Prediction of GMA Welding Characteristic Parameter by Artificial Neural Network System

Abstract:

Nowadays, demand for automated Gas metal arc welding (GMAW) is growing and consequently need for intelligent systems is increased to ensure the accuracy of the procedure. To date, welding pool geometry has been the most used factor in quality assessment of intelligent welding systems. But, it has recently been found that Mahalanobis Distance (MD) not only can be used for this purpose but also is more efficient. In the present paper, Artificial Neural Networks (ANN) has been used for prediction of MD parameter. However, advantages and disadvantages of other methods have been discussed. The Levenberg–Marquardt algorithm was found to be the most effective algorithm for GMAW process. It is known that the number of neurons plays an important role in optimal network design. In this work, using trial and error method, it has been found that 30 is the optimal number of neurons. The model has been investigated with different number of layers in Multilayer Perceptron (MLP) architecture and has been shown that for the aim of this work the optimal result is obtained when using MLP with one layer. Robustness of the system has been evaluated by adding noise into the input data and studying the effect of the noise in prediction capability of the network. The experiments for this study were conducted in an automated GMAW setup that was integrated with data acquisition system and prepared in a laboratory for welding of steel plate with 12 mm in thickness. The accuracy of the network was evaluated by Root Mean Squared (RMS) error between the measured and the estimated values. The low error value (about 0.008) reflects the good accuracy of the model. Also the comparison of the predicted results by ANN and the test data set showed very good agreement that reveals the predictive power of the model. Therefore, the ANN model offered in here for GMA welding process can be used effectively for prediction goals.

• Periodical: Advanced Materials Research (Volumes 1061-1062)
• Pages: 481-491
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1061-1062.481
• Online since: December 2014
• Authors: Ill Soo Kim*, Ji Hye Lee, Javad Malekani, Prasad K.D.V. Yarlagadda
• Keywords: Artificial Neural Network (ANN), Automation, Gas Metal Arc Welding, Prediction

References

[1] Moore, K.L., Naidu, D.S., and Ozcelik, S, Modeling, sensing and control of gas metal arc welding 2003: Elsevier.

DOI: 10.1016/b978-008044066-8/50005-7

[2] Kim, I. S. , Son, K. J. , Yang, Y. S. , and Yaragada, P. K. D. V., Sensitivity analysis for process parameters in GMA welding processes using a factorial design method. International Journal of Machine Tools and Manufacture, 2003. 43(8): pp.763-769.

DOI: 10.1016/s0890-6955(03)00054-3

[3] Naidu, Desineni Subbaram., Ozcelik, Selahattin., and Moore, Kevin L., Gas Metal Arc Welding: Automatic Control, 2003, Elsevier publicatio. pp.147-218.

DOI: 10.1016/b978-008044066-8/50006-9

[4] Posinasetti, Praveen, Yarlagadda, Prasad K.D.V., Kang, Mun-Jin, and Rhee, Sehun, Short circuit severity model for pulse gasmetal arc welding of aluminium. Materials Science Forum, 2008. 580-582: pp.451-454.

DOI: 10.4028/www.scientific.net/msf.580-582.451

[5] Benyounis, K. Y. and Olabi, A. G., Optimization of different welding processes using statistical and numerical approaches – A reference guide. Advances in Engineering Software, 2008. 39(6): pp.483-496.

DOI: 10.1016/j.advengsoft.2007.03.012

[6] Goyal, V. K., Ghosh, P. K., and Saini, J. S., Analytical studies on thermal behaviour and geometry of weld pool in pulsed current gas metal arc welding. Journal of Materials Processing Technology, 2009. 209(3): pp.1318-1336.

DOI: 10.1016/j.jmatprotec.2008.03.035

[7] Mousavi Anzehaee, Mohammad and Haeri, Mohammad, A new method to control heat and mass transfer to work piece in a GMAW process. Journal of Process Control, 2012. 22(6): pp.1087-1102.

DOI: 10.1016/j.jprocont.2012.04.004

[8] Feng, Shengqiang, Hiroyuki, Otsuka, Hidennori, Terasaki, Yuichi, Komizo , and Hu, Shengsun, Qualitative and quantitative analysis of gmaw welding fault based on mahalanobis distance. International Journal of Precision Engineering and Manufacturing, 2011. 12(6): pp.949-955.

DOI: 10.1007/s12541-011-0127-3

[9] Kim, Ill-Soo, Son, Joon-Sik, and Yarlagadda, Prasad K. D. V., A study on the quality improvement of robotic GMA welding process. Robotics and Computer-Integrated Manufacturing, 2003. 19(6): pp.567-572.

DOI: 10.1016/s0736-5845(03)00066-8

[10] Tam, Joseph, Methods of Characterizing Gas-Metal Arc Welding Acoustics for Process Automation, 2005, University of Waterloo.

[11] Correia, Davi Sampaio, Gonçalves, Cristiene Vasconcelos, da Cunha Jr, Sebastião Simões, and Ferraresi, Valtair Antonio, Comparison between genetic algorithms and response surface methodology in GMAW welding optimization. Journal of Materials Processing Technology, 2005. 160(1): pp.70-76.

DOI: 10.1016/j.jmatprotec.2004.04.243

[12] Kim, Ill-Soo, Lee, Sang-Heon, and Yarlagadda, Prasad K, Comparison of multiple regression and back-propagation neural network approaches in modelling top bead height of multipass gas metal arc welds. J Science and Technology of Welding and Joining, 2003. 8(5): pp.347-352.

DOI: 10.1179/136217103225010998

[13] Horvat, J., Prezelj, J, ., Polajnar, I, ., and Čudina, M, . Monitoring Gas Metal Arc Welding Process by Using Audible Sound Signal. Strojniški vestnik - Journal of Mechanical Engineering, 2011. 57(3): pp.267-278.

DOI: 10.5545/sv-jme.2010.181

[14] Yarlagadda, Prasad K. D. V., Development of an integrated neural network system for prediction of process parameters in metal injection moulding. Journal of Materials Processing Technology, 2002. 130–131(0): pp.315-320.

DOI: 10.1016/s0924-0136(02)00738-0

[15] Kim, Ill-Soo, Son, Joon-Sik, Lee, Sang-Heon, and Yarlagadda, Prasad K. D. V., Optimal design of neural networks for control in robotic arc welding. Robotics and Computer-Integrated Manufacturing, 2004(20): p.57–63.

DOI: 10.1016/s0736-5845(03)00068-1

[16] Yarlagadda, Prasad K., Kim, Ill-Soo, Son, Joon-Sik, and Lee, C.W., A study on prediction of bead height in robotic arc welding using a neural network. Journal of Materials Processing Technology, 2002. 130-131: pp.229-234.

DOI: 10.1016/s0924-0136(02)00803-8

[17] Liu, Yin A and Baughman, D Richard, Neural Networks in Bioprocessing and Chemical Engineering, 1995, Academic Press, Inc., San Diego.

[18] Tanaka, H., Uegima, S., and Asai, K. , Linear Regression Analysis with Fuzzy Model. IEEE Transactions on Systems, Man and Cybernetics, 1982. 12(6): pp.903-907.

DOI: 10.1109/tsmc.1982.4308925

[19] Ates, Hakan, Prediction of gas metal arc welding parameters based on artificial neural networks. Materials and Design, 2007. 28: p.2015–(2023).

DOI: 10.1016/j.matdes.2006.06.013

[20] Al-Faruk, Abdullah , ., Hasib, Md. Abdul, ., Ahmed, Naseem, ., and Kumar Das, Utpal., Prediction of Weld Bead Geometry and Penetration in Electric Arc Welding using Artificial Neural Networks International Journal of Mechanical & Mechatronics Engineering IJMME-IJENS, 2010. 10(4): pp.23-28.