[1]韦永奇,胥光申,刘 晖,等.基于图像识别的激光切割质量分析[J].机械与电子,2021,(01):56-61.
 WEI Yongqi,XU Guangshen,LIU Hui,et al.Laser Cutting Quality Analysis Based on Image Recognition[J].Machinery & Electronics,2021,(01):56-61.
点击复制

基于图像识别的激光切割质量分析()
分享到:

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年01期
页码:
56-61
栏目:
自动控制与检测
出版日期:
2021-01-20

文章信息/Info

Title:
Laser Cutting Quality Analysis Based on Image Recognition
文章编号:
1001-2257(2021)01-0056-06
作者:
韦永奇12胥光申12刘 晖12谢如炎3俞宝福3
1.西安工程大学机电工程学院,陕西 西安 710048 ;
2.西安市现代智能纺织装备重点实验室,陕西 西安 710048 ;
3.绍兴纺织机械集团有限公司,浙江 绍兴 312000
Author(s):
WEI Yongqi12XU Guangshen12LIU Hui12XIE Ruyan3YU Baofu3

1. School of Mechanical and Electrical Engineering, Xi ’an Polytechnic University, Xi’an 710048,China ;
2.Xi ’an Modern Intelligent Textile Equipment Key Laboratory, Xi’an 710048, China;
3.Shaoxing Textile Machinery Group Co., Ltd., Shaoxing 312000, China

关键词:
图像识别激光切割特征提取质量分析
Keywords:
image recognitionlaser cuttingfeature extractionquality analysis
分类号:
TP391.41;TN249
文献标志码:
A
摘要:
为了准确量化激光切割过程中出现的烧蚀缺陷,提出了基于改进的形态学缺陷提取算法与基于霍夫变换的缺陷测量相结合的方法。改进的形态学提取算法用于缺陷位置的检测和提取,霍夫变换用于缺陷尺寸计算,该方法可以准确提取并测量出切割缺陷尺寸和面积特征。以不同工艺参数下切割产品烧蚀区域宽度和面积为激光切割质量评价指标,研究了切割速度和氧气压力对切割质量的影响。当氧气压力在1.0 MPa范围内,顺时针切割时烧蚀区域宽度和面积呈现出相同的变化规律,逆时针切割时烧蚀区域宽度和面积呈现相反的变化规律。顺时针切割时,切割质量最佳,最小烧蚀宽度为9 px,最小烧蚀区域面积为34 px2。实验结果表明,所提出的方法能够快速识别出激光切割产品缺陷特征,准确评价激光切割质量。
Abstract:
In order to accurately quantify the ablative defects during laser cutting, a method based on improved morphological defect extraction and defect measurement based on Hough transform was proposed.Morphological extraction algorithm is used for defect location detection and extractionand Hough transform is used for defect size calculation.This method can accurately extract and measure the size and area characteristics of cut defects.The effect of cutting speed and oxygen pressure on cutting quality was studied by taking the width and area of ablative area of cutting product under different process parameters as the evaluation index of laser cutting quality.When the oxygen pressure is within the range of 1.0 MPa., the width and area of the ablative area show the same change rule when cutting clockwise.When cutting counterclockwise, the width and area of ablative area change in opposite direction.When cutting clockwise, the cutting quality is the best, the minimum ablation width is 9 pixels, and the minimum ablation area is 34 px2.The experimental results show that the proposed method can quickly identify the defect characteristics of laser cutting products and accurately evaluate the quality of laser cutting.

参考文献/References:

[1].邢雪亮,甘文波,蒋朝根.基于机器视觉的航空铆钉尺寸检测技术[J].计量学报,2020,41(5):518-523.
[2]赵三军,赵水,张志强, 等.激光切割8mm厚锰钢板的工艺试验研究[J].制造技术与机床,2019(9):70-73.
[3]张永强,吴艳华,陈武柱,等.激光切割质量的在线评价方法[J].中国激光,2006(11):1580-1584.
[4]FUSHIMIT,NAKANISHI A,YAMAGUCHI Y, et al. Flow observation in a laser cut kerf[J].Journal of advanced science 1999, 11(2):164-165.
[5] 王彦飞,王续跃,徐文骥, 等.基于图像处理的铝合金薄板激光切割质量研究[J].中国激光,2014,41(1):52-58.
[6] 郑磊,施立发,张乔英.高牌号无取向硅钢材料热变形特性研究[J].金属功能材料,2017,24(3):61-66.
[7]孙登科,邓倩,杨新华,等.不锈钢板材激光切割工艺分析[J].焊接技术,2017,46(11):50-51.
[8] 戴斌宇,吴静静.基于机器视觉的定子表面缺陷检测系统研究[J].传感技术报,2019,32(10):1589-1594.
[9]贺振东,王耀南,刘洁, 等.基于背景差分的高铁钢轨表面缺陷图像分割[J].仪器仪表学报,2016,37(3):640-649.
[10] 赵慧娟,姜盼松,黄文聪.基于图像识别算法的图像传感器质量检测方法改善研究[J].工业工程,2020,23(3):115-122.
[11]张建国,齐家坤,李颖, 等.倾斜图像的车牌识别方法研究[J].机械设计与制造,2020(6):58-61,65.
[12]赵立新,侯发东,吕正超, 等.基于迁移学习的棉花叶部病虫害图像识别[J].农业工程学报,2020,36(7):184-191.
[13] FROST M,CURRY CB,GLENZERS H.Laser cutting apparatus for high energy density and diamondanvil cell science[J]. Journal of instrumentation , 2020, 15(5):P05004.
[14]高士友,马雷,张润生.基于视觉激光切割厚板切割状态监控方法[J].中国激光,2012,39(2):91-97.
[15]崔鹏宇.多维特征融合与Adaboost-SVM的车辆识别算法[J].控制工程,2019,26(3):608-612.
[16]CHUM O,MATAS J.Matching with PROSAC-progressivesampleconsensus[C]//ComputerVisionandPatternRecognition,2005:220-226.
[[17]BARATHD, NOSKOVAJ, MATASJ.MAGSAC:marginalizingsampleconsensus[C]//ConferenceonComputerVisionandPatternRecognition,2019:10189-10197.

相似文献/References:

[1]王 嵘,万永菁.一种基于SLAM 的多功能探索机器人设计[J].机械与电子,2019,(09):51.
 .Design of Multifunctional Exploration Robot Based on SLAM[J].Machinery & Electronics,2019,(01):51.
[2]张立鑫,李 堑.激光切割参数对辅助气体流场影响研究[J].机械与电子,2019,(02):18.
 .Influence of Laser Cutting Parameters on Auxiliary Gas Flow Field[J].Machinery & Electronics,2019,(01):18.
[3]邵悦辰,贡 亮,沈晓晔,等.基于机器视觉的FDM-3D快速成型异常工况监控系统[J].机械与电子,2021,(04):28.
 SHAO Yuechen,GONG Liang,SHEN Xiaoye,et al.Abnormal Working Condition Monitoring System in FDM-3D Rapid Prototyping Based on Machine Vision[J].Machinery & Electronics,2021,(01):28.
[4]刘 哲,闫佳文,陈长金,等.电力线图像检测方法研究[J].机械与电子,2022,(03):54.
 LIU Zhe,YAN Jiawen,CHEN Changjin,et al.Research on Power Line Image Detection Method[J].Machinery & Electronics,2022,(01):54.

备注/Memo

备注/Memo:
收稿日期:2020-09-27
基金项目:西安工程大学柯桥纺织产业创新研究院暨西安工程大学(柯桥)研究生创新学院产学研协同创新项目(19KQYB12);西安市现代智能纺织装备重点实验室科技创新平台建设工程/重点实验室建设项目(2019220614SYS021CG043)
作者简介:韦永奇(1996-),男,陕西宝鸡人,硕士研究生,研究方向为激光切割与智能检测;胥光申(1964-),男,陕西宝鸡人,硕士研究生导师,研究方向为先进制造技术。
更新日期/Last Update: 2020-12-28