维度分割法轴承全表面缺陷检测

doi:10.3778/j.issn.1002-8331.2206-0509

摘要/Abstract

摘要： 为提高轴承全表面缺陷的检测精度与速度，提出基于维度分割法的轴承全表面缺陷检测方法。通过自主搭建轴承缺陷检测平台，采用维度分割法对轴承视觉信息进行维度划分，并初步对各维度疑似缺陷区域提取，增强轴承外表面检测的完整性；利用轴承各维度小区域数据集训练VGG16网络模型，获取轴承特征向量，应用改进欧式距离公式替换VGG16全连接层对可疑区域进行判断；采用并行处理模式运行各维度缺陷检测算法。实验结果表明，该方法能有效地提高轴承全表面缺陷检测精度与速度，且漏检率较低，同时降低了设备的体积与成本，能够满足轴承工业全表面缺陷在线检测的需求。

关键词: 轴承, 维度分割, 神经网络, 多线程

Abstract: In order to improve the detection accuracy and speed of bearing full-surface defects, a bearing full surface defect detection method based on dimensional segmentation method is proposed. In this paper, by building a bearing defect detection platform independently, The dimensional segmentation method is used to dimensionally divide the bearing visual informationand initially extract the suspected defect areas in each dimension to enhance the integrity of bearing outer surface detection. The VGG16 network model is trained using the small region dataset of each dimension of the bearing to obtain the bearing feature vector and apply the improved Euclidean distance formula to replace the VGG16 fully connected layer to judge the suspicious region. Finally, parallel processing mode is used to run the defect detection algorithm in each dimension. The experimental results show that the method can effectively improve the accuracy and speed of full-surface defect detection of bearings, and the leakage rate is low, while reducing the size and cost of the equipment, which can meet the needs of online detection of full-surface defects in the bearing industry.

Key words: bearing, dimension segmentation, neural network, multithreading

杨冬毅, 黄丹平, 徐佳乐, 廖世鹏, 于少东. 维度分割法轴承全表面缺陷检测[J]. 计算机工程与应用, 2023, 59(24): 176-184.

YANG Dongyi, HUANG Danping, XU Jiale, LIAO Shipeng, YU Shaodong. Bearing Full Surface Defect Detection by Dimension Segmentation Method[J]. Computer Engineering and Applications, 2023, 59(24): 176-184.

参考文献

[1] 牛荣军，刘越，唐红利，等.多点支撑结构形变及轴系轴承承载性能分析[J].兵工学报，2023，44（2）：615-628.
NIU R J，LIU Y，TANG H L，et al.Deformation of the multi-point support structure and loading performance analysis of its shafting bearing[J].Acta Armamentarii，2023，44（2）：615-628.
[2] 张跃明，贾迎帅，纪姝婷.圆柱滚子轴承的径向刚度分析[J/OL].航空动力学报：1-10[2022-06-24].https：//doi.org/10.13224/j.cnki.jasp.20210474.
ZHANG Y M，JIA Y S，JI Z T.Radial stiffness analysis of cylindrical roller bearing[J/OL].Journal of Aerospace Power：1-10[2022-06-24].https：//doi.org/10.13224/j.cnki.jasp.20210474.
[3] 李军星，黄嘉鸿，邱明，等.基于广义Wiener过程的滚动轴承剩余寿命预测[J/OL].计算机集成制造系统：1-17[2022-06-24].http：//kns.cnki.net/kcms/detail/11.5946.TP.20220613.
0818.002.html.
LI J X，HUANG J H，QIU M，et al.Remaining life prediction of rolling bearings based on a generalized Wiener process[J/OL].Computer Integrated Manufacturing Systems：1-17[2022-06-24].http：//kns.cnki.net/kcms/detail/11.5946.TP.20220613.0818.002.html.
[4] LEI L，SUN S，ZHANG Y，et al.Segmented embedded rapid defect detection method for bearing surface defects[J].Machines，2021，9（2）：40.
[5] 徐建桥，吴俊，陈向成，等.基于规范化样本拆分的轴承缺陷检测[J].应用光学，2021，42（2）：327-333.
XU J Q，WU J，CHEN X C，et al.Bearing defects detection based on standardized sample split[J].Journal of Applied Optics，2021，42（2）：327-333.
[6] LIU B，YANG Y，WANG S，et al.An automatic system for bearing surface tiny defect detection based on multi-angleilluminations[J].Optik，2020，208：164517.
[7] KHEMILI I，CHOUCHANE M.Detection of rolling element bearing defects by adaptive filtering[J].European Journal of Mechanics-A/Solids，2005，24（2）：293-303.
[8] LI J Y，MIAO B，ZHANG W，et al.Refined composite multiscale fuzzy entropy：localized defect detection of rolling element bearing[J].Journal of Mechanical Science and Technology，2019，33：109-120.
[9] 石炜，李嘉楠，张惠丽，等.基于Faster R-CNN算法的列车轴承表面缺陷检测研究[J].机床与液压，2021，49（11）：103-108.
SHI W，LI J N，ZHANG H L，et al.Research on surface defect detection of train bearings based on Faster R-CNN algorithm[J].Machine Tool ＆ Hydraulics，2021，49（11）：103-108.
[10] 郑泽昊.基于改进YOLOv3的轴承封盖缺陷检测研究[D].辽宁鞍山：辽宁科技大学，2021.
ZHENG Z H.Research on detecting bearing-cover defects based on improved YOLOv3[D].Anshan：University of Science and Technology Liaoning，2021.
[11] 张闯闯.基于机器视觉的轴承套圈全表面缺陷检测系统研究[D].北京：中国矿业大学，2021.
ZHANG C C，Research on full surface defect inspection of bearing rings system based on machine vision[D].Beijing：China University of Mining and Technology，2021.
[12] 文生平，周正军，张啸言，等.基于计算机视觉的轴承滚子表面缺陷在线检测系统[J].华南理工大学学报（自然科学版），2020，48（10）：76-87.
WEN S P，ZHOU Z J，ZHANG X Y，et al.Online detection system of bearing roller’s surface defects based on computational vision[J].Journal of South China University of Technology，2020，48（10）：76-87.
[13] 陈文达，白瑞林，吉峰，等.基于机器视觉的轴承防尘盖表面缺陷检测[J].计算机工程与应用，2014，50（6）：250-254.
CHEN W D，BAI R L，JI F，et al.Bearing shield surface defect detection based on machine vision[J].Computer Engineering and Applications，2014，50（6）：250-254.
[14] 黄丹平，廖世鹏，于少东，等.基于机器视觉瓦楞纸板自动计数系统研究[J].机械工程学报，2017，53（10）：79-86.
HUANG D P，LIAO S P，YU S D，et al.Research on automatic counting system corrugated paper board based on machine vision[J].Journal of Mechanical Engineering，2017，53（10）：79-86.
[15] KAREN S，ANDREW Z.Very deep convolutional networks for large-scale image recognition[J].Computer Science，2014（3）：11-18.
[16] 黄丹平，李静，于少东，等.基于Curvelet变换的机器视觉系统在焊缝缺陷检测中的应用[J].焊接技术，2015，44（6）：57-61.
HUANG D P，LI J，YU S D，et al.Application of machine vision system based on Curvelet transform in the weld defect detection[J].Welding Technology，2015，44（6）：57-61.
[17] XU X M，XIE M S，MIAO P Q，et al.Perceptual-aware sketch simplification based on integrated VGG layers[J].IEEE Transactions on Visualization and Computer Graphics，2021，27（1）：178-189.
[18] BEHRENS T，SCHMIDT K，VISCARRA ROSSEL R A，et al.Spatial modelling with Euclidean distance fields and machine learning[J].European Journal of Soil Science，2018，69（5）：757-770.