Surface defect detection and analysis of Si3N4 ceramic bearing inner ring raceway based on shearlet transform
-
摘要:
为有效检测航空动力系统中Si3N4陶瓷轴承内圈沟道表面凹坑、划痕、擦伤的缺陷。采用中值滤波除去Si3N4陶瓷轴承内圈沟道原始图像零散噪点，对其处理图像进行剪切波变换，归一化阈值曲面法对变换后的剪切波系数进行重构、剪切波逆变换获取缺陷增强图像，对缺陷增强图像进行灰度阈值分割与识别分类，定位提取缺陷。基于剪切波变换的Si3N4陶瓷轴承内圈沟道的表面缺陷检测方法能有效的检测出Si3N4陶瓷轴承内圈沟道表面的缺陷。该方法对Si3N4陶瓷轴承内圈沟道表面缺陷提取的准确率可达97.50%，具有高精度与高准确性，满足预期要求。
-
关键词:
- Si3N4陶瓷轴承内圈 /
- 剪切波变换 /
- 表面缺陷检测 /
- 缺陷增强 /
- 缺陷提取
Abstract:To effectively detect the defects of pits, scratches and abrasions on the raceway surface of Si3N4 ceramic bearing inner ring in aviation power system, median filter was used to remove original image scattered noise of Si3N4 ceramic bearing inner ring channel, and conduct its processing image's shear wave transform, and the normalized threshold surface method was adopted to reconstruct the conversion coefficient of shear wave, enable shear wave inverse transformation for defect enhancing image, gray threshold segmentation for defect enhancing image classification and recognition, and position to extract the defect. The surface defect detection method of Si3N4 ceramic bearing inner racetrack based on shear wave transform can effectively detect the surface defect of Si3N4 ceramic bearing inner racetrack. This method can extract surface defects of inner raceways of Si3N4 ceramic bearing with 97.50% accuracy, which can meet the expected requirements.
-
图 1 图像采集与检测装置示意图
1 弹性挡圈；2 固定轨道；3 LED灯；4 CCD相机；5 Si3N4陶瓷轴承内圈；6 输出轴；7 联轴器；8 轴承支座；9 步进电动机。
Figure 1. Schematic diagram of image acquisition and detection device
图 2 缺陷图像及灰度值三维示意图
Figure 2. Three-dimensional schematic diagram of defect image and gray value
表 1 缺陷分类结果表
Table 1. Defect identification results
参数 凹坑 划痕 擦伤 总计 检测数量 40 40 40 120 识别数量 39 37 37 113 识别率/% 95.00 92.20 92.50 94.17 
下载: 导出CSV
表 2 Si3N4陶瓷轴承内圈4种算法缺陷提取结果准确率对比表
Table 2. Comparison table of defect extraction accuracy of Si3N4 ceramic bearing inner ring by four algorithms
应用方法 图像类型 检测数量 检测出缺陷数量 准确率/% 总准确率/% 精确性 剪切波变换算法 含缺陷 60 60 100.00 97.50 精确 无缺陷 60 3 95.00 大津算法 含缺陷 60 60 100.00 50.00 不精确 无缺陷 60 60 0 归一化算法 含缺陷 60 58 98.00 94.17 较精确 无缺陷 60 5 91.67 轮廓波变换算法 含缺陷 60 60 100.00 50.00 不精确 无缺陷 60 60 0
下载: 导出CSV
-
[1] CAO Shuwei,ZHANG Yue,ZHANG Dahai,et al. Effect of surface nano-modification on the antioxidation properties of Si3N4 ceramics[J]. Journal of Alloys and Compounds,2018,766: 678-685. doi: 10.1016/j.jallcom.2018.06.363 [2] YUE Xuejie,ZHANG Tao,YANG Dongya,et al. Fabrication of flexible ceramic membranes derived from hard Si3N4 and soft MnO2 nanowires[J]. Ceramics International,2020,46(6): 8478-8482. doi: 10.1016/j.ceramint.2019.11.226 [3] YU Dongling,ZHANG Huiling,ZHANG Xiaohui,et al. Si3N4 ceramic ball surface defects’ detection based on SWT and nonlinear enhancement[J]. Mathematical Problems in Engineering,2021,2021: 1-9. [4] 田欣利,毛亚涛,许森,等. 新型坦克发动机涡轮增压器高速混合陶瓷轴承的研制[J]. 机械科学与技术,2012,31(9): 1390-1394.TIAN Xinli,MAO Yatao,XU Sen,et al. Development of high speed hybrid ceramic bearing for tank engine turbocharger[J]. Mechanical Science and Technology for Aerospace Engineering,2012,31(9): 1390-1394. (in Chinese) [5] 吴承伟,张伟,李东炬. 超精密高性能氮化硅轴承研究现状与应用[J]. 精密制造与自动化,2020(1): 1-3,11.WU Chengwei,ZHANG Wei,LI Dongju. Current situation and application of research on super-precision high-performance silicon nitride bearings[J]. Precise Manufacturing & Automation,2020(1): 1-3,11. (in Chinese) [6] CHEN Meng,YIN Xiaowei,LI Mian,et al. Electromagnetic interference shielding properties of silicon nitride ceramics reinforced by in situ grown carbon nanotubes[J]. Ceramics International,2015,41(2): 2467-2475. doi: 10.1016/j.ceramint.2014.10.062 [7] DUAN Yusen,ZHANG Jingxian,LI Xiaoguang,et al. Optimization of the tape casting process for the development of high performance silicon nitride substrate[J]. International Journal of Applied Ceramic Technology,2017,14(4): 712-718. doi: 10.1111/ijac.12679 [8] 杨铁滨,王黎钦,古乐,等. 氮化硅陶瓷球加工缺陷分析与无损检测技术研究[J]. 兵工学报,2007,28(3): 353-357.YANG Tiebin,WANG Liqin,GU Le,et al. Processing defect analysis and nondestructive evaluation technology for Si3N4 bearing ball[J]. Acta Armamentarii,2007,28(3): 353-357. (in Chinese) [9] YU Dongling,ZHU Zuoxiang,MIN Jianliang,et al. Multi-scale decomposition enhancement algorithm for surface defect images of Si3N4 ceramic bearing balls based on stationary wavelet transform[J]. Advances in Applied Ceramics,2021,120(1): 47-57. doi: 10.1080/17436753.2020.1858010 [10] LU Manhuai,CHEN C L. Detection and classification of bearing surface defects based on machine vision[J]. Applied Sciences,2021,11(4): 1825.1-1825.22. [11] ZHU Li,BAO Xukang,LIU Shousheng. Machine vision based on pipe joint surface defect detection and identification[J]. Journal of Physics:Conference Series,2020,1621(1): 012012.1-012012.11. [12] YANG J,XU Y,RONG H J,et al. A method for wafer defect detection using spatial feature points guided affine iterative closest point algorithm[J]. IEEE Access,2020,8: 79056-79068. doi: 10.1109/ACCESS.2020.2990535 [13] KHARE A,KHARE M,SRIVASTAVA R. Shearlet transform based technique for image fusion using median fusion rule[J]. Multimedia Tools and Applications,2021,80(8): 11491-11522. doi: 10.1007/s11042-020-10184-1 [14] 何永红,朱建军,靳鹏伟. 一种使用剪切波变换的干涉图滤波算法[J]. 武汉大学学报(信息科学版),2018,43(7): 1008-1014.HE Yonghong,ZHU Jianjun,JIN Pengwei. An interferogram filtering algorithm using shearlet transform[J]. Geomatics and Information Science of Wuhan University,2018,43(7): 1008-1014. (in Chinese) [15] 杨成立,殷鸣,向召伟,等. 基于非下采样Shearlet变换的磁瓦表面缺陷检测[J]. 工程科学与技术,2017,49(2): 217-224.YANG Chengli,YIN Ming,XIANG Zhaowei,et al. Defect detection in magnetic tile images based on non-subsampled shearlet transform[J]. Advanced Engineering Sciences,2017,49(2): 217-224. (in Chinese) [16] 杨冠雨,栾锡武,孟凡顺,等. 基于Shearlet变换和广义全变分正则化的地震数据重建[J]. 地球物理学报,2020,63(9): 3465-3477.YANG Guanyu,LUAN Xiwu,MENG Fanshun,et al. Seismic data reconstruction based on Shearlet transform and total generalized variation regularization[J]. Chinese Journal of Geophysics,2020,63(9): 3465-3477. (in Chinese) [17] 薛林,程浩,巩恩普,等. Shearlet域自适应阈值地震数据随机噪声压制[J]. 石油地球物理勘探,2020,55(2): 282-291,228.XUE Lin,CHENG Hao,GONG Enpu,et al. Random noise suppression using adaptive threshold in Shearlet domain[J]. Oil Geophysical Prospecting,2020,55(2): 282-291,228. (in Chinese) [18] LI Biyuan,TANG Chen,ZHU Xinjun,et al. Shearlet transform for phase extraction in fringe projection profilometry with edges discontinuity[J]. Optics and Lasers in Engineering,2016,78: 91-98. doi: 10.1016/j.optlaseng.2015.10.007 [19] 李雪琴,蒋红海,刘培勇,等. 非下采样Contourlet域自适应阈值面的磁瓦表面缺陷检测[J]. 计算机辅助设计与图形学学报,2014,26(4): 553-558.LI Xueqin,JIANG Honghai,LIU Peiyong,et al. Defect detection on magnetic tile surface based on adaptive threshold surfaces in NSCT domain[J]. Journal of Computer-Aided Design & Computer Graphics,2014,26(4): 553-558. (in Chinese) -
点击查看大图
计量
- 文章访问数: 40
- HTML浏览量: 7
- PDF量: 6
- 被引次数: 0