Journal of the Korean Society for Precision Engineering (한국정밀공학회지)

Korean Society for Precision Engineering (한국정밀공학회)
권호 표지

Development of Statistical Model and Neural Network Model for Tensile Strength Estimation in Laser Material Processing of Aluminum Alloy

알루미늄 합금의 레이저 가공에서 인장 강도 예측을 위한 회귀 모델 및 신경망 모델의 개발

  • 박영환 (한양대학교 BK21 혁신 설계 기계인력 양성사업단) ;
  • 이세헌 (한양대학교 기계공학부)
  • Published : 2007.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Aluminum alloy which is one of the light materials has been tried to apply to light weight vehicle body. In order to do that, welding technology is very important. In case of the aluminum laser welding, the strength of welded part is reduced due to porosity, underfill, and magnesium loss. To overcome these problems, laser welding of aluminum with filler wire was suggested. In this study, experiment about laser welding of AA5182 aluminum alloy with AA5356 filler wire was performed according to process parameters such as laser power, welding speed and wire feed rate. The tensile strength was measured to find the weldability of laser welding with filler wire. The models to estimate tensile strength were suggested using three regression models and one neural network model. For regression models, one was the multiple linear regression model, another was the second order polynomial regression model, and the other was the multiple nonlinear regression model. Neural network model with 2 hidden layers which had 5 and 3 nodes respectively was investigated to find the most suitable model for the system. Estimation performance was evaluated for each model using the average error rate. Among the three regression models, the second order polynomial regression model had the best estimation performance. For all models, neural network model has the best estimation performance.

Keywords

References

  1. Mather, G., 'The Welding of Aluminium and its Alloy,' Woodhead Publishing Ltd, pp. 1-9, 2002
  2. Pastor, M., Zhao, H., Martukanitz, R. P. and Debroy, T., 'Porosity, Underfill and Magnesium Loss during Continuous Wave Nd:YAG Laser welding of Thin Plates of Aluminum Alloys 5182 and 5754,' Welding Journal, Vol. 78, No.6, pp. 207s-216s, 1999
  3. Naeem, M. and Jessett, R., 'Aluminum Tailored Blank Welding With and Without Wire Feed, Using High Power Continuous Wave Nd:YAG Laser,' SAE Conference Proceedings P, No. 334, pp. 247-256, 1998
  4. Yoon, J. W., 'Laser Welding of Aluminum Alloys,' Journal of Korean Welding Society, Vol. 18, No.2, pp. 20-26, 2000
  5. Kar, A. and Mazumder, J., 'Mathematical Modeling of Keyhole Laser Welding,' Journal of Applied Physics, Vol. 78, No.1, pp. 6353-6360, 1995 https://doi.org/10.1063/1.360686
  6. Modest, M. F., 'Thee-dimensional. Transient Model for Laser Machining of Ablating/Decomposition Materials,' International Journal of Heat and Mass Transfer, Vol. 39, No.2, pp. 221-234, 1996 https://doi.org/10.1016/0017-9310(95)00134-U
  7. Park, H. and Rhee, S., 'Estimation of Weld Bead Size in $CO_{2}$ Laser Welding by Using Multiple Regression and Neural Network,' Journal of Laser Applications, Vol. 11, No.3, pp. 143-150, 1999 https://doi.org/10.2351/1.521890
  8. Park, Y. W. and Rhee, S., 'Development of Statistical Model for Line Width Estimation in Laser Micro Material Processing Using Optical Sensor,' Journal of the Korean Society for Precision Engineering, Vol. 22, No.7, pp. 27-37, 2005
  9. Jeng, J. Y., Mau, T. F. and Leu, S. M., 'Prediction of Laser Butt Joint Welding Parameters Using Back Propagation and Learning Vector Quantization Networks,' Journal of Materials Processing Technology, Vol. 99, No. 1-3, pp. 207-218, 2000 https://doi.org/10.1016/S0924-0136(99)00424-0
  10. Chan, B., Pacey, J. and Bibby, M., 'Modeling Gas Metal Arc Weld Geometry Using Artificial Neural Network Technology,' Canadian Metallurgical Quarterly, Vol. 38, No.1, pp. 43-51, 1999 https://doi.org/10.1016/S0008-4433(98)00037-8
  11. Montgomery, D. C., 'Design and Analysis of Experiments,' 5th Edition, John Wiley & Sons, Inc., pp. 392-426, 2001