高级检索

基于正交试验-BP神经网络的GH4169膜片微束TIG焊接工艺优化

余果,尹玉环,高嘉爽,郭立杰

余果,尹玉环,高嘉爽,郭立杰. 基于正交试验-BP神经网络的GH4169膜片微束TIG焊接工艺优化[J]. 焊接学报, 2018, 39(11): 119-123. DOI: 10.12073/j.hjxb.2018390285
引用本文: 余果,尹玉环,高嘉爽,郭立杰. 基于正交试验-BP神经网络的GH4169膜片微束TIG焊接工艺优化[J]. 焊接学报, 2018, 39(11): 119-123. DOI: 10.12073/j.hjxb.2018390285
YU Guo, YIN Yuhuan, GAO Jiashuang, GUO Lijie. Orthogonal experiment method and BP neural networks in optimization of microbeam TIG welded GH4169[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(11): 119-123. DOI: 10.12073/j.hjxb.2018390285
Citation: YU Guo, YIN Yuhuan, GAO Jiashuang, GUO Lijie. Orthogonal experiment method and BP neural networks in optimization of microbeam TIG welded GH4169[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(11): 119-123. DOI: 10.12073/j.hjxb.2018390285

基于正交试验-BP神经网络的GH4169膜片微束TIG焊接工艺优化

Orthogonal experiment method and BP neural networks in optimization of microbeam TIG welded GH4169

  • 摘要: 将正交试验与BP神经网络结合用于0.2 mm厚GH4169膜片微束TIG焊接工艺参数优化,根据正交试验结果对神经网络模型进行训练,建立了峰值电流、基值电流、焊接速度、脉冲频率与接头直径、高度、抗拉力的BP神经网络模型. 结果表明,在BP神经网络模型预测的基础上,结合小步长搜索法获得的最佳工艺参数范围为峰值电流11.6 A±0.2 A、基值电流4.3 A±0.1 A、焊接速度4.14 mm/s±0.1 mm/s、脉冲频率52 Hz±2 Hz. 通过试验验证,4组试样各指标试验值均处于模型预测值范围内,抗拉力值均高于先期试验. 试验结果证明,该模型预测精度高,并且该工艺优化方法能有效提高实际工艺设计的效率.
    Abstract: Orthogonal experiment was combined with BP neural networks to optimize welding process parameters of 0.2 mm GH4169 diaphragms by using microbeam TIG welding echnique. The BP neural networks model was trained by the results of orthogonal experiment, and the BP neural networks model described the relationship between welding joints’ properties (diameter, height, and tensile resistance) and welding process parameters, including peak current, background current, welding velocity, and pulse frequency. The results shows that according to the orthogonal experiment and the prediction of BP neural networks model, then small-step method is used for further searching, the best parameters are found when peak current is 11.6 A±0.2 A, background current is 4.3 A±0.1 A, welding velocity is 4.14 mm/s±0.1mm/s, and pulse frequency is 52 Hz±2 Hz. The xperiment validated that the test values of four samples are within the prediction range, and the tensile force is higher than that of previous experiment. It proves that the model has a high accuracy of prediction and the method can increase the efficiency of process design availably.
  • [1] 刘锦凡, 孙 丹, 陈雪巍, 等. 蓄压器膜盒机械刚度对液体火箭POGO振动影响研究[J]. 振动与冲击, 2016, 35(19): 168 ? 171
    Liu Jinfan, Sun Dan, Chen Xuewei, et al. Influences of mechanical stiffness of accumulator on POGO vibration of liquid rockets[J]. Journal of Vibration and Shock, 2016, 35(19): 168 ? 171
    [2] Chen Y, Zhang K, Huang J, et al. Characterization of heat affected zone liquation cracking in laser additive manufacturing of Inconel 718[J]. Materials & Design, 2016, 90: 586 ? 594.
    [3] Mei Y P, Liu Y C, Liu C X, et al. Effect of base metal and welding speed on fusion zone microstructureand HAZ hot-cracking of electron-beam welded Inconel 718[J]. Materials & Design, 2016, 89: 964 ? 977.
    [4] Azadian S, Wei L Y, Warren R. Delta phase precipitation in Inconel 718[J]. Materials Characterization, 2004, 53: 7 ? 16.
    [5] Chen G Q, Zhang B G, Lü T M, et al. Causes and control of welding cracks in electron-beam-welded superalloy GH4169 joints[J]. Transactions of Nonferrous Metals Society of China, 2013, 23: 1971 ? 1976.
    [6] Chen Yuhua, Liu Dongya, Xie Jilin, et al. Development of the active flux in superalloy laser welding and the effect on the weld formation[J]. China Welding, 2017, 26(1): 44 ? 48.
    [7] 李延民. 超薄壁GH4169膜盒微束等离子焊接工艺研究[D]. 北京: 北京工业大学, 2014.
    [8] 李卓然, 冯广杰, 徐 慨, 等. 高温合金GH4169真空扩散连接工艺[J]. 焊接学报, 2013, 34(6): 21 ? 24
    Li Zhuoran, Feng Guangjie, Xu Kai, et al. Vacuum diffusion bonding of GH4169 superalloy[J]. Transactions of the China Welding Institution, 2013, 34(6): 21 ? 24
    [9] Shojaeefard M H, Behnagh R A, Akbari M, et al. Modeling and pareto optimization of mechanical properties of friction stir welded AA7075/AA5083 butt joints using neural network and particle swarm algorithm[J]. Materials & Design, 2013, 44(2): 190 ? 198.
    [10] 夏卫生, 张海鸥, 王桂兰, 等. 基于多层ANN的机器人等离子熔射智能化模型[J]. 焊接学报, 2009, 30(7): 41 ? 44
    Xia Weisheng, Zhang Haiou, Wang Guilan, et al. Intelligent process modeling of robotic plasma spraying based on multi-layer artificial neural network[J]. Transactions of the China Welding Institution, 2009, 30(7): 41 ? 44
    [11] 王东生, 杨 斌, 田宗军. 基于遗传神经网络的等离子喷涂纳米ZrO2-7%Y2O3涂层工艺参数优化[J]. 焊接学报, 2013, 34(3): 10 ? 14
    Wang Dongsheng, Yang Bin, Tian Zongjun, et al. Process parameters optimization of nanostructured ZrO2-7%Y2O3 coating deposited by plasma spraying based on genetic algorithms and neural networks[J]. Transactions of the China Welding Institution, 2013, 34(3): 10 ? 14
    [12] 滕 凯. 基于正交试验和BP神经网络的Ti-6Al-4V合金电火花线切割工艺参数优化[J]. 制造业自动化, 2015, 37(10): 24 ? 27
    Teng Kai. Parameter optimization of Ti-6Al-4V alloy wire cutting process based on orthogonal test and BP neural network[J]. Manufacturing Automation, 2015, 37(10): 24 ? 27
  • 期刊类型引用(9)

    1. 关皓真,张裕,孙磊,吴艳明. 脉冲熔化极气体保护焊弧长神经网络建模及参数预测. 材料开发与应用. 2024(03): 28-35 . 百度学术
    2. 王超,陈信宇,吴春彪,李雷,王洁. 基于快速蜜蜂试验法的304不锈钢激光焊工艺优化. 焊接学报. 2023(02): 102-110+135 . 本站查看
    3. 杜晓辉,陈凡红,刘帅,朱敏杰,许佳豪. 压力传感器波纹膜片低应力激光焊接工艺. 光学精密工程. 2023(11): 1652-1659 . 百度学术
    4. 杨华庆,张建护,唐德渝,王克宽. 机器人立体视觉系统标定误差预测补偿技术. 控制工程. 2022(04): 757-762 . 百度学术
    5. 朱胜,张雨豪,郭迎春,王晓明,常青,赵阳. 高能微弧沉积H65黄铜涂层试验研究. 热加工工艺. 2021(14): 102-104+108 . 百度学术
    6. 易润华,邓黎鹏,程东海,刘奋成. 基于多指标综合评分方差分析的镍铬合金储能缝焊工艺研究. 材料导报. 2021(14): 14161-14165 . 百度学术
    7. 刘晓明,刘威,李龙女,朱高嘉,姜文涛. 基于改进神经网络和遗传算法的真空灭弧室优化设计. 真空科学与技术学报. 2020(04): 359-364 . 百度学术
    8. 任书文,陈士忠,刘子金,夏忠贤,侯爱山,王永华. 钢筋骨架焊接工艺参数的优化研究. 建筑机械化. 2020(11): 98-101 . 百度学术
    9. 尹燕,赵超,潘存良,路超,张瑞华. 气体流量对射频等离子体球化GH4169合金粉末的影响. 焊接学报. 2019(11): 100-105+165 . 本站查看

    其他类型引用(9)

计量
  • 文章访问数:  648
  • HTML全文浏览量:  5
  • PDF下载量:  3
  • 被引次数: 18
出版历程
  • 收稿日期:  2017-07-30

目录

    /

    返回文章
    返回