Neural Network Modeling and Parameter Prediction for Arc Length of Pulsed Gas Metal Arc Welding
-
摘要: 针对脉冲熔化极气体保护焊中的基值电流、脉冲电流、脉冲时间、脉冲频率和电流上升速度等5个核心脉冲参数,通过高速摄影系统采集不同参数组合下焊接过程中的电弧弧长变化,并基于60条所得试验结果建立了关于电弧长度的BP神经网络预测模型。利用该模型预测脉冲参数与焊接弧长的相关性规律,建立的弧长预测模型相关系数R2=0.91,预测误差波动范围为[-7.065 2%,7.301 0%],在单因素预测中能够较好地反映脉冲参数对弧长的影响规律和变化趋势。Abstract: Aiming at the five core pulse parameters of pulsed gas metal arc welding, such as the base current, pulse current, pulse time, pulse frequency and current rising speed, the arc length changes during welding process under different parameter combinations are collected by using the high-speed photography system, and based on 60 experimental results, a BP neural network prediction model for arc length is established. The correlation coefficient R2=0.91, and the prediction error range is [-7.065 2%,7.301 0%]. The BP neural network prediction model can well reflect the variation trend of arc length affected by the pulse parameters in single factor prediction.
-
Keywords:
- BP neural network /
- pulse parameters /
- P-GMAW /
- arc length
-
-
[1] 杨春利,林三宝.电弧焊基础[M].哈尔滨:哈尔滨工业大学出版社, 2003. [2] 鲍爱莲,耿正,刘万辉. GMAW熔滴过渡过程稳定性自相关分析[J].焊接学报, 2008, 29(1):77-80. [3] 李科,齐志龙,吴志生,等. MIG焊熔滴过渡与电弧形态的观察与分析[J].焊接, 2016(1):19-22. [4] 华学明,李芳,陆志强,等. GMAW-P频率特性复合弧长适应控制法[J].焊接学报, 2009, 30(10):53-56. [5] 张裕,薛钢,吴艳明,等. GMAW-P脉冲参数对焊接过程及焊缝尺寸的影响[J].材料开发与应用, 2021, 36(4):76-81. [6] 张刚,黄健康,石玗,等.基于脉冲电流参数的铝合金脉冲MIG焊过程控制[J].焊接学报, 2013, 34(12):59-62. [7] 黄健康,石玗,卢立晖,等.脉冲MIG焊建模仿真分析及弧长控制[J].机械工程学报, 2011, 47(4):37-41. [8] 张涛,桂卫华,王随平.脉冲熔化极气体保护焊的弧长和熔滴尺寸控制[J].中南大学学报(自然科学版), 2012, 43(1):215-220. [9] 严春妍,胡绳荪,郭院波,等. CO2焊接弧长控制模型[J].焊接学报, 2005, 26(6):69-72. [10] GHOSH P K, DORN L, KULKARNI S, et al. Arc characteristics and behaviour of metal transfer in pulsed current GMA welding of stainless steel[J]. Journal of Materials Processing Technology, 2009, 209(3):1262-1274.
[11] WANG Q, QI B J, CONG B Q, et al. Output characteristic and arc length control of pulsed gas metal arc welding process[J]. Journal of Manufacturing Processes, 2017, 29:427-437.
[12] 王猛,何实,吕晓春,等.基于GA+BP神经网络预测脉冲钨极氩弧横焊焊缝成形[J].焊接, 2015(8):18-21. [13] 郭艳平,陈剑虹,侯凤贞.基于神经网络模型的CMT脉冲焊接焊缝几何形状预测[J].铸造技术, 2018, 39(11):2575-2579. [14] 刘立鹏,王伟,董培欣,等.基于遗传神经网络的焊接接头力学性能预测系统[J].焊接学报,2011,32(7):105-108+118. [15] 余果,尹玉环,高嘉爽,等.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. [16] 张雨浓,杨逸文,李巍.神经网络权值直接确定法[M].广州:中山大学出版社, 2010:1-50. [17] 施彦,韩力群,廉小亲.神经网络设计方法与实例分析[M].北京:北京邮电大学出版社, 2009:1-36. [18] 丛爽.面向MATLAB工具箱的神经网络理论与应用[M]. 3版.合肥:中国科学技术大学出版社, 2009:1-5, 63-92.
计量
- 文章访问数: 113
- HTML全文浏览量: 9
- PDF下载量: 13