The use of the taguchi method and a neural-genetic approach to optimize the quality of a pulsed Nd:YAG laser welding process

In the production process of lithium-ion secondary batteries, the lap-joint quality of the safety vent and the cathode lead influences the product quality and production efficiency. A pulsed Nd:YAG laser welding machine was employed herein. The welding parameters that influence the pulsed Nd:YAG laser welding quality was evaluated by measuring the tensile-shear strength. In this study, the Taguchi method was used to perform the initial optimization of the process parameters. A neural network (NN) with the Levenberg–Marquardt back-propagation algorithm was adopted to develop the nonlinear relationship between factors and the response. Then, a genetic algorithm based on a well-trained NN model was applied to determine the optimal factor settings. Experimental results illustrated the proposed approach.

[1]  Ryszard Tadeusiewicz,et al.  Neural networks: A comprehensive foundation: by Simon HAYKIN; Macmillan College Publishing, New York, USA; IEEE Press, New York, USA; IEEE Computer Society Press, Los Alamitos, CA, USA; 1994; 696 pp.; $69–95; ISBN: 0-02-352761-7 , 1995 .

[2]  A. Olabi,et al.  Weld-bead profile and costs optimisation of the CO2 dissimilar laser welding process of low carbon steel and austenitic steel AISI316 , 2011 .

[3]  Thomas L. Saaty,et al.  Rank from comparisons and from ratings in the analytic hierarchy/network processes , 2006, Eur. J. Oper. Res..

[4]  R. Roy.  A Primer on the Taguchi Method , 1990 .

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

[6]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[7]  Chao-Ton Su,et al.  Parameter design optimization via neural network and genetic algorithm , 2000 .

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

[9]  C. Wang,et al.  Optimization of Nd:YAG laser welding onto magnesium alloy via Taguchi analysis , 2005 .

[10]  Prasad K. Yarlagadda,et al.  Prediction of welding parameters for pipeline welding using an intelligent system , 2002 .

[11]  Genichi Taguchi,et al.  Taguchi methods : design of experiments , 1993 .

[12]  S.‐C Chi,et al.  A fuzzy Q-analysis taguchi method for parameter design with multiple quality characteristics , 2008 .

[13]  Chung-Feng Jeffrey Kuo,et al.  Application of an LM-neural network for establishing a prediction system of quality characteristics for the LGP manufactured by CO2 laser , 2011 .

[14]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[15]  Paul B. Lochert,et al.  A fuzzy logic approach for dealing with qualitative quality characteristics of a process , 2008, Expert Syst. Appl..

[16]  B. S. Lim,et al.  Optimal design of neural networks using the Taguchi method , 1995, Neurocomputing.

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

[18]  C. Muralidharan,et al.  Selection of welding process for hardfacing on carbon steels based on quantitative and qualitative factors , 2009 .

[19]  Kamal Pal,et al.  Optimisation of weld deposition efficiency in pulsed MIG welding using hybrid neuro-based techniques , 2011, Int. J. Comput. Integr. Manuf..

[20]  Luis G. Vargas.  An overview of the analytic hierarchy process and its applications , 1990 .

[21]  T. R. Bement,et al.  Taguchi techniques for quality engineering , 1995 .

[22]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[23]  Chao-Ton Su,et al.  Optimizing the IC wire bonding process using a neural networks/genetic algorithms approach , 2003, J. Intell. Manuf..

[24]  Martin T. Hagan,et al.  Neural network design , 1995 .