基于BP神经网络的光纤激光切割切口粗糙度预测

郭华锋; 李菊丽; 孙涛

doi:10.7510/jgjs.issn.1001-3806.2014.06.016

基于BP神经网络的光纤激光切割切口粗糙度预测

1.
徐州工程学院机电工程学院, 徐州 221000

作者简介: 郭华锋(1981-),男,硕士,讲师,现从事激光加工技术及表面工程技术的研究。E-mail:ghfmaster@163.com.

基金项目:
徐州市科技计划资助项目(XM13B103)
中图分类号:
TG485

Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks

1.
Department of Mechanical and Electronic Engineering, Xuzhou Institute of Technology, Xuzhou 221008, China
CLC number:
TG485

摘要: 为了研究工艺参量对光纤激光切割切口质量的影响,进行了切割T4003不锈钢试验,分析了工艺参量与切口质量之间的关系。采用基于误差反向传播算法的人工神经网络,建立了激光功率、切割速率、辅助气体压力等工艺参量与切口粗糙度之间的预测模型。对切割试验采集的训练样本进行了网络训练,并利用测试样本对训练模型进行验证。结果表明,随着激光功率增加,切口粗糙度增大;随着切割速率和辅助气体压力增加,切口粗糙度减小。神经网络预测模型精度较高,网络训练效果良好,预测值与试验样本值间的最大相对误差为2.4%。训练后检验精度较高,检验样本最大相对误差仅为6.23%。该模型可有效预测激光切割切口表面粗糙度,同时为合理选择及优化工艺参量,提高激光切割质量提供试验依据。
- 激光技术 /
- 切口质量 /
- 反向传播人工神经网络 /
- 粗糙度 /
- 预测
Abstract: In order to study effects of process parameters on kerf quality of fiber laser cutting, the relationship between process parameters and kerf quality was analyzed based on the test of laser cutting T4003 stainless steel. The prediction model between the main process parameters, such as laser power, cutting speed, assistant gas pressure and kerf roughness was established based on error back propagation artificial neural network. The samples collected by the cutting test was network trained and the training model was inspected by the test samples. The results show that, kerf roughness increases while laser power increases and kerf roughness decreases while cutting speed and assist gas pressure increase. The neural network prediction model has high precision and the network training has good effect. The maximum relative error between the predictive values and the test sample value is 2.4%. After training, the prediction model has high inspection precision, the maximum relative error of the test sample is only 6.23%. The model can predict the laser cutting kerf roughness effectively and can provide the experiment basis for selecting and optimizing process parameters and improving laser cutting quality.
- laser technique /
- kerf quality /
- back propagation artificial neural network /
- roughness /
- prediction

[1]	SCINTILLA L D, TRICARICO L. Estimating cutting front temperature difference in disk and CO2 laser beam fusion cutting[J]. Optics Laser Technology, 2012, 44(5):1468-1479.
[2]	PANDEY A K, DUBEY A K. Simultaneous optimization of multiple quality characteristics in laser cutting of titanium alloy sheet[J]. Optics Laser Technology, 2012, 44(6):1858-1865.
[3]	MUHAMMADA N, WHITEHEADA D, BOORB A, et al. Comparison of dry and wet fibre laser profile cutting of thin 316L stainless steel tubes for medical device applications[J]. Journal of Materials Processing Technology, 2010, 210(15): 2261-2267.
[4]	CHOUDHURY I A, SHIRLEY S. Laser cutting of polymeric materials: an experimental investigation [J]. Optics Laser Technology, 2010, 42(3):503-508.
[5]	WANG X H, YAO J H, ZHOU G B, et al. Numerical simulation and experiment of laser cutting liquid crystal display glass substrates[J]. Chinese Journal of Lasers, 2011, 38(6): 1-5 (in Chinese).
[6]	CHEN X Ch, JI L F, BAO Y, et al. Improving cutting quality by analysis of microstructure characteristics and solidification behaviour of recast layer formation on laser cut ceramic[J]. Journal of the European Ceramic Society, 2012, 32(10): 2203-2211.
[7]	JI L F, YAN Y Zh, BAO Y, et al. Crack-free cutting of thick and dense ceramics with CO2 laser by single-pass process[J]. Optics and Lasers in Engineering, 2008, 46(10): 785-790.
[8]	ELTAWAHNI H A, ROSSINI N S, DASSISTI M, et al. Evalaution and optimization of laser cutting parameters for plywood materials[J]. Optics and Lasers in Engineering, 2013, 51(9): 1029-1043.
[9]	RIVEIRO A, QUINTERO F, LUSQUIN~OS F, et al. Experimental study on the CO2 laser cutting of carbon fiber reinforced plastic composite[J]. Composites, 2012, A43(7):1400-1409.
[10]	LAMIKIZ A, LPEZ de LCALLE L N, SANCHEZ J A, et al. CO2 laser cutting of advanced high strength steels (AHSS)[J]. Applied Surface Science, 2005, 242(3/4): 362-368.
[11]	KIM M J. 3-D finite element analysis of evaporative laser cutting[J]. Applied Mathematical Modelling, 2005,29(10):938-954.
[12]	YILBAS B S. Laser cutting of thick sheet metals: Effects of cuttingparameters on kerf size variations[J]. Journal of Materials Processing Technology, 2008, 201(1/3):285-290.
[13]	YAN C, LI L J, LI J, et al. Review of surface quality study on laser sheets cutting[J]. Laser Technology, 2005, 29(3):270-274 (in Chinese).
[14]	TONG G, XU H, YU H Q. Control model of laser cutting quality based on simulated annealing and BP neural network [J]. Machinery Design Manufacture, 2012(6):85-87 (in Chinese).
[15]	LIU J, GUO Q D,WANG Y H. Optimizing the laser-cutting parameters by using improved artificial neural network [J]. Laser Journal,2007, 28(6): 80-81 (in Chinese).
[16]	WU Y H, ZHANG Y Q, CHEN W Zh, et al. Application of RBF Neural Network in three dimensional laser cutting[J].China Mechanical Engineering, 2006, 17(12): 1234-1237(in Chinese).
[17]	LIU Y, XU D, TAN M. A genetic algorithm based artificial neural network approach for parameter selection of laser cutting [J]. Manufacturing Automation, 2006, 28(12): 20-22(in Chinese).
[18]	CHEN J M, ZUO T Ch. Analysis of artificial neural network on 3-D orientation CO2 laser cutting [J]. Chinese Journal of Lasers, 2004, 31(3): 245-248 (in Chinese).
[19]	FENG W J, QIN F D, CHEN Y Y, et al. Analysis of technological parameter for laser cutting stainless steel sheet[J]. Machinery Design Manufacture, 2011(11):191-192(in Chinese).
[20]	RIVEIRO A, QUINTERO F, LUSQUIN~OS F, et al. Influence of assist gas nature on the surfaces obtained by laser cutting of Al-Cu alloys [J]. Surface Coatings Technology,2010, 205(7): 1878-1885.
[21]	YANG D H, MA L, HUANG W D. Component's surface quality predicitons by laser rapid forming based on artifical neural networks[J].Chinese Journal of Lasers, 2011, 38(8): 1-5 (in Chinese).
[22]	YU J H, LI X N, ZHAI Y, et al. BP ANN model for annealing parameter and hardness of zirconium base alloy[J]. Rare Metal Materials and Engineering, 2012, 41(8): 1346-1350 (in Chinese).

[1]	赵士伟 , 张海云 , 李志永 , 赵玉刚 , 张晋烨 . 激光参量对血管支架切缝形貌及粗糙度的影响. 激光技术, 2020, 44(3): 299-303. doi: 10.7510/jgjs.issn.1001-3806.2020.03.005
[2]	陈君 , 张群莉 , 姚建华 , 傅纪斌 . 材料表面粗糙度对激光吸收率影响的研究. 激光技术, 2008, 32(6): 624-627.
[3]	黄文荣 , 徐宾 , 汤光平 , 杨家林 . 大角度斜面激光切割加工的工艺研究. 激光技术, 2001, 25(4): 290-292.
[4]	王飞 , 姚振强 . 激光冲击强化黄铜的实验研究. 激光技术, 2006, 30(5): 511-513.
[5]	徐大鹏 , 周建忠 , 郭华锋 , 季霞 . 基于进化神经网络的激光熔覆层质量预测. 激光技术, 2007, 31(5): 511-514.
[6]	张文博 , 张群莉 , 姚建华 . 基于人工神经网络脉冲激光强化镀层形貌预测. 激光技术, 2010, 34(2): 173-177. doi: 10.3969/j.issn.1001-3806.2010.02.009
[7]	null , . 电子调制的激光相干粗糙度测量技术研究. 激光技术, 2016, 40(3): 447-450. doi: 10.7510/jgjs.issn.1001-3806.2016.03.031
[8]	黄伟 , 周肇飞 , 张涛 . 集成光电传感器的研究. 激光技术, 2004, 28(6): 595-597.
[9]	秦华 , 郑荣儿 , 杨爱玲 . 潮湿环境对黄铜烧蚀阈值的影响. 激光技术, 2003, 27(6): 497-499.
[10]	徐海岩 , 李涛 , 李海波 , 王鑫林 , 张洪潮 . 316L激光熔覆质量预测及路径选择研究. 激光技术, 2018, 42(1): 53-59. doi: 10.7510/jgjs.issn.1001-3806.2018.01.011
[11]	蔡雯 , 陈培锋 , 王英 , 张恒 , 王莫 , 王钇苏 . 基于激光散射的表面粗糙度测量系统研究. 激光技术, 2020, 44(5): 611-615. doi: 10.7510/jgjs.issn.1001-3806.2020.05.014
[12]	刘睿诚 , 杨永强 , 王迪 . 选区激光熔化成型金属零件上表面粗糙度的研究. 激光技术, 2013, 37(4): 425-430. doi: 10.7510/jgjs.issn.1001-3806.2013.04.003
[13]	王金来 , 於自岚 , 高传玉 , 吉选芒 , 安毓英 , 曾丹勇 , 刘劲松 , 杨继昌 , 张永康 . 激光冲击区表面质量的人工神经网络研究. 激光技术, 2001, 25(1): 1-6.
[14]	何国豪 , 劳子彬 , 甘宏海 , 曹明轩 , 付斌 , 刘志平 , 王颖 , 袁铭辉 . 工艺参数对SLM成形CuCrZr合金微流道粗糙度的影响. 激光技术, 2023, 47(5): 639-645. doi: 10.7510/jgjs.issn.1001-3806.2023.05.010
[15]	王平江 , 吴浩 , 陈吉红 , 唐小琦 . 动光式激光切割无缝拼接技术的研究与应用. 激光技术, 2009, 33(4): 369-373. doi: 10.3969/j.issn.1001-3806.2009.04.010
[16]	黄福民 , 谢小柱 , 魏昕 , 胡伟 , 苑学瑞 . 半导体晶圆激光切割新技术. 激光技术, 2012, 36(3): 293-297.
[17]	韩香娥 , 吴振森 , 张向东 . 大粗糙度表面激光散射特性实验研究. 激光技术, 1997, 21(3): 151-155.
[18]	夏桂芬 , 赵保军 , 韩月秋 . 基于神经网络的远程激光测距机混沌弱信号检测. 激光技术, 2006, 30(5): 449-451.
[19]	黄威威 , 游德勇 , 高向东 , 张艳喜 , 黄宇辉 . 基于相关分析和神经网络的激光焊接稳态识别. 激光技术, 2022, 46(3): 312-319. doi: 10.7510/jgjs.issn.1001-3806.2022.03.004
[20]	颜鑫 , 应恺宁 , 戴鹭楠 , 谭钧夫 , 沈中华 , 倪辰荫 . 基于物理信息神经网络的激光超声波场研究. 激光技术, 2024, 48(1): 105-113. doi: 10.7510/jgjs.issn.1001-3806.2024.01.017

点击查看大图

计量

文章访问数: 3007
HTML全文浏览量: 718
PDF下载量: 608
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于BP神经网络的光纤激光切割切口粗糙度预测

作者简介: 郭华锋(1981-),男,硕士,讲师,现从事激光加工技术及表面工程技术的研究。E-mail:ghfmaster@163.com.

Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks

计量

基于BP神经网络的光纤激光切割切口粗糙度预测

作者简介: 郭华锋(1981-),男,硕士,讲师,现从事激光加工技术及表面工程技术的研究。E-mail:ghfmaster@163.com

English Abstract

Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks

全文HTML

目录

留言板

基于BP神经网络的光纤激光切割切口粗糙度预测

作者简介: 郭华锋(1981-),男,硕士,讲师,现从事激光加工技术及表面工程技术的研究。E-mail:ghfmaster@163.com.

Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks

计量

出版历程

基于BP神经网络的光纤激光切割切口粗糙度预测

作者简介: 郭华锋(1981-),男,硕士,讲师,现从事激光加工技术及表面工程技术的研究。E-mail:ghfmaster@163.com

English Abstract

Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks

全文HTML

目录