基于网格聚类算法的搅拌摩擦焊接质量评价系统研究
Quality Evaluation of Friction Stir Welding Based on Grid Clustering Algorithm
- 2026年56卷第7期 页码:34-40
收稿:2025-02-14,
修回:2025-06-01,
纸质出版:2026-07-20
DOI: 10.7512/j.issn.1001-2303.2026.07.04
移动端阅览

浏览全部资源
扫码关注微信
收稿:2025-02-14,
修回:2025-06-01,
纸质出版:2026-07-20
移动端阅览
针对搅拌摩擦焊接过程中的焊接质量波动问题,设计了一套基于网格聚类算法的搅拌摩擦焊接质量评价系统。通过采集搅拌摩擦焊接过程中的焊接区温度、下压量、搅拌头倾角、搅拌头转速及焊接速度等参数,经过滤波、归一化等数据处理后作为数据样本。根据高铁车钩座搅拌摩擦焊接过程的特点,对网格聚类算法进行了优化,设计了中位数簇类识别算法,实现了对焊缝的工件归属识别。设计了焊接质量评价算法,在经过大量样本训练后,获得了车钩座搅拌摩擦焊接质量评价系统。利用拉伸试验对系统进行了验证,结果表明拉伸强度与量化评分值之间呈现出高度一致的变化趋势,证明该系统能够对车钩座搅拌摩擦焊接质量进行有效评价,对提升焊接产品质量稳定性具有显著意义。
A set of friction stir welding quality evaluation system based on grid clustering algorithm was designed to address the problem of welding quality fluctuations in the process of friction stir welding. By collecting parameters such as welding zone temperature
plunge depth
tool angle
tool rotation speed
and welding speed during the friction stir welding process
and processing them through filtering
normalization
etc. as data samples
the grid clustering algorithm was optimized according to the characteristics of the high-speed railway car hook seat friction stir welding
and a median cluster recognition algorithm was designed to achieve workpiece attribution recognition of the weld seam. A welding quality evaluation algorithm was designed
and after training with a large number of samples
a car hook seat friction stir welding quality evaluation system was obtained. The system was validated using tensile tests
the results showed a highly consistent trend between tensile strength and quantitative scoring values
proving that the system can effectively evaluate the quality of friction stir welding of railway car hook seat and has significant significance in improving the stability of welding product quality.
Song Y , Yang X , Cui L , et al . Defect features and mechanical properties of friction stir lap welded dissimilar AA2024-AA7075 aluminum alloy sheets [J]. Materials & Design , 2014 , 55 : 9 - 18 .
Ahmed S , Saha P . Development and testing of fixtures for friction stir welding of thin aluminum sheets [J]. Journal of Materials Processing Technology , 2018 , 252 : 242 - 248 .
Okuyucu H , Kurt A , Arcaklioglu E . Artificial neural network application to the friction stir welding of aluminum plates [J]. Materials and Design , 2007 , 28 ( 1 ): 78 - 84 .
Nait Salah A , Mehdi H , Mehmood A , et al . Optimization of process parameters of friction stir welded joints of dissimilar aluminum alloys AA3003 and AA6061 by RSM [J]. Materials Today:Proceedings , 2022 , 56 : 1675 - 1683 .
Verma S , Gupta M , Misra J P . Performance evaluation of friction stir welding using machine learning approaches [J]. MethodsX , 2018 , 5 : 1048 - 1058 .
王希靖 , 徐成 , 张杰 , 等 . 基于神经网络BP算法的7075-T651铝合金搅拌摩擦焊焊接接头疲劳寿命预测 [J]. 兰州理工大学学报 , 2008 , 34 ( 3 ): 12 - 15 .
WANG X J , XU C , ZHANG J , et al . Fatigue life prediction of friction-stir welding joints of aluminum alloy
7070 - 7651 based on BP algorithm of neural network [J]. Journal of Lanzhou University of Technology , 2008 , 34 ( 3 ): 12 - 15 .
Manvatkar V D , Arora A , De A , et al . Neural network models of peak temperature,torque,traverse force,bending stress and maximum shear stress during friction stir welding [J]. Science and Technology of Welding and Joining , 2012 , 17 ( 6 ): 460 - 466 .
池浩瀚 , 刘雪松 , 李世海 . 基于遗传算法及神经网络的6005A-T6铝合金FSW工艺参数优化 [J]. 热加工工艺 , 2021 , 50 ( 07 ): 118 - 120 .
CHI H H , LIU X S , LI S H . Optimization of FSW process parameters for 6005A-T6 aluminum alloy based on genetic algorithm and neural network [J]. Hot Working Technology , 2021 , 50 ( 7 ): 118 - 120 .
李甲顺 . 基于自组织增量学习神经网络的FSW质量评价研究 [D]. 哈尔滨 : 哈尔滨工业大学 , 2019 .
LI J S . Study on FSW quality evaluation based on self-organizing incremental learning neural network [D]. Harbin : Harbin Institute of Technology , 2019 .
叶镭 . 基于密度聚类算法的搅拌摩擦焊过程异常检测研究 [D]. 哈尔滨 : 哈尔滨工业大学 , 2021 .
YE L . Study on anomaly detection of friction stir welding process based on density clustering algorithm [D]. Harbin : Harbin Institute of Technology , 2021 .
Wang H , Bah M J , Hammad M . Progress in Outlier Detection Techniques:A Survey [J]. IEEE Access , 2019 , 7 : 107964 - 108000 .
Chandola V , Banerjee A , Kumar V . Anomaly detection [J]. ACM Computing Surveys , 2009 , 41 ( 3 ): 1 - 58 .
Tang J , Chen Z , Fu A W , et al . Enhancing effectiveness of outlier detections for low density patterns [C]// Advances in Knowledge Discovery and Data Mining , 2002 : 535 - 548 .
Jin W , Tung A K H , Han J , et al . Ranking outliers using symmetric neighborhood relationship [C]// the 10th Pacific-Asia Conference , 2006 : 577 - 593 .
Papadimitriou S , Kitagawa H , Gibbons P B , et al . LOCI:fast outlier detection using the local correlation integral [C]// the 19th International Conference on Data Engineering , 2003 : 315 - 326 .
曹炳琪 . 基于网格聚类优化算法的搅拌摩擦焊接质量评价系统研究 [D]. 哈尔滨 : 哈尔滨工业大学 , 2023 .
CAO B Q . Study on friction stir welding quality evaluation system based on grid clustering optimization algorithm [D]. Harbin : Harbin Institute of Technology , 2023 .
相关作者
相关机构
公网安备11010802024621