Estimation and optimization of depth of penetration in hybrid CO2 LASER-MIG welding using ANN-optimization hybrid model

The paper presents an artificial neural network-optimization hybrid model to predict and optimize penetration depth of CO2 LASER-MIG hybrid welding used for 5005 Al–Mg alloy. The input welding parameters are power, focal distance from the work piece surface, torch angle, and the distance between the laser and the welding torch. The model combines single hidden layer back propagation artificial neural networks (ANN) with Bayesian regularization for prediction and quasi-Newton search algorithm for optimization. In this method, training and prediction performance of different ANN architectures are initially tested, and the architecture with the best performance is further used for optimization. Finally, the best ANN architecture is found to show much better prediction capability compared to a regression model developed from the experimental data.

[1]  Giuseppe Casalino,et al.  Investigation on Ti6Al4V laser welding using statistical and Taguchi approaches , 2005 .

[2]  Patrick van der Smagt.  Minimisation methods for training feedforward neural networks , 1994, Neural Networks.

[3]  Olcay Ersel Canyurt,et al.  Estimation of laser hybrid welded joint strength by using genetic algorithm approach , 2008 .

[4]  Surjya K. Pal,et al.  Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals , 2008 .

[5]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[6]  Pietro Mario Lugarà,et al.  Comparison of two different nozzles for laser beam welding of AA5083 aluminium alloy , 2005 .

[7]  M.S.J. Hashmi,et al.  Optimizing the laser-welded butt joints of medium carbon steel using RSM , 2005 .

[8]  G. Casalino,et al.  An ANN and Taguchi algorithms integrated approach to the optimization of CO2 laser welding , 2006, Adv. Eng. Softw..

[9]  Mohamad H. Hassoun.  Guest Editorial Neural Networks Council Awards , 1996, IEEE Trans. Neural Networks.

[10]  Arunanshu S. Kuar,et al.  An artificial neural network approach on parametric optimization of laser micro-machining of die-steel , 2008 .

[11]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[12]  E. Anawa,et al.  Using Taguchi method to optimize welding pool of dissimilar laser-welded components , 2008 .

[13]  Giovanni Tani,et al.  The influence of shielding gas in hybrid LASER–MIG welding , 2007 .

[14]  Hsien-Yu Tseng.  Welding parameters optimization for economic design using neural approximation and genetic algorithm , 2006 .

[15]  K. Y. Benyounis,et al.  Multi-response optimization of CO2 laser-welding process of austenitic stainless steel , 2008 .

[16]  Young Whan Park,et al.  Process modeling and parameter optimization using neural network and genetic algorithms for aluminum laser welding automation , 2008 .

[17]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[18]  G. Casalino.  Statistical analysis of MIG-laser CO2 hybrid welding of Al–Mg alloy , 2007 .

[19]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[20]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[21]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[24]  M. Hashmi,et al.  Effect of laser welding parameters on the heat input and weld-bead profile , 2005 .

[25]  Surjya K. Pal,et al.  Soft computing models based prediction of cutting speed and surface roughness in wire electro-discharge machining of tungsten carbide cobalt composite , 2008 .

[26]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.