基于机器视觉的加工刀具磨损量在线测量

doi:10.16183/j.cnki.jsjtu.2020.083

摘要/Abstract

摘要：

针对实际生产中测量刀具磨损需要人工操作、停机检测等问题,开发了一个基于机器视觉的加工刀具磨损测量系统.首先提出基于Laplacian算子边缘信息的Otsu分割算法将图像二值化,再通过基于形态学的Canny算子边缘检测粗定位及图像配准提取清晰的刀具磨损区域.最后,使用基于Zernike矩的亚像素边缘检测方法提高测量精度,并通过主曲线方法拟合亚像素边缘点得到光滑的边缘曲线,实现了刀具磨损量的在线测量.实际加工过程中的刀具磨损测试结果表明,该系统检测自动化程度高、运行速度快、测量精度可以达到微米级,可以有效地应用于工业上对加工刀具磨损的实时监控.

关键词: 加工刀具, 磨损测量, 机器视觉, 图像分割, 边缘检测

Abstract:

In order to solve the problems of tool wear measurement in actual production, such as manual operation and shutdown detection, a machining tool wear measurement system based on machine vision is developed in this paper. First, the Otsu segmentation algorithm based on Laplacian edge information is proposed to binarize the images. Then, through rough positioning by morphology-based Canny operator edge detection and image registration, the tool wear area is extracted effectively. Finally, sub-pixel edge detection based on Zernike moment is used to improve the measurement accuracy while the principal curve method is used to fit sub-pixel edge points so as to obtain the smooth edge curve and realize the online measurement of tool wear. In real machining process, the tool wear test results show that the system has a high degree of automation and a rapid running speed. Moreover, its measurement accuracy can reach micron level. This system can be effectively applied to real-time monitoring of tool wear in industry.

Key words: machining tool, wear measurement, machine vision, image segmentation, edge detection

中图分类号:

TG71
TP391.4

周俊杰, 余建波. 基于机器视觉的加工刀具磨损量在线测量[J]. 上海交通大学学报, 2021, 55(6): 741-749.

ZHOU Junjie, YU Jianbo. Online Measurement of Machining Tool Wear Based on Machine Vision[J]. Journal of Shanghai Jiao Tong University, 2021, 55(6): 741-749.

图/表 17

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

表2

表3

图11

表4

图12

表5

参考文献 17

[1]	HOU Q L, SUN J, HUANG P L. A novel algorithm for tool wear online inspection based on machine vision[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101(9/10/11/12):2415-2423. doi: 10.1007/s00170-018-3080-9 URL
[2]	GARCÍA-ORDÁS M T, ALEGRE E, GONZÁLEZ-CASTRO V, et al. A computer vision approach to analyze and classify tool wear level in milling processes using shape descriptors and machine learning techniques[J]. The International Journal of Advanced Manufacturing Technology, 2017, 90(5/6/7/8):1947-1961. doi: 10.1007/s00170-016-9541-0 URL
[3]	孙涛, 傅玉灿, 何磊, 等. 损伤容限型钛合金的切削加工性[J]. 上海交通大学学报, 2016, 50(7):1017-1022.
	SUN Tao, FU Yucan, HE Lei, et al. Cutting machinability for damage-tolerant titanium alloy[J]. Journal of Shanghai Jiao Tong University, 2016, 50(7):1017-1022.
[4]	荣雪宁, 卢浩, 王明洋, 等. 基于刀盘扭转能量的土压平衡盾构刀具磨损分析[J]. 上海交通大学学报, 2019, 53(8):965-970.
	RONG Xuening, LU Hao, WANG Mingyang, et al. Analysis of tools wear for earth pressure balance shield based on torque energy of cutterhead[J]. Journal of Shanghai Jiao Tong University, 2019, 53(8):965-970.
[5]	KONG D D, CHEN Y J, LI N, et al. Tool wear monitoring based on kernel principal component analysis and v-support vector regression[J]. The International Journal of Advanced Manufacturing Technology, 2017, 89(1/2/3/4):175-190. doi: 10.1007/s00170-016-9070-x URL
[6]	SIMON G D, DEIVANATHAN R. Early detection of drilling tool wear by vibration data acquisition and classification[J]. Manufacturing Letters, 2019, 21:60-65. doi: 10.1016/j.mfglet.2019.08.006 URL
[7]	RMILI W, OUAHABI A, SERRA R, et al. An automatic system based on vibratory analysis for cutting tool wear monitoring[J]. Measurement, 2016, 77:117-123. doi: 10.1016/j.measurement.2015.09.010 URL
[8]	LI Z X, LIU R, WU D Z. Data-driven smart manufacturing: Tool wear monitoring with audio signals and machine learning[J]. Journal of Manufacturing Processes, 2019, 48:66-76. doi: 10.1016/j.jmapro.2019.10.020 URL
[9]	LIU M K, TSENG Y H, TRAN M Q. Tool wear monitoring and prediction based on sound signal[J]. The International Journal of Advanced Manufacturing Technology, 2019, 103(9/10/11/12):3361-3373. doi: 10.1007/s00170-019-03686-2 URL
[10]	DUTTA S, PAL S K, SEN R. Progressive tool flank wear monitoring by applying discrete wavelet transform on turned surface images[J]. Measurement, 2016, 77:388-401. doi: 10.1016/j.measurement.2015.09.028 URL
[11]	ZHU K P, YU X L. The monitoring of micro milling tool wear conditions by wear area estimation[J]. Mechanical Systems and Signal Processing, 2017, 93(93):80-91. doi: 10.1016/j.ymssp.2017.02.004 URL
[12]	LI L H, AN Q B. 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 URL
[13]	DAI Y Q, ZHU K P. A machine vision system for micro-milling tool condition monitoring[J]. Precision Engineering, 2018, 52:183-191. doi: 10.1016/j.precisioneng.2017.12.006 URL
[14]	XIE X, GE S L, XIE M Y, et al. An improved industrial sub-pixel edge detection algorithm based on coarse and precise location[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 11(5):2061-2070. doi: 10.1007/s12652-019-01232-2 URL
[15]	KUMAR B M, RATNAM M M. Machine vision method for non-contact measurement of surface roughness of a rotating workpiece[J]. Sensor Review, 2015, 35(1):10-19. doi: 10.1108/SR-01-2014-609 URL
[16]	HASTIE T, STUETZLE W. Principal curves[J]. Journal of the American Statistical Association, 1989, 84(406):502-516. doi: 10.1080/01621459.1989.10478797 URL
[17]	MEHTA S, SINGH R A, MOHATA Y, et al. Measurement and analysis of tool wear using vision system[C]// 2019 IEEE 6th International Conference on Industrial Engineering and Applications (ICIEA) . Piscataway, NJ, USA: IEEE, 2019: 45-49.

方法	b₀/μm	ε₀/%
Otsu分割算法	471.32	8.65
基于Laplacian算子边缘信息的Otsu分割算法	545.74	5.77
人工测量	515.97	0

边缘检测方法	t_s/s
拟合法亚像素边缘检测	1.722
插值法亚像素边缘检测	1.241
Zernike矩法亚像素边缘检测	0.818

边缘检测方法	b_E/μm	ε_E/%
拟合法亚像素边缘检测	396.90	23.08
插值法亚像素边缘检测	542.56	5.15
Zernike矩法亚像素边缘检测	545.74	5.77
Canny算子边缘检测	555.66	7.69
人工测量	515.97	0

刀具图示	b₁/μm	b₂/μm	ε/%
①	0	0	0
②	396.90	385.99	2.75
③	396.90	406.82	2.50
④	436.59	447.11	2.41
⑤	476.28	505.06	6.04
⑥	515.97	545.74	5.77

刀具磨损测量各步骤	t_p/s
图像预处理	0.271
图像二值化及边缘初定位	0.470
亚像素边缘精定位及边缘拟合	0.818
磨损量计算	0.079
合计	1.638