Please wait a minute...
浙江大学学报(工学版)  2021, Vol. 55 Issue (5): 896-904    DOI: 10.3785/j.issn.1008-973X.2021.05.010
机械工程     
基于机器视觉的加工刀具磨损监测方法
程训(),余建波*()
同济大学 机械与能源工程学院,上海 201804
Monitoring method for machining tool wear based on machine vision
Xun CHENG(),Jian-bo YU*()
School of Mechanical Engineering, Tongji University, Shanghai 201804, China
 全文: PDF(1819 KB)   HTML
摘要:

为了对加工过程中刀具的磨损状态进行监测,针对麻花钻的磨损形式,提出基于机器视觉的加工刀具磨损监测方法. 根据磨损刀具图像的灰度分布特点,提出基于积分图加速和Turky bi-weight核函数的非局部均值去噪方法;采用单、双阈值大津法获取磨损区域的灰度区间,实现对图像的自适应对比度增强;提出基于形态学重构方法的磨损区域局部极值点提取方法,有效完成对磨损区域的检测和边界提取. 该刀具磨损检测方法成功应用于麻花钻头磨损状态的监测过程,实验结果表明,相较于目前已有的机器视觉监测方法,所提出的方法具有更高的检测精度和效率,准确地提取磨损轮廓,从而有效实现对刀具磨损状态的监测和自动化监控加工过程,达到降低人工成本和产品不合格率的目的.

关键词: 刀具磨损机器视觉图像去噪图像增强边缘提取    
Abstract:

A set of tool wear monitoring methods based on machine vision was proposed aiming at the wear form of twist drill, in order to monitor the wear conditon of the tool during the machining process. A non-local mean denoising method was proposed based on integral image and Turky bi-weight kernel function according to the gray distribution of worn tool images. The single and double threshold Otsu methods were proposed to obtain the gray interval of the worn area to adaptively enhance the image. A method of extracting local extreme points of wear regions based on morphological reconstruction was proposed to effectively complete the detection of wear regions and boundary extraction. Experimental results show that the monitoring method of tool wear can be effectively implemented in the monitoring of twist drill wear. And it is proved that the proposed method has higher detection accuracy and efficiency and it can extract tool wear more accurately than other methods. It helps to realize the monitoring of tool wear and automatic monitoring of the processing process, and achieve the purpose of reducing labor costs and product failure rate.

Key words: tool wear    machine vision    image denoising    image enhancement    edge detection
收稿日期: 2020-03-27 出版日期: 2021-06-10
CLC:  TH 164  
基金资助: 国家自然科学基金资助项目(71777173);上海科委“科技创新行动计划”高新技术领域资助项目(19511106303);装备预先研究领域基金项目(61400020119)
通讯作者: 余建波     E-mail: 15801789097@163.com;jbyu@tongji.edu.cn
作者简介: 程训(1997—),男,硕士生,从事图像处理研究. orcid.org/0000-0002-6360-8908. E-mail: 15801789097@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
程训
余建波

引用本文:

程训,余建波. 基于机器视觉的加工刀具磨损监测方法[J]. 浙江大学学报(工学版), 2021, 55(5): 896-904.

Xun CHENG,Jian-bo YU. Monitoring method for machining tool wear based on machine vision. Journal of ZheJiang University (Engineering Science), 2021, 55(5): 896-904.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2021.05.010        http://www.zjujournals.com/eng/CN/Y2021/V55/I5/896

图 1  基于机器视觉的加工刀具磨损监测方法
图 2  NLM的执行过程
图 3  积分图计算过程
图 4  形态学重构求局部极值示意图
图 5  麻花钻头整体结构图
图 6  实验加工和图像处理装置示意图
图 7  实验加工和图像处理装置实物图
参数 取值 参数 取值
相机型号 acA2500-60um 感光芯片 PYTHON 5000
感光芯片
供应商
ON Semiconductor 靶面尺寸 1
快门 Global Shutter 感光芯片尺寸 12.4 mm×9.8 mm
感光芯片
类型
CMOS 分辨率 5 MP
水平/垂直
分辨率
2590 px×2048 px 帧速率 60 fps
水平/垂直
像素尺寸
4.8 μm×4.8 μm 接口 USB 3.0
黑白/彩色 Mono ? ?
表 1  相机参数
参数 取值
镜头型号 M0824-MPW2
靶面尺寸 2/3″
焦距/mm 8
最大成像尺寸/mm 8.8 × 6.6(Φ 11)
光圈范围(F-Stop) F2.4~F16.0
最小物距(M.O.D)/m 0.05
表 2  镜头参数
图 8  刀具磨损图像处理
图 9  磨损边界的二值提取和边界定位
去噪算法 去噪时间/s PSNR SNR SSIM 原图 处理后图像
尺寸: 160×160 尺寸: 320×320
NLM 13.08 53.78 75.5714 16.2157 0.4969
NFNLM 0.23 4.51 75.6511 16.2954 0.4981
表 3  NLM与NFNLM计算速度与滤噪结果对比
图 10  形态学重构方法与其他分割方法的边界提取效果对比
原始图像 边界图像 重合图像 磨损最大宽度像素数
8.1
13.8
16.2
18.0
19.3
表 4  磨损区域检测
测量次数 钻头直径像素/像素 像素当量/μm
1 140.8 42.3
2 139.7 42.6
3 139.4 42.7
4 141.8 42.0
5 138.2 43.1
平均值 140.0 42.5
表 5  像素当量测量结果
实际像素
数目
实际宽度/
mm
估计像素
数目
估计宽度/
mm
误差百分比/
%
8.1 0.344 8.1 0.344 0
14.8 0.629 13.8 0.587 6.7
16.8 0.714 16.2 0.689 3.5
18.8 0.799 18.0 0.765 4.3
19.6 0.833 19.3 0.820 1.6
表 6  麻花钻磨损宽度测量
1 陈雷明, 杨润泽, 张治 刀具检测方法综述[J]. 机械制造与自动化, 2011, 40 (1): 49- 50
CHEN Lei-ming, YANG Run-ze, ZHANG Zhi Summary of the tool monitoring methods[J]. Machine Building and Automation, 2011, 40 (1): 49- 50
doi: 10.3969/j.issn.1671-5276.2011.01.016
2 赵帅, 黄亦翔, 王浩任, 等 基于随机森林与主成分分析的刀具磨损评估[J]. 机械工程学报, 2017, 53 (21): 181- 189
ZHAO Shuai, HUANG Yi-xiang, WANG Hao-ren, et al Random forest and principle components analysis based on health assessment methodology for tool wear[J]. Journal of Mechanical Engineering, 2017, 53 (21): 181- 189
doi: 10.3901/JME.2017.21.181
3 刘佳佳, 姜兴刚, 张德远 钛合金高速旋转超声椭圆振动侧铣削切屑特征和刀具磨损研究[J]. 机械工程学报, 2019, 55 (19): 186- 194
LIU Jia-jia, JIANG Xing-gang, ZHANG De-yuan Research on the characteristics of chips and tool flank wear in high-speed rotary ultrasonic elliptical machining for side milling of Ti-6Al-4V[J]. Journal of Mechanical Engineering, 2019, 55 (19): 186- 194
doi: 10.3901/JME.2019.19.186
4 杨建国, 肖蓉, 李蓓智, 等 基于机器视觉的刀具磨损检测技术[J]. 东华大学学报: 自然科学版, 2012, 38 (5): 505- 508
YANG Jian-guo, XIAO Rong, LI Bei-zhi, et al Tool wear detection based on machine vision[J]. Journal of Donghua University: Natural Science, 2012, 38 (5): 505- 508
5 贾冰慧. 基于机器视觉的刀具状态在机检测关键技术研究[D]. 广州: 华南理工大学, 2014.
JIA Bing-hui. Key technology research of tool condition detection on-machine based on machine vision[D]. Guangzhou: South China University of Technology, 2014.
6 廖玉松, 韩江 基于像素分布特征的图像去噪法在刀具磨损检测中的应用[J]. 机械设计, 2015, 32 (6): 93- 98
LIAO Yu-song, HAN Jiang Application of image denoising method based on pixel-distribution on tool wear detection[J]. Journal of Machine Design, 2015, 32 (6): 93- 98
7 吴一全, 殷骏 粒子群优化的Contourlet域数字全息再现像增强[J]. 中国激光, 2013, 40 (8): 190- 196
WU Yi-quan, YIN Jun Contourlet domain digital holographic image enhancement based on particle swarm optimization[J]. Chinese Journal of Lasers, 2013, 40 (8): 190- 196
8 尹士畅, 喻松林 基于小波变换和直方图均衡的红外图像增强[J]. 激光与红外, 2013, 43 (2): 225- 228
YIN Shi-chang, YU Song-lin Infrared image enhancement algorithm based on wavelet transform and histogram equalization[J]. Laser and Infrared, 2013, 43 (2): 225- 228
doi: 10.3969/j.issn.1001-5078.2013.02.024
9 何翔, 任小洪 基于数字图像的刀具磨损状态检测技术[J]. 机床与液压, 2016, 44 (3): 125- 128
HE Xiang, REN Xiao-hong Tool wear state detection technology based on digital image[J]. Machine Tool and Hydraulics, 2016, 44 (3): 125- 128
doi: 10.3969/j.issn.1001-3881.2016.03.031
10 HOU Q, SUN J, HUANG P A novel algorithm for tool wear online inspection based on machine vision[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101 (9?12): 2415- 2423
doi: 10.1007/s00170-018-3080-9
11 MOOK W K, SHAHABI H H, RATNAM M M Measurement of nose radius wear in turning tools from a single 2D image using machine vision[J]. The International Journal of Advanced Manufacturing Technology, 2009, 43 (3/4): 217- 225
doi: 10.1007/s00170-008-1712-1
12 HUSSAIN S, CHEN X Remote milling tool-wear monitoring and direct wear features extraction by image processing[J]. International Journal of Internet Manufacturing and Services, 2008, 1 (3): 246- 261
doi: 10.1504/IJIMS.2008.021197
13 ZHANG C, ZHANG J On-line tool wear measurement for ball-end milling cutter based on machine vision[J]. Computers in Industry, 2013, 64 (6): 708- 719
doi: 10.1016/j.compind.2013.03.010
14 ZHU K, YU X The monitoring of micro milling tool wear conditions by wear area estimation[J]. Mechanical Systems and Signal Processing, 2017, 93: 80- 91
doi: 10.1016/j.ymssp.2017.02.004
15 LI L, AN Q An in-depth study of tool wear monitoring technique based on image segmentation and texture analysis[J]. Measurement, 2016, 79: 44- 52
doi: 10.1016/j.measurement.2015.10.029
16 SCHMITT R, CAI Y, PAVIM A Machine vision system for inspecting flank wear on cutting tools[J]. International Journal on Control System and Instrumentation, 2012, 3 (1): 37- 31
17 BUADES A, COLL B, MOREL J M Non-local means denoising[J]. Image Processing On Line, 2011, 1: 208- 212
doi: 10.5201/ipol.2011.bcm_nlm
18 VIOLA P A, JONES M J. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai: IEEE, 2001.
19 TIAN J, YU W Y, XIE S L. On the kernel function selection of nonlocal filtering for image denoising[C]// 2008 International Conference on Machine Learning and Cybernetics. Kunming: IEEE, 2008, 5: 2964-2969.
20 OTSU N A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9 (1): 62- 66
doi: 10.1109/TSMC.1979.4310076
21 GONG L X Crop image recognition based on ComVI and double threshold OTSU algorithm[J]. Journal of Drainage and Irrigation Machinery Engineering, 2014, 32 (4): 363- 368
22 VINCENT L. Morphological grayscale reconstruction: definition, efficient algorithm and applications in image analysis [C]// Champaign: CVPR, 1992: 633-635.
23 马利杰, 田泽正, 王贵成 轴向振动钻削中麻花钻的失效形式分析[J]. 制造技术与机床, 2008, (11): 105- 108
MA Li-jie, TIAN Ze-zheng, WANG Gui-cheng Analysis on failure from of twist drill in axial vibration drilling[J]. Manufacturing Technology and Machine Tool, 2008, (11): 105- 108
doi: 10.3969/j.issn.1005-2402.2008.11.035
[1] 雍子叶,郭继昌,李重仪. 融入注意力机制的弱监督水下图像增强算法[J]. 浙江大学学报(工学版), 2021, 55(3): 555-562.
[2] 杜军,马琛,魏正英. 基于视觉传感的铝合金电弧增材沉积层形貌动态响应[J]. 浙江大学学报(工学版), 2020, 54(8): 1481-1489.
[3] 康庄,杨杰,郭濠奇. 基于机器视觉的垃圾自动分类系统设计[J]. 浙江大学学报(工学版), 2020, 54(7): 1272-1280.
[4] 贾真,董文德,徐贵力,朱士鹏. 基于马尔科夫专家场的泊松噪声图像去噪方法[J]. 浙江大学学报(工学版), 2020, 54(6): 1164-1169.
[5] 汪海晋,尹宗宇,柯臻铮,郭英杰,董辉跃. 基于一维卷积神经网络的螺旋铣刀具磨损监测[J]. 浙江大学学报(工学版), 2020, 54(5): 931-939.
[6] 李瑛,成芳,赵志林. 采用结构光的大跨度销孔加工精度在线测量[J]. 浙江大学学报(工学版), 2020, 54(3): 557-565.
[7] 王万良,杨小涵,赵燕伟,高楠,吕闯,张兆娟. 采用卷积自编码器网络的图像增强算法[J]. 浙江大学学报(工学版), 2019, 53(9): 1728-1740.
[8] 张承志, 冯华君, 徐之海, 李奇, 陈跃庭. 图像噪声方差分段估计法[J]. 浙江大学学报(工学版), 2018, 52(9): 1804-1810.
[9] 刘亚男,倪鹤鹏,张承瑞,王云飞,孙好春. 基于PC的运动视觉一体化开放控制平台设计[J]. 浙江大学学报(工学版), 2016, 50(7): 1381-1386.
[10] 王志, 朱世强, 卜琰, 郭振民. 改进导向滤波器立体匹配算法[J]. 浙江大学学报(工学版), 2016, 50(12): 2262-2269.
[11] 叶肖伟,张小明,倪一清,黄启远,樊可清. 基于机器视觉技术的桥梁挠度测试方法[J]. 浙江大学学报(工学版), 2014, 48(5): 813-819.
[12] 徐嵩,孙秀霞,何衍. 利用直线段成像特性的摄像机畸变迭代标定方法[J]. J4, 2014, 48(3): 404-413.
[13] 刘涛, 赵巨峰, 徐之海, 冯华君, 陈慧芳. 基于卡尔曼滤波的红外图像增强算法[J]. J4, 2012, 46(8): 1534-1539.
[14] 吕谷来, 李建平, 李锵, 俞利兴, 朱松明, 楼建忠, 袁祎琳. 基于机器视觉的砧木定位识别方法[J]. J4, 2011, 45(10): 1766-1770.
[15] 王宣银, 梁冬泰. 基于多元图像分析的表面缺陷检测算法[J]. J4, 2010, 44(3): 448-452.