A study on fiber laser lap welding of thin stainless steel

作者：Yang Rong Tai^*; Chen Zhi Wei

来源：International Journal of Precision Engineering and Manufacturing, 2013, 14(2): 207-214.

DOI：10.1007/s12541-013-0029-7

• Lap welding
• Response surface methodology
• Back-propagation neural network
• Genetic algorithm
• ANOVA
• Optimization

This study analyzed variations of shear strength that depend on the fiber laser process during lap welding of AISI 304 stainless thin sheets. The experimental plan was based on a Taguchi orthogonal array table. A hybrid method that includes the response surface methodology (RSM) and back-propagation neural network (BPNN) integrated genetic algorithm (GA) are proposed to search for an optimal parameter setting of the lap welding process. The results show that the RSM and BPNN/GA methods are both effective tools for the optimization of lap welding process parameters. At the same time, an analysis of variance (ANOVA) was implemented to identify significant factors influencing the lap welding process parameters. In addition, the micrographs also show that the appropriate setting of the laser power, befitting the penetration depth and welding line length of the fusion zone sections were produced. A confirmation experiment was also conducted in order to validate the optimal welding process parameter values.

• 出版日期2013-2