期刊
MATERIALS TODAY-PROCEEDINGS
卷 16, 期 -, 页码 907-917出版社
ELSEVIER
DOI: 10.1016/j.matpr.2019.05.176
关键词
Submerged Friction Stir Welding (SFSW); Response Surface Methodology (RSM) and Artificial Neural Network (ANN)
资金
- Science &Engineering Research Board, Department of Science and Technology (SERB-DST), New Delhi, India [SR/S3/MERC/0092/2011]
In this study, submerged friction stir welded AA6061-T6 alloy was investigated by experiments, RSM and ANN in order to determine the average grain size in the nugget zone. RSM based on the Box-Behnken design with three parameters, three levels, and 15 runs, was used for the planning, conduct, execution and development of the models. Two models, linear (second-order polynomial equation) and nonlinear (neural network) were developed for predicting the average grain size (mu m) of SFS welded AA6061-T6 alloy as the function of rotational speed (rpm), welding speed (mm/min) and water head (mm) by using Minitab and Matlab software. The effects of those factors have also been studied. The performances of the RSM and ANN model compared using the test data. The ANN model yields more accurate results compared to the RSM model. (C) 2019 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据