[1]黄无云,刘益剑,刘宗熙,等.焊道形貌特征的BP神经网络建模与预测[J].南京师范大学学报(工程技术版),2021,21(01):001-7.[doi:10.3969/j.issn.1672-1292.2021.01.001]
　Huang Wuyun,Liu Yijian,Liu Zongxi,et al.Welded Surface Morphology Modeling and PredictionBased on BP Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2021,21(01):001-7.[doi:10.3969/j.issn.1672-1292.2021.01.001]
点击复制

焊道形貌特征的BP神经网络建模与预测
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
21卷
期数:
2021年01期
页码:
001-7
栏目:
控制科学与工程
出版日期:
2021-03-15

文章信息/Info

Title:
Welded Surface Morphology Modeling and PredictionBased on BP Neural Network
作者:
黄无云1; 刘益剑1; 刘宗熙1; 杨继全1; 朱钊伟1; 谢 非1; 史建军2
(1.南京师范大学南瑞电气与自动化学院,江苏 南京 210023)(2.南京中科煜宸激光技术有限公司,江苏 南京 210038)
Author(s):
Huang Wuyun1; Liu Yijian1; Liu Zongxi1; Yang Jiquan1; Zhu ZhaoWei1; Xie Fei1; Shi Jianjun2
(1.NARI School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210023,China)(2.Nanjing Zhongke Yuchen Laser Technology Co.,Ltd.,Nanjing 210038,China)
关键词:
焊道形貌; BP神经网络; 优化求解; 粒子群算法
Keywords:
weld bead morphology; BP neural network; optimization solution; PSO algorithm
分类号:
TP183
DOI:
10.3969/j.issn.1672-1292.2021.01.001
文献标志码:
A
摘要:
良好的焊道是成功进行电弧增材制造的保障,其受到焊接电流、电压、扫描速度、送丝速度等多种参数影响. 提出了以焊道高度、宽度为形貌特征的4输入2输出BP神经网络模型,并利用PSO进行了神经网络权值的优化求解. 实验结果表明,设计的BP神经网络实现了对焊道形貌的预测,为后续电弧增材制造的实时预测与控制提供了模型基础.
Abstract:
A good weld bead provides a guarantee for successful wire arc additive manufacturing,which is affected by various parameters such as welding current,voltage,scanning speed,and wire feed speed. A four-input and two-output BP neural network model is proposed,which is applied to the surface morphology characteristic identification of the weld bead height and width. The particle swarm optimization(PSO)algorithm is used to optimize the neural network weight. Experimental results show that the BP neural network designed in this paper realizes the prediction of the weld bead morphology and that it provides a model basis for the real-time prediction and control of subsequent arc additive manufacturing.

参考文献/References:

[1] CUNNINGHAM C R,FLYNN J M,SHOKRANI A,et al. Invited review article:strategies and processes for high quality wire arc additive manufacturing manufacturing[J]. Additive Manufacturing,2018,22:672-686.
[2]XIANG D F,WANG Y B,LIU J,et al. Research status of welding rapid prototyping technology[J]. Welding Ttechnology,2012,41(7):1-6.
[3]何冠宇. 电弧增材成形过程电弧及溶滴过渡行为研究[D]. 兰州:兰州理工大学,2016.
[4]余淑荣,程能弟,黄健康,等. 旁路耦合微束等离子弧焊增材制造的热过程[J]. 材料导报,2019,33(1):162-166.
[5]LI P,ZENG S Q,HU X Y. Direct laser fabrication of thin-walled metal parts under open-loop control[J]. International Journal of Machine Tools and Manufacture,2007,47(6):996-1002.
[6]JANDRIC Z,LABUDOVIC M,KOVACEVIC R. Effect of heat sink on microstructure of three-dimensional parts built by welding-based deposition[J]. International Journal of Machine Tools and Manufacture,2004,44(7/8):785-796.
[7]BOLARINWA J K,SALIU O S,GODWIN I E,et al. Review of GTAW welding parameters[J]. Journal of Minerals and Materials Characterization and Engineering,2018,6(5):541-554.
[8]SEN M,MUKHERJEE M,PAL T K. Evaluation of correlations between DP-GMAW process parameters and bead geometry[J]. Welding Journal,2015,94(8):265-279.
[9]MOHAMMED A,TOMáS M. A review of modularization techniques in artificial neural networks[J]. Artificial Intelligence Review,2019,52(1):527-561.
[10]SUGA Y,NARUS M,TOKIWA T. Application of neural network to visual sensing of weld line and automatic tracking in robot welding[J]. Welding in the World,1994,34:275-282.
[11]MADHIARASAN M,DEEPA S N. Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting[J]. Artificial Intelligence Review,2017,48(4):449-471.
[12]YANG S M,WANG Y L,WANG M Y,et al. Excitation function learnable neural network[J]. Journal of Jiangnan University(Natural Science Edition),2015,14(6):689-694.
[13]杨亚超,全惠敏,邓林峰,等. 基于神经网络的焊机参数预测方法[J]. 焊接学报,2018,39(1):32-36,130.
[14]张淑珍,冯振民,于子然. 一种弧焊机器人轨迹跟踪控制方法的研究[J]. 机械制造与自动化,2016,45(6):159-163.
[15]岳中彤. 基于PSO与BP神经网络的脱机手写体汉字识别算法[J]. 信息化研究,2018,44(2):68-70.
[16]YIN H X,WANG K,ZHANG T Z,et al. Wheelset axle box failure prediction of urban rail bogie based on PSO-BP neural network[J]. Complex Systems and Complexity Science,2015,12(4):97-103.
[17]JOSEPH A Y,DOUW G B B. Combining BP with PSO algorithms in weights optimization and ANNs training for mass appraisal of properties[J]. International Journal of Housing Markets and Analysis,2018,11(2):290-314.

相似文献/References:

[1]陈德良,曲维光,周春林.基于神经网络的教师教学评估系统[J].南京师范大学学报(工程技术版),2004,04(01):073.
　Chen Deliang,Qu Weiguang,Zhou Chunlin.Evaluation System for Teaching Quality Based on Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2004,04(01):073.
[2]张会敏,胡　太.基于SVM的老年痴呆症智能诊断研究[J].南京师范大学学报(工程技术版),2016,16(02):086.[doi:10.3969/j.issn.1672-1292.2016.02.014]
　Zhang Huimin,Hu Tai.A Study on Intelligent Diagnosis of Senile Dementia Based on SVM[J].Journal of Nanjing Normal University(Engineering and Technology),2016,16(01):086.[doi:10.3969/j.issn.1672-1292.2016.02.014]
[3]王凯翔.基于多元回归和神经网络途径的太湖富营养化指标分析与预测[J].南京师范大学学报(工程技术版),2017,17(02):070.[doi:10.3969/j.issn.1672-1292.2017.02.011]
　Wang Kaixiang.Taihu Lake Eutrophication Index Analysis and PredictionBased on Multiple Regression and Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2017,17(01):070.[doi:10.3969/j.issn.1672-1292.2017.02.011]

备注/Memo

备注/Memo:
收稿日期:2020-09-12.
基金项目:国家重点研发计划项目(2017YFB11032002)、江苏省科技成果转化专项资金项目(BA2020004)、2020年江苏省省级工业和信息产业转型升级专项资金项目(智能化金属增减材制造装备).
通讯作者:刘益剑,博士,副教授,研究方向:金属增材制造、机器人技术. E-mail:63055@njnu.edu.cn
更新日期/Last Update: 2021-03-15