期刊
MANUFACTURING LETTERS
卷 29, 期 -, 页码 52-55出版社
ELSEVIER
DOI: 10.1016/j.mfglet.2021.05.010
关键词
Machine learning; Friction stir welding; Neural network; Pearson coefficient
This study employed machine learning models to analyze the impact of process parameters on the mechanical properties of friction stir welded copper joints, with the neural network model achieving the highest accuracy of 94%. The machine learning model suggested that tool features and design were the most important parameters influencing the joint's mechanical properties.
The paper presents a machine learning classification-based model for a friction stir welded copper's mechanical properties. The models train and test 119 experimental data for the pure copper system to study the effect of process parameters on FSW copper joints' mechanical properties. Four classification models were employed to analyze the impact of process parameters on the mechanical properties. The deep learning-based neural network model exhibited the highest accuracy of 94%. The machine learning model suggested that tool features and design were the most important parameters influencing the joint's mechanical property. (C) 2021 Society of Manufacturing Engineers (SME). Published by 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