目的 找到一种高效、精确的数据驱动方法,以解决6061-T6铝合金机器人搅拌摩擦焊（Friction Stir Welding,FSW）工艺中多目标质量的快速预测与优化难题。方法 结合数值仿真与人工智能技术,首先建立了机器人FSW过程的三维瞬态热源模型与顺序热力耦合模型,系统模拟了不同工艺参数组合下的温度场与残余应力场。随后,以转速、焊速和下压力为输入变量,以仿真与实验获得的峰值温度、最大纵向残余应力及实验获得的接头抗拉强度为输出响应,构建并训练了反向传播神经网络（Back Propagation Neural Network,BPNN）预测模型。结果 构建的BPNN模型表现出优异的预测性能,它对峰值温度、残余应力和抗拉强度的预测决定系数（R2）分别达到0.934 8、0.840 7和0.726 2,最大预测误差均小于5%。分析表明,转速对焊接温度影响最为显著,焊速对残余应力影响最大。结论 采用数值仿真与神经网络相结合的混合建模策略,实现了机器人搅拌摩擦焊工艺参数与焊接质量的高效预测与优化。相较于单一的传统实验或数值仿真方法,该方法在保证预测精度的同时显著降低了计算成本,BPNN模型在预测阶段的计算效率较有限元仿真提升了数个数量级,为复杂焊接工艺的智能化设计与优化提供了可靠的理论依据和工程实用工具。
Abstract
The work aims to propose an efficient and precise data-driven approach to achieve rapid prediction and optimization of the robotic friction stir welding (FSW) process for 6061-T6 aluminum alloy. Firstly, by combining numerical simulation with artificial intelligence technology, a three-dimensional transient heat source model and a sequentially coupled thermo-mechanical model were developed to accurately simulate the temperature and residual stress fields under various welding parameters. Subsequently, a back-propagation neural network (BPNN) model was established and trained, with the rotational rate, welding speed and plunge force as input parameters, and the simulated peak temperature, maximum longitudinal residual stress, and ultimate tensile strength as output parameters. The BPNN model demonstrated remarkable predictive accuracy with the corresponding determination coefficients (R2) of 0.9348, 0.840 7, and 0.726 2 for peak temperature, residual stress, and tensile strength. The maximum prediction errors remained below 5%. Furthermore, rotational rate exerted the most significant effect on peak temperature, while residual stress distribution was predominantly controlled by welding speed. These results validate that the proposed hybrid strategy effectively offers the efficient prediction and optimization of both robotic FSW parameters and welding quality. Compared with traditional single methods regarding experimental or numerical simulation, this approach significantly reduces computational costs without sacrificing accuracy. The BPNN model is more efficient than conventional finite element simulation by several orders of magnitude. This provides a reliable theoretical basis and practical engineering tools for the intelligent design and optimization of complex welding processes.
关键词
机器人搅拌摩擦焊 /
铝合金 /
神经网络 /
数值仿真 /
工艺优化
Key words
robotic friction stir welding /
aluminum alloy /
neural network /
numerical simulation /
process optimization
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王千瑞, 居晓锋, 李振华, 等. 高强铝合金焊接对板材性能的影响[J]. 电焊机, 2024, 54(10): 116-123.
WANG Q R, JU X F, LI Z H, et al.Effect of High-Strength Aluminum Alloy Welding on the Properties of Aluminum Alloy Plate[J]. Electric Welding Machine, 2024, 54(10): 116-123.
[2] WANG Z X, LI M Y, HAN Q H, et al.Structural Fire Behaviour of Aluminium Alloy Structures: Review and Outlook[J]. Engineering Structures, 2022, 268: 114746.
[3] 王洪铎, 王子龙, 常素腾, 等. 5052铝合金搅拌摩擦焊接头组织与性能研究[J]. 精密成形工程, 2025, 17(9): 60-69.
WANG H D, WANG Z L, CHANG S T, et al.Microstructure and Properties of 5052 Aluminum Alloy Stir Friction Welded Joints[J]. Journal of Netshape Forming Engineering, 2025, 17(9): 60-69.
[4] 张子傲, 张知航, 黄继华, 等. 高速列车铝合金车体焊接工艺研究进展[J]. 轨道交通材料, 2023, 2(1): 1-7.
ZHANG Z A, ZHANG Z H, HUANG J H, et al.Advance in the Research of Welding Procedures for Aluminum Car Bodies of High Speed Train[J]. Materials for Rail Transportation System, 2023, 2(1): 1-7.
[5] SEN M, PURI A B.Formation of Intermetallic Compounds (IMCs) in FSW of Aluminum and Magnesium Alloys (Al/Mg Alloys) - a Review[J]. Materials Today Communications, 2022, 33: 105017.
[6] AHMED M M Z, EL-SAYED SELEMAN M M, FYDRYCH D, et al. Friction Stir Welding of Aluminum in the Aerospace Industry: The Current Progress and State-of-the-Art Review[J]. Materials, 2023, 16(8): 2971.
[7] 周海鹏, 邢松龄, 韩赞东, 等. 6005A-T6铝合金搅拌摩擦焊接头的疲劳性能分析[J]. 热加工工艺, 2025, 54(3): 35-40.
ZHOU H P, XING S L, HAN Z D, et al.Fatigue Performance Analysis for Friction Stir Welding Joints of 6005A-T6 Aluminum Alloy[J]. Hot Working Technology, 2025, 54(3): 35-40.
[8] 程渝龙, 赵素, 李云良, 等. 新能源电池托盘中镁/铝异种合金搅拌摩擦焊研究[J]. 热加工工艺, 2025, 54(20): 175-182.
CHENG Y L, ZHAO S, LI Y L, et al.Study on Friction Stir Welding of Magnesium/Aluminum Dissimilar Alloy in New Energy Battery Tray[J]. Hot Working Technology, 2025, 54(20): 175-182.
[9] PATIL S, NAGAMADHU M, MALYADRI T.A Critical Review on Microstructure and Hardness of Aluminum Alloy 6061 Joints Obtained by Friction Stir Welding-Past, Present, and Its Prospects[J]. Materials Today: Proceedings, 2023, 82: 75-78.
[10] KUMAR S, GAO S, WU C S, et al.Towards Sustainability: Critical Insights into Solid-State Joining Processes for Developing Lightweight Hybrid Structures[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2026, 13(1): 89-115.
[11] SUBRAMANIAN S, NATARAJAN E, KHALFALLAH A, et al.Current Trends and Emerging Strategies in Friction Stir Spot Welding for Lightweight Structures: Innovations in Tool Design, Robotics, and Composite Reinforcement—A Review[J]. Crystals, 2025, 15(6): 556.
[12] BORAH M J, SARMA K, NIRSANAMETLA Y, et al.A Critical Review on Friction Stir Spot Welding of Aluminium Alloys: Tool, Mechanical, and Micro-Structural Characteristics[J]. Crystals, 2025, 15(9): 755.
[13] WALZ D, SOMMER K, WERZ M, et al.Development and Evaluation of a Robot Guided Friction Stir Welding Gun[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2025, 12(6): 1795-1808.
[14] 李雨, 周利, 杨朝旭, 等. 搅拌摩擦焊技术在汽车材料连接中的应用、发展与挑战[J]. 电焊机, 2025, 55(8): 24-37.
LI Y, ZHOU L, YANG Z X, et al.Application, Development and Challenges of Friction Stir Welding Technology in Automotive Material Joining[J]. Electric Welding Machine, 2025, 55(8): 24-37.
[15] 卢云飞, 黎训学, 齐锋, 等. 机器人搅拌摩擦焊电主轴的设计与验证[J]. 机电工程技术, 2025, 54(13): 90-95.
LU Y F, LI X X, QI F, et al.Design and Verification of Electric Spindle for Robot Friction Stir Welding[J]. Mechanical & Electrical Engineering Technology, 2025, 54(13): 90-95.
[16] 韩玉莹, 王梦雪, 王歆一, 等. GTA偏置预热的2219铝合金厚板搅拌摩擦焊接温度场与受力特性[J]. 焊接, 2025(9): 32-38.
HAN Y Y, WANG M X, WANG X Y, et al. Temperature Field and Mechanical Characteristics of Friction Stir Welding in2219 Aluminum Alloy Thick Plates with GTA Offset Preheating[J]. Welding & Joining, 2025(9): 32-38.
[17] 李亭, 史清宇, 李红克, 等. 铝合金搅拌摩擦焊接头残余应力分布[J]. 焊接学报, 2007, 28(6): 105-108.
LI T, SHI Q Y, LI H K, et al.Residual Stresses for Friction Stir Welded Al Sheets[J]. Transactions of the China Welding Institution, 2007, 28(6): 105-108.
[18] CAI Y Y, ZHAN R, LI M, et al.A Force-Data-Constrained Approach for Simulation of Temperature Field and Residual Stress in Friction Stir Welding[J]. Materials Letters, 2025, 394: 138639.
[19] EL-ZATHRY N E, AKINLABI S, WOO W L, et al. Enhancing Friction Stir-Based Techniques with Machine Learning: A Comprehensive Review[J]. Machine Learning: Science and Technology, 2025, 6(2): 021001.
[20] 尤佳庆, 林志成, 赵运强, 等. 智能化搅拌摩擦焊接技术研究进展[J]. 金属加工(热加工), 2023(2): 17-26.
YOU J Q, LIN Z C, ZHAO Y Q, et al.Research Progress of Intelligent Friction Stir Welding Technology[J]. MW Metal Forming, 2023(2): 17-26.
[21] DORBANE A, HARROU F, DURSUN B, et al.Enhancing Predictive Capabilities: Machine Learning Approaches for Predicting Mechanical Behavior in Friction Stir Welded Aluminum Alloys[J]. Journal of Materials Engineering and Performance, 2025, 34(4): 3566-3584.
[22] 丁来顺, 陈秋任, 刘勇, 等. 基于数据驱动的搅拌摩擦焊对接接头强度预测[J]. 焊接, 2025(9): 59-69.
DING L S, CHEN Q R, LIU Y, et al.Data-Driven Prediction of Tensile Strength for Friction Stir Welded Butt Joints[J]. Welding & Joining, 2025(9): 59-69.
[23] NANDAN R, ROY G G, DEBROY T.Numerical Simulation of Three-Dimensional Heat Transfer and Plastic Flow during Friction Stir Welding[J]. Metallurgical and Materials Transactions A, 2006, 37(4): 1247-1259.
[24] RIAHI M, NAZARI H.Analysis of Transient Temperature and Residual Thermal Stresses in Friction Stir Welding of Aluminum Alloy 6061-T6 via Numerical Simulation[J]. The International Journal of Advanced Manufacturing Technology, 2011, 55(1): 143-152.
[25] SONG M, KOVACEVIC R.Thermal Modeling of Friction Stir Welding in a Moving Coordinate System and Its Validation[J]. International Journal of Machine Tools and Manufacture, 2003, 43(6): 605-615.
[26] SHEN W J, XUE F M, LI C Z, et al.Study on Constitutive Relationship of 6061 Aluminum Alloy Based on Johnson-Cook Model[J]. Materials Today Communications, 2023, 37: 106982.
[27] XIONG X H, WANG C, WANG F S, et al.Optimization of Process Parameters for Induction Welding of Composite Materials Based on NSGA-II and BP Neural Network[J]. Materials Today Communications, 2022, 33: 104749.
[28] WU C B, WANG C, KIM J W.Bending Deformation Prediction in a Welded Square Thin-Walled Aluminum Alloy Tube Structure Using an Artificial Neural Network[J]. The International Journal of Advanced Manufacturing Technology, 2021, 117(9): 2791-2805.
基金
国家重点研发计划（2023YFE0201500）; 广东省重点人才计划（2023TQ07C702）; 广东省科学院青年人才专项杰出青年项目（2024GDASQNRC-0103）; 广东省科协青年科技人才培育计划（SKXRC2025080）; 广东省自然科学基金面上项目（2025A1515011033）
PDF(10087 KB)
渝公网安备 50010702501719号 渝ICP备15012534号-4
