouchard, P., and Buttle, D., “Recent Advances in Residual Stress Measurement”, International Journal of Pressure Vessels and Piping, Vol. 85, No. 3, 2008, pp. 118-127.
[27]   El-Kassas, E. M. A., Mackie, R. I., and El-Sheikh, A. I., “Using Neural Networks in Cold-Formed Steel Design”, Computers & Structures, Vol. 79, 2001, pp. 1687-1696.
[28]   Freeman, J. A., “Simulating Neural Networks”, Addison–Wesley Publishing Company, Inc., New York, 1994.
[29]   Wasserman, P. D., “Neural Computing: Theory and Practice”, Van Nostrand Reinhold, New York, 1989.
[30]   Heidari, M., Homaei, H., “Design of a PID Controller for Suspension System by Back Propagation Neural Network”, Journal of Engineering, Vol. 2013, 2013, pp. 1-9.
[31]   Jacobs R. A., “Increased Rates of Convergence Through Learning Rate Adaptation”, Neural Network, Vol. 1, 1988, pp. 295-307.
[32]   Demuth, H., Beale, M., “Matlab Neural Networks Toolbox”, User’s Guide. Copyright 1992-2001, The Math Works, Inc., See also URL
[33]   Zhang, H., Wei, W., and Mingchen, Y., “Boundedness and Convergence of Batch Back-Propagation Algorithm with Penalty for Feedforward Neural Networks”, Neurocomputing, Vol. 89, 2012, pp. 141-146.