摘要
【目的】旨在探究数据驱动的方法对铝合金搅拌摩擦焊对接接头抗拉强度的预测效果。【方法】该文利用Python编程语言的决策树、随机森林、支持向量机和人工神经网络等机器学习算法,基于搅拌摩擦焊对接接头的试验数据,预测其抗拉强度。对数据集进行特征分析后,选取包括材料各元素质量分数、焊接工艺参数、板材属性等12个关键参数作为输入特征进行抗拉强度的预测。【结果】结果显示,测试集的R^(2)达到0.92,测试集五折交叉验证R^(2)达到0.9。表明所采用的机器学习算法在预测搅拌摩擦焊对接接头抗拉强度方面表现出色。其中,随机森林算法的预测效果最好,测试集R^(2)为0.955,五折交叉验证R^(2)达到0.935,并通过5.82 mm厚的6082-T6铝合金板材的试验结果为试验数据外推验证集验证了该方法的无偏性。【结论】这表明,对于搅拌摩擦焊对接接头抗拉强度的预测,数据驱动的解决方案能够提升并优化传统解决方案的性能和效率。
[Objective]The aim is to explore predictive effect of data-driven methods on tensile strength of aluminum alloy friction stir welded butt joints.[Methods]In this paper,machine learning algorithms such as decision tree,random forest,support vector machine and artificial neural network of Python programming language were utilized to predict tensile strength of friction stir welded butt joints based on test data.After conducting feature analysis on the dataset,12 key parameters including mass fraction of each element in the material,welding parameters,and plate properties were selected as input features to predict tensile strength.[Results]The results show that R^(2) of test set reaches 0.92,and R^(2)of five-fold cross-validation test set reaches 0.9.It indicates that the adopted machine learning algorithm performs well in predicting tensile strength of friction stir welded butt joints.Among them,random forest algorithm has the best prediction effect.R^(2) of test set is 0.955,and R^(2)of five-fold cross-validation reaches 0.935.The unbiasedness of this method is verified by extrapolating validation set of test data through test results of 5.82 mm thick 6082-T6 aluminum alloy plates.[Conclusion]This indicates that for tensile strength prediction of friction stir welded butt joints,data-driven solutions can enhance and optimize performance and efficiency of traditional solutions.
作者
丁来顺
陈秋任
刘勇
付条奇
吴坤
王显会
DING Laishun;CHEN Qiuren;LIU Yong;FU Tiaoqi;WU Kun;WANG Xianhui(Nanjing University of Science and Technology,Nanjing 210094,China;Nanjing University of Technology,Nanjing 211816,China;National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology,Baotou 014030,Inner Mongolia,China)
出处
《焊接》
2025年第9期59-69,共11页
Welding & Joining
基金
特种车辆设计制造集成技术全国重点实验室开放基金(GZ2023KF014)。
关键词
搅拌摩擦焊
6082铝合金
机器学习
热输入
强度预测
数据驱动
friction stir welding
6082 aluminum alloy
machine learning
heat input
strength prediction
data-driven
