基于图像技术的钢球表面缺陷分析与识别
|
摘要
钢球作为轴承的主要零件,其表面缺陷对轴承的精度、运转性能和使用寿命等都有着至关重要的影响。目前,在轴承行业中,对钢球表面缺陷的检测仍然采用传统的人工目视检验法,其准确性和稳定性均难以保证。本文应用数字图像技术进行了钢球表面缺陷实时检测识别系统的基础性研究,给出了钢球缺陷识别有效性的评价体系。
钢球表面有5种类型的缺陷,本文采用了高斯滤波和中值滤波分别对不同缺陷进行去噪,采用了灰度变换方法提高钢球图像边界信息对比度。根据钢球图像的特点,本文采用双阈值对缺陷进行分割,并提出了基于转基因遗传算子的OTSU理论自动优选阈值,清晰地将缺陷与背景分割开,完成图像二值化分割,达到计算机处理缺陷要求。由于分割后的钢球缺陷图像,存在缺陷边缘的不连续以及空间到图像映射不一致问题,导致缺陷边缘难以确定,为此本文提出了在小波域内利用小波变换多尺度分析和模局部极大值确定图像的边缘点并进行边缘点连接。实验结果表明,该方法检出的边缘完整、清晰,不需要进一步细化,同时避免噪声干扰。
钢球在转动时其表面缺陷的面积是随其位置而变化的,因此仅靠平面图像中的面积进行缺陷分类会产生很大的误差,造成缺陷等级分类不明确及漏检现象。为消除这一影响,本文在大量实验的基础上,建立了钢球球体面积投射的校正模型,恢复了缺陷面积为钢球表面对应的实际面积。
本文描述了钢球缺陷的形状特征参数:面积、长/短径比和欧拉数,给出了这些参数的计算方法,并对缺陷分类值进行定量分析。在对RBF神经网络训练算法深入研究的基础上,本文设计了基于RBF神经网络分类器对钢球缺陷进行识别。采用了两阶段学习策略来加速学习收敛;提出了动静相结合的隐含层设计算法构造较优的RBF神经网络结构;提出了误差校正的方法提高了RBF网络输出精度。开发了神经网络检测程序,并对点缺陷、凹坑缺陷、条缺陷和擦伤缺陷进行训练并测试,实验结果表明,基于RBF神经网络钢球缺陷识别法,准确率达96%。
由于钢球是强反射球面,给获取清晰的缺陷图像带来困难,通过对钢球光学反射特性进行研究,结合大量的试验,设计了用柔光布制作的光照箱,完成了图像采集实验系统的搭建。针对钢球表面全检测的要求,本文设计了用于图像检测的钢球展开机构,对钢球在展开装置上的运动进行了分析,建立了拍摄点运动轨迹的数学模型,确定检测一粒钢球需要拍摄的次数。通过计算机仿真和实验验证了钢球在该机构上能够完全展开,从而达到了对钢球表面的全部检测。
本文设计并开发了基于图像技术的钢球表面缺陷分析识别的软件系统,开发工具为VisualC++6.0,系统软件包括文件管理、图像处理算法、缺陷特征提取和缺陷判别4个功能模块,同时也可完成系统标定和分类器训练功能。
Surface defects of steel balls, which are an important part of bearings, make a great difference to the accuracy, revolving performances and service life of bearings. Currently, it is a common practice to identify defects of steel balls by means of human visual checking whose accuracy and stabilization are hard to guarantee. This dissertation carries out a basic research on a real-time detection system of identifying steel ball surface defects with digital image technology, and provides an integral and effective evaluation system of identifying steel ball defects.
There are five kinds of defects on steel ball surface, which appear at random. The dissertation first reduces noise through Gaussian filtering and median filtering, and then increases the contrast of edge information image through grey-scale transform. According to the property of steel ball images, this dissertation dismembers defects using dual threshold, presents automatically preferred threshold value based on a transgenic genetic GA genetic algorithms OTUS theory, thus clearly separating defects and background, completing image binarization separation, and enabling a computer to process testing. Because the edge of steel ball surface defects is discontinuous and inconsistent from space to plane, it is difficult to determine the edge of detects. This dissertation points out that multistage analysis and maximum of partial modulus can determine edge point of images based on wavelet transform and edge point link. Experimental results indicate that the method can get complete and clear edges and needs no further refinement, and at the same time avoid noise interference.
The area of defect region varies with the location of defects while a ball is rotating, so it would result in great error, unclear classification of defects and omission of testing if defects were classified just according to areas of flat images. To remove this phenomenon, on the basis of a great number of experiments, this dissertation summarizes an emendating model of ball projected area, and resuming defect area is the responding surface area of a steel ball.
This dissertation describes the shape characteristics of steel balls: area, ratio of long and short diameters, and Euler numbers, gives a calculation method, and quantitatively analyzes classified values of defects as well. Through further research on the training algorithms for RBF neural network, this dissertation designs a classifier based on RBF neural network to identify the defects of steel balls. Two-stage learning strategy is used to accelerate the rate of convergence, a preferable frame of implication layer by using a static and dynamic combination implication layer is put forward, and a algorithm is presented to improve the precision of RBF network output by means of error correction. Neural network programs are developed to train and test four kinds of defects: point defects, dent defects, strip defects and abrasion defects. Experiments have shown that accuracy is 96% based on RBF.
It is hard to get a clear image of steel ball defects due to the complexity of steel balls’mirror reflection, so an illuminating system is designed, whose lighting box is produced with soft lighting cloth to finish the building of an image collecting experimental system. This dissertation designs a spreading device to detect steel balls, analyzes the motion of steel balls on the device, builds a math model of shooting point-motion trails, and determines the shooting times of testing a ball. Computer simulation and experiments have shown that this device can test the whole of the surface of a steel ball.
This dissertation designs and develops an experimenting testing system based on image technology using VisualC++ 6.0 to identify defects of steel balls. The system consists of four-function modules: file management, image processing algorithm, defect property extraction, and identification of defects.
钢球表面有5种类型的缺陷,本文采用了高斯滤波和中值滤波分别对不同缺陷进行去噪,采用了灰度变换方法提高钢球图像边界信息对比度。根据钢球图像的特点,本文采用双阈值对缺陷进行分割,并提出了基于转基因遗传算子的OTSU理论自动优选阈值,清晰地将缺陷与背景分割开,完成图像二值化分割,达到计算机处理缺陷要求。由于分割后的钢球缺陷图像,存在缺陷边缘的不连续以及空间到图像映射不一致问题,导致缺陷边缘难以确定,为此本文提出了在小波域内利用小波变换多尺度分析和模局部极大值确定图像的边缘点并进行边缘点连接。实验结果表明,该方法检出的边缘完整、清晰,不需要进一步细化,同时避免噪声干扰。
钢球在转动时其表面缺陷的面积是随其位置而变化的,因此仅靠平面图像中的面积进行缺陷分类会产生很大的误差,造成缺陷等级分类不明确及漏检现象。为消除这一影响,本文在大量实验的基础上,建立了钢球球体面积投射的校正模型,恢复了缺陷面积为钢球表面对应的实际面积。
本文描述了钢球缺陷的形状特征参数:面积、长/短径比和欧拉数,给出了这些参数的计算方法,并对缺陷分类值进行定量分析。在对RBF神经网络训练算法深入研究的基础上,本文设计了基于RBF神经网络分类器对钢球缺陷进行识别。采用了两阶段学习策略来加速学习收敛;提出了动静相结合的隐含层设计算法构造较优的RBF神经网络结构;提出了误差校正的方法提高了RBF网络输出精度。开发了神经网络检测程序,并对点缺陷、凹坑缺陷、条缺陷和擦伤缺陷进行训练并测试,实验结果表明,基于RBF神经网络钢球缺陷识别法,准确率达96%。
由于钢球是强反射球面,给获取清晰的缺陷图像带来困难,通过对钢球光学反射特性进行研究,结合大量的试验,设计了用柔光布制作的光照箱,完成了图像采集实验系统的搭建。针对钢球表面全检测的要求,本文设计了用于图像检测的钢球展开机构,对钢球在展开装置上的运动进行了分析,建立了拍摄点运动轨迹的数学模型,确定检测一粒钢球需要拍摄的次数。通过计算机仿真和实验验证了钢球在该机构上能够完全展开,从而达到了对钢球表面的全部检测。
本文设计并开发了基于图像技术的钢球表面缺陷分析识别的软件系统,开发工具为VisualC++6.0,系统软件包括文件管理、图像处理算法、缺陷特征提取和缺陷判别4个功能模块,同时也可完成系统标定和分类器训练功能。
Surface defects of steel balls, which are an important part of bearings, make a great difference to the accuracy, revolving performances and service life of bearings. Currently, it is a common practice to identify defects of steel balls by means of human visual checking whose accuracy and stabilization are hard to guarantee. This dissertation carries out a basic research on a real-time detection system of identifying steel ball surface defects with digital image technology, and provides an integral and effective evaluation system of identifying steel ball defects.
There are five kinds of defects on steel ball surface, which appear at random. The dissertation first reduces noise through Gaussian filtering and median filtering, and then increases the contrast of edge information image through grey-scale transform. According to the property of steel ball images, this dissertation dismembers defects using dual threshold, presents automatically preferred threshold value based on a transgenic genetic GA genetic algorithms OTUS theory, thus clearly separating defects and background, completing image binarization separation, and enabling a computer to process testing. Because the edge of steel ball surface defects is discontinuous and inconsistent from space to plane, it is difficult to determine the edge of detects. This dissertation points out that multistage analysis and maximum of partial modulus can determine edge point of images based on wavelet transform and edge point link. Experimental results indicate that the method can get complete and clear edges and needs no further refinement, and at the same time avoid noise interference.
The area of defect region varies with the location of defects while a ball is rotating, so it would result in great error, unclear classification of defects and omission of testing if defects were classified just according to areas of flat images. To remove this phenomenon, on the basis of a great number of experiments, this dissertation summarizes an emendating model of ball projected area, and resuming defect area is the responding surface area of a steel ball.
This dissertation describes the shape characteristics of steel balls: area, ratio of long and short diameters, and Euler numbers, gives a calculation method, and quantitatively analyzes classified values of defects as well. Through further research on the training algorithms for RBF neural network, this dissertation designs a classifier based on RBF neural network to identify the defects of steel balls. Two-stage learning strategy is used to accelerate the rate of convergence, a preferable frame of implication layer by using a static and dynamic combination implication layer is put forward, and a algorithm is presented to improve the precision of RBF network output by means of error correction. Neural network programs are developed to train and test four kinds of defects: point defects, dent defects, strip defects and abrasion defects. Experiments have shown that accuracy is 96% based on RBF.
It is hard to get a clear image of steel ball defects due to the complexity of steel balls’mirror reflection, so an illuminating system is designed, whose lighting box is produced with soft lighting cloth to finish the building of an image collecting experimental system. This dissertation designs a spreading device to detect steel balls, analyzes the motion of steel balls on the device, builds a math model of shooting point-motion trails, and determines the shooting times of testing a ball. Computer simulation and experiments have shown that this device can test the whole of the surface of a steel ball.
This dissertation designs and develops an experimenting testing system based on image technology using VisualC++ 6.0 to identify defects of steel balls. The system consists of four-function modules: file management, image processing algorithm, defect property extraction, and identification of defects.
引文
[1]王霞君.国内外钢球振动测试[J].轴承,1989,10(3):36-41.
[2]黑部利次.スピン角度制御型ボール研磨(第二报)[J].精密工學會誌,1997,63(5):726-730.
[3]姜海彬.钢球的几何精度及表面质量对钢球单体振动值的影响分析[J].机械工程师,2003(5):45-46.
[4]杨晓蔚.国外低噪声轴承技术发展[J].轴承,2002,23(4):31-34.
[5] KUROSAWA Y.Subspace Method Obtained from Gaussian Distribution on a Hyper Spherical Surface[J].Journal of the Japan Society for Elint and Commu-nications,1998,J81-D-Ⅱ(6):1205-1212.
[6]张葵摘.日本NSK新型滚动轴承浅析[J].轴承,2000,21(9):36-39.
[7]蒋沂萍.钢球抽检最佳方案的确定[J].轴承,2002,23(11):25-28.
[8]陶必悦.对我国当前球轴承振动噪声状况的技术探讨[J].轴承,2000,21(2):5-8.
[9] ROBERT W L.Optical Scanner for Ball Bearing Inspection[J].Optical Inspection Ballroom East,1981:170-172.
[10] ANTHONY J E, GOODAL L W.The Future of 3-D Range Image Measurement Using Binary-Encoded Pattern Projection[J].Optics and Lasers in Engineer- ing,1994(21):99-110.
[11] GENG Z J.Rainbow Three-Dimensional Camera:New Concept of High-Speed Three Dimensional Vision Systems[J].Optical Engineering,1994,35(2):376-383.
[12] TECHNICAL.Description and Instructions for Attendance of Automatic Sorting Machine for Defect-metric Inspection of Bearing Ball Surfaces[R].Types AVIKO K-06140E and AVIKO K-1418E.Made in Somet Ltd of Czech.
[13] RONG Q A.Research and Manufacture of the Instrument of Bearing Ball's Nondestructive Testing[J].Aviation Precision Manufacturing Technology, 2005,4(41):52-54.
[14]王保振.国外钢球制造技术简介[J].轴承,1999,20(3):40-42.
[15] ABDULLAH M Z, MOHAMAD S J, FATHINUL S A, et al.Discrimination and Classification of Fresh-Cut Starfruits Using Automated Machine VisionSystem[J].Journal of Food Engineering,2006,(76):506-523.
[16]徐科,徐金悟.基于图像处理的冷轧带钢表面缺陷在线检测[J].钢铁,2002,(12):66-73.
[17] TANDON N, CHOUDHURY A.A Review of Vibration and Acoustic Measurement Methods for the Detection of Defects in Rolling Element Bearings[J].Tribology International,1999,(32):469-480.
[18] KAKIMOTO A.Detection of Surface Defects on Steel Ball Bearing in Production Process Using a capacitive sensor[J].Measurement,1996,17(1): 51-57.
[19]张艳萍.钢球表面缺陷涡流探伤仪分析[J].轴承,2007,28(2):32-33.
[20] OSAWA S.Profile Measurement by Combination Projection Method[J].1996 the Japan-China Bilateral Symposium on Advanced Manufacturing Engineering. Hayama,Japan Society for the Promotion of Science and Chi-nese Academy of Sciences,1996(8):207-211.
[21]徐淑琼.轴承球的声发射检测技术[J].无损检测,2003,24(7):358-359.
[22] LIOULIOS A N, ANTONIADIS I A.Effect of Rotational Speed Fluctuations on the Dynamic Behaviour of Rolling Element Bearings with Radial Clearances[C].International Journal of Mechanical Sciences,2006,(48):809-829.
[23]理华,徐春广.滚动轴承声发射检测技术[J].轴承,2002,23(7):24-26.
[24]张永林,狄红卫.光电子技术[M].北京:高等教育出版社,2005:140-141.
[25]蒋沂萍.轴承球缺陷的超声波检测方法[J].机械制造与自动化,2005,34(5):37-39.
[26]王新民.对钢球质量验收标准条款的理解[J].轴承,1997,18(4):32-35.
[27]葛华伟,贺霞.改进钢球生产工艺与提高钢球制造精度等级[J].黑龙江科技信息,2003(11):29-32.
[28]谢恒星,张一清.钢球的应用状况与磨损机理[J].武汉化工学院学报,2002,24(1):42-48.
[29]杨怀玉.钢球检测中的运动分析[J].中国水运:学术版,2006,6(10):33-34.
[30]机械工业部轴承工业局统一企业标准.ZQ8-83.钢球表面质量标准照片图册[S].
[31] FURUTANI R.Profile Measurement by Comparing the Multi-Gray Projection with Reference Projection[C].Proc of the 5th ISMQC, 1995(8): 368-372.
[32] AZENCOTT R, Wang J P, Younes L.Texture Classification Using Windowed Fourier Filters[C].IEEE Trans on Patt.Anal.Mach.Intess,1997,19(2):148-153.
[33] JENS W.A Milestone on the Way to the High-performance Rolling Bearing.Ceramic Forum International,2002,79(4):21-24.
[34]康涛.基于图像处理的检测系统的研究与设计[D].西安:西安科技大学(硕士学位论文),2005:1-2.
[35]董璐.数字图像处理与识别系统的开发[D].南京:东南大学(硕士学位论文),2004:1-3.
[36]李伊文,刘盛长.钢球表面缺陷的电脑显微观测[J].轴承,1998,19(10):32-35.
[37]潘洪平,谢水生.钢球表面质量评价系统用展开轮的理论研究[J].轴承,2001,22(12):28-31.
[38]赵刚,王宝义.AvikoK型钢球外观检验机中子午线展开机构的理论分析[J].轴承,1997,18(5):35-39.
[39]赵刚,马松轩.钢球表面展开机构的运动学方程解析解[J].轴承,1998,19(7):25-32.
[40]杨铁滨,王黎钦.陶瓷球表面缺陷图像检测及球面展开机构的研究[J].兵工学报,2006,27(4):708-711.
[41]潘洪平,董申.一种基于图像纹理特征的钢球振动值检测新方法[J].中国机械工程,2001,12(5):174-176.
[42]潘洪平,董申.钢球表面质量评价系统[J].轴承,2000,21(7):30-35.
[43]潘洪平,董申.数字图像处理与识别技术在钢球质量检测中的应用[J].机电产品市场,2000(1):30-31.
[44]马云艳.CCD钢球外观检测技术研究[D].哈尔滨:哈尔滨工业大学(硕士学位论文),2005:26-28.
[45]李春颖.机器视觉在钢球表面缺陷检测中的应用[J].计算机与现代化,2005,122(10):63-65.
[46] DEMIRKAYA O, MUSA H.Determination of Image Bimodality Thresholds for Different Intensity Distributions[J].Signal Processing Image Communic-ation,2004,(19):507-516.
[47]刘桥方,严枫.我国轴承制造技术的现状及其发展趋势[J].轴承,2005,26(6):42-45.
[48] BLAYVAL I, BRUCKSTEIN A, KIMMEL R.Efficient Computation of Adaptive Threshold Surfaces for Image Binarization[J].Pattern Recognition, 2006,(39):89-101.
[49] RAMAR K, ARUMUGAM S, SIVANANDAM S N, et al.Quantitative Fuzzy Measures for Threshold Selection[J].Pattern Recongnition Letters, 2000,(21): 1-7.
[50]彭仪普.傅立叶变换原理及其在数字图像处理中的应用[J].铁路航测,2000(3):4-5.
[51]王文东,张根耀,王文发.数字图像在频域中的处理[J].西安工程科技学院学报,2006,20(4):515-517.
[52]赵军芳.傅立叶变换在数字图像处理中的应用[J].国外电子测量技术,2004,(6):17-20.
[53] MURINO, VITTORIO.Noise Texture Classification:A Higher-Order Statist-ics Approach[J].Pattern Recognition,1998,31(4):383-393.
[54]夏振良.数字图像处理技术[M].北京:科学出版社,1999:147-155.
[55]李粥程,彭天强,彭波.智能图像处理技术[M].北京:电子工业出版社,2004:71-78.
[56]陈欣,楼玉萍.基于PDE’S的图像平滑方法[J].计算机与现代化,2004,121(5):8-10.
[57]叶晓东,朱兆达.中值滤波的快速算法[J].信号处理,1997,13(3):227-230.
[58] POLESEL A, RAMPONI G, Mathews V.Image Enhancement Via Adaptive Unsharp Masking[C].IEEE Transactions on Image Processing, 2000,9(3): 505-510.
[59]雷小丽,党群.一种新的非线性变换法实现图像增强的方法[J].光子学报,2007,36(6):346-348.
[60]付忠良.图像阈值选取方法—Ostu方法的推广[J].计算机应用,2000,20(5):37-39.
[61] SANKUR B, SEZGIN M.A Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation[J].Journal of Electronic Imaging, 2004, 13(1):146-165.
[62] LIFFNG L, SCLAROFF S.Indes Trees for Accelerating Deformable Temp- late Matching[J].Pattem Recognition Letters,2002,23(12):1483-1493.
[63]魏志成等.一种新的图像分割的自适应算法的研究[J].中国图像图形学报,2000,5(3):216-220.
[64]高求英,张利等.一种基于会读期望值的图像二值化算法[J].中国图像图形学报,1999,4(6):524-527.
[65] ZHOU X, He X R, Chen B, et al.Convergencc Cnhanced Genetic Algoritlm with Successive Zoom in Method for Solving Continuous Lptin Ization Probkms[J].Computers and Structures,2003,81(1):1715-1725.
[66] Su C T, Chiang C L.No Convex Power Coonomic Dispatch by Improved Genetic Algonithm with Multiplier Updating Metbod[J].Electric Power Components and Systems,2004,32(3):257-273.
[67]杨世达,李庆华,阮幼林.改进遗传算法全局收敛分析[J].计算机工程与设计,2005,7:1695-1697.
[68] SUDEEP S, KIM L B.On Optimal Infinite Impulse Response Edge Detecti- on Filter[J].IEEE Trans Pattern Analysis and Machine Intelligence,1991,11 (13):1154~1170.
[69] RAVI D.A New Active Contour Model for Shape Extraction[J].Math Meth Appl Sci,2000,223:709-722.
[70] OSAWA S.Profile Measurement Using Multi-Gray Scale Patterns Pro-jection[J].Journal of Japan Precision Engineering,1995,61(8):1101-1125.
[71] JACQUIN A, ELEFTHERIADIS A.Automatic Location Tracking of Faces and Facial Featcial Features in Video Sequences[C].IEEI Proc,Of Int,Workshop on Automatic Face and Gesture Recongnition,1995:142-147.
[72] CANNY J.A Computation Approach to Edge Detection[J].IEEE Trans on PAMI,1986,8(6):679-698.
[73] WANG P, LIU J, WU C Y, et al.Adaptive Model Based on Voting Probabilis-tic Models for Image Tracking Algorithm[C].Proceedings of WCICA, 2006: 9822-9826.
[74]王义文,刘献礼,谢晖.基于小波变换的显微图像清晰度评价函数及3-D自动调焦技术[J].光学精密工程,2006,14(6):1063-1069.
[75]李瑛.多元小波的结构及其应用[D].长春:吉林大学(博士学位论文),2004:41-50.
[76] LIU X L.The Measuration of Craster Wear of Cutting Tools Based on Image[C].Proceedings of the Fifth International Conference on Electronic Measurement&Instr7uments, Guilin China, 2001(18):622-625.
[77] GIROSI F, JONES M.Regularization Theory and Neural Networks Architec- tures[J].Neural Computation,1995,(7):219-269.
[78] BLANZIERI E.Theoretical Interpretations and Applications of Radial Basis Function Networks[J].Department of Information and Communication Tech- nology University of Trento,Italy,2003,230-242.
[79]王旭东,邵惠鹤.RBF神经网络理论及在控制中的应用[J].信息与控制,1997,26(4):272-284.
[80] TIANPING C, HONG C.Approximation Capability To Functions of Several Variables Nonlinear Functionals And Operators by Radial Basis Function Neural Networks[J].IEEE Transactions on Neural Networks,1995,6(4):904-910.
[81] SHANG Y, WAH B W.Global Optimization for Neural Network Training[J]. IEEE Computer,1996,29(3):45-54.
[82] YAO X.Evolving Artificial Neural Networks[C].PIEEE,Proceedings of the IEEE,1999,87(9):123-132.
[83] BANSAL K, VADHAVKAR S.Neural Networks Based Data Mining Applic- ation for Medical Inventory Problems[J].Brandeis Univrsity,2005,91-98.
[84]周俊武,孙传尧.径向基函数(RBF)网络的研究及实现[J].矿冶,2001,10(4):78-88.
[85]阎平凡,张长水.人工神经网络与模拟进化计算[M].第二版.北京:清华大学出版社,2005:45-47.
[86] PINKUS A.Approximation Theory of the MLP Model in Neural Networks[J]. Acta Numerica Cambridge University Press,1999,143-195.
[87] JAIN A K, MAO J.Artificial Neural Networks:A Tutorial[J].IEEE Compu- ter Special Issue on Neural Computing,1996:69~82.
[88] MURPHYP M, AHAD D W.UCI Repository Of Machine Learning Databases [OL].[2007,11].University of California,Irvine, http://www.ics. uci.edu/- mlearn/.
[89] ZEKKERIVA U, CUNEVT G.Analysis of Input-output Clustering for Dete- rmining Centers of RBF[J].IEEE Trans Neural Networks,2000,16(4):851-857.
[90]朱明星,张德龙.RBF网络基函数中心选取算法的研究[J].安徽大学学报:自然科学版,2000,24(1):72-78.
[91]孙延风,梁艳春,孟庆福.改进的神经网络最近邻聚类学习算法及其应用[J].吉林大学学报:信息科学版,2002,(1):63-66.
[92]陶红勇,王京,刘聪.基于RBF神经网络的板形缺陷识别[J].新疆钢铁,2003,(2):17-18,22.
[93] DENIS A L, FRED M, CHRISTOPHE D, et al.Vision System for Defect Iimaging Detection and Characterization on a Specular Surface of a 3D Object[J].Image and Vision Computing,2002,20:569-580.
[94] LE J, GUO J J.A Fast Defect-detecting Method for Smooth Hemispherical Shell Surface[J].Opto-Electronic Engineering,2004, 31(10):32-35.
[95] ZHANG J, CAI L.Profilometry Using an Optical Stylus with Interferometric readout[J].Measurement Science & Technology,1997,8:546-549.
[96]苏显渝.三维面形测量技术的新进展[J].物理,1996,25(10):614-620.
[97] ZENG L J, HIROKAZU M.Two-directional Scanning Method for Reducing the Shadow Effects in Laser Triangulation[J].Measurement Science & Technology,1997,8:262-266.
[98] JENS W.Ceranics A Milestone on the Way to the High-performance Rolling Bearing[C].Ceramic Forum International,2002,79(4):21-24.
[99] WANG Y, HADFIELD M.Failure Modes of Ceramic Rolling Elements With Surface Crack Defects[J].Wear,2004,256(1):208-219.
[100]WANG L, SNIDLE R W, Gu L.Rolling Contact Silicon Nitride Bearing Technology:A Review of Recent Research[J].Wear,2000,246(11):159-173.
[101]郭红燕.新型精密轴承球超精密研磨加工系统仿真与设计优化[D].南京:南京航空航天大学(硕士学位论文),2006:55-72.
[102]龚曙光.ANSYS工程应用实例解析[M].北京:机械工业出版社,2003:32-40.
[2]黑部利次.スピン角度制御型ボール研磨(第二报)[J].精密工學會誌,1997,63(5):726-730.
[3]姜海彬.钢球的几何精度及表面质量对钢球单体振动值的影响分析[J].机械工程师,2003(5):45-46.
[4]杨晓蔚.国外低噪声轴承技术发展[J].轴承,2002,23(4):31-34.
[5] KUROSAWA Y.Subspace Method Obtained from Gaussian Distribution on a Hyper Spherical Surface[J].Journal of the Japan Society for Elint and Commu-nications,1998,J81-D-Ⅱ(6):1205-1212.
[6]张葵摘.日本NSK新型滚动轴承浅析[J].轴承,2000,21(9):36-39.
[7]蒋沂萍.钢球抽检最佳方案的确定[J].轴承,2002,23(11):25-28.
[8]陶必悦.对我国当前球轴承振动噪声状况的技术探讨[J].轴承,2000,21(2):5-8.
[9] ROBERT W L.Optical Scanner for Ball Bearing Inspection[J].Optical Inspection Ballroom East,1981:170-172.
[10] ANTHONY J E, GOODAL L W.The Future of 3-D Range Image Measurement Using Binary-Encoded Pattern Projection[J].Optics and Lasers in Engineer- ing,1994(21):99-110.
[11] GENG Z J.Rainbow Three-Dimensional Camera:New Concept of High-Speed Three Dimensional Vision Systems[J].Optical Engineering,1994,35(2):376-383.
[12] TECHNICAL.Description and Instructions for Attendance of Automatic Sorting Machine for Defect-metric Inspection of Bearing Ball Surfaces[R].Types AVIKO K-06140E and AVIKO K-1418E.Made in Somet Ltd of Czech.
[13] RONG Q A.Research and Manufacture of the Instrument of Bearing Ball's Nondestructive Testing[J].Aviation Precision Manufacturing Technology, 2005,4(41):52-54.
[14]王保振.国外钢球制造技术简介[J].轴承,1999,20(3):40-42.
[15] ABDULLAH M Z, MOHAMAD S J, FATHINUL S A, et al.Discrimination and Classification of Fresh-Cut Starfruits Using Automated Machine VisionSystem[J].Journal of Food Engineering,2006,(76):506-523.
[16]徐科,徐金悟.基于图像处理的冷轧带钢表面缺陷在线检测[J].钢铁,2002,(12):66-73.
[17] TANDON N, CHOUDHURY A.A Review of Vibration and Acoustic Measurement Methods for the Detection of Defects in Rolling Element Bearings[J].Tribology International,1999,(32):469-480.
[18] KAKIMOTO A.Detection of Surface Defects on Steel Ball Bearing in Production Process Using a capacitive sensor[J].Measurement,1996,17(1): 51-57.
[19]张艳萍.钢球表面缺陷涡流探伤仪分析[J].轴承,2007,28(2):32-33.
[20] OSAWA S.Profile Measurement by Combination Projection Method[J].1996 the Japan-China Bilateral Symposium on Advanced Manufacturing Engineering. Hayama,Japan Society for the Promotion of Science and Chi-nese Academy of Sciences,1996(8):207-211.
[21]徐淑琼.轴承球的声发射检测技术[J].无损检测,2003,24(7):358-359.
[22] LIOULIOS A N, ANTONIADIS I A.Effect of Rotational Speed Fluctuations on the Dynamic Behaviour of Rolling Element Bearings with Radial Clearances[C].International Journal of Mechanical Sciences,2006,(48):809-829.
[23]理华,徐春广.滚动轴承声发射检测技术[J].轴承,2002,23(7):24-26.
[24]张永林,狄红卫.光电子技术[M].北京:高等教育出版社,2005:140-141.
[25]蒋沂萍.轴承球缺陷的超声波检测方法[J].机械制造与自动化,2005,34(5):37-39.
[26]王新民.对钢球质量验收标准条款的理解[J].轴承,1997,18(4):32-35.
[27]葛华伟,贺霞.改进钢球生产工艺与提高钢球制造精度等级[J].黑龙江科技信息,2003(11):29-32.
[28]谢恒星,张一清.钢球的应用状况与磨损机理[J].武汉化工学院学报,2002,24(1):42-48.
[29]杨怀玉.钢球检测中的运动分析[J].中国水运:学术版,2006,6(10):33-34.
[30]机械工业部轴承工业局统一企业标准.ZQ8-83.钢球表面质量标准照片图册[S].
[31] FURUTANI R.Profile Measurement by Comparing the Multi-Gray Projection with Reference Projection[C].Proc of the 5th ISMQC, 1995(8): 368-372.
[32] AZENCOTT R, Wang J P, Younes L.Texture Classification Using Windowed Fourier Filters[C].IEEE Trans on Patt.Anal.Mach.Intess,1997,19(2):148-153.
[33] JENS W.A Milestone on the Way to the High-performance Rolling Bearing.Ceramic Forum International,2002,79(4):21-24.
[34]康涛.基于图像处理的检测系统的研究与设计[D].西安:西安科技大学(硕士学位论文),2005:1-2.
[35]董璐.数字图像处理与识别系统的开发[D].南京:东南大学(硕士学位论文),2004:1-3.
[36]李伊文,刘盛长.钢球表面缺陷的电脑显微观测[J].轴承,1998,19(10):32-35.
[37]潘洪平,谢水生.钢球表面质量评价系统用展开轮的理论研究[J].轴承,2001,22(12):28-31.
[38]赵刚,王宝义.AvikoK型钢球外观检验机中子午线展开机构的理论分析[J].轴承,1997,18(5):35-39.
[39]赵刚,马松轩.钢球表面展开机构的运动学方程解析解[J].轴承,1998,19(7):25-32.
[40]杨铁滨,王黎钦.陶瓷球表面缺陷图像检测及球面展开机构的研究[J].兵工学报,2006,27(4):708-711.
[41]潘洪平,董申.一种基于图像纹理特征的钢球振动值检测新方法[J].中国机械工程,2001,12(5):174-176.
[42]潘洪平,董申.钢球表面质量评价系统[J].轴承,2000,21(7):30-35.
[43]潘洪平,董申.数字图像处理与识别技术在钢球质量检测中的应用[J].机电产品市场,2000(1):30-31.
[44]马云艳.CCD钢球外观检测技术研究[D].哈尔滨:哈尔滨工业大学(硕士学位论文),2005:26-28.
[45]李春颖.机器视觉在钢球表面缺陷检测中的应用[J].计算机与现代化,2005,122(10):63-65.
[46] DEMIRKAYA O, MUSA H.Determination of Image Bimodality Thresholds for Different Intensity Distributions[J].Signal Processing Image Communic-ation,2004,(19):507-516.
[47]刘桥方,严枫.我国轴承制造技术的现状及其发展趋势[J].轴承,2005,26(6):42-45.
[48] BLAYVAL I, BRUCKSTEIN A, KIMMEL R.Efficient Computation of Adaptive Threshold Surfaces for Image Binarization[J].Pattern Recognition, 2006,(39):89-101.
[49] RAMAR K, ARUMUGAM S, SIVANANDAM S N, et al.Quantitative Fuzzy Measures for Threshold Selection[J].Pattern Recongnition Letters, 2000,(21): 1-7.
[50]彭仪普.傅立叶变换原理及其在数字图像处理中的应用[J].铁路航测,2000(3):4-5.
[51]王文东,张根耀,王文发.数字图像在频域中的处理[J].西安工程科技学院学报,2006,20(4):515-517.
[52]赵军芳.傅立叶变换在数字图像处理中的应用[J].国外电子测量技术,2004,(6):17-20.
[53] MURINO, VITTORIO.Noise Texture Classification:A Higher-Order Statist-ics Approach[J].Pattern Recognition,1998,31(4):383-393.
[54]夏振良.数字图像处理技术[M].北京:科学出版社,1999:147-155.
[55]李粥程,彭天强,彭波.智能图像处理技术[M].北京:电子工业出版社,2004:71-78.
[56]陈欣,楼玉萍.基于PDE’S的图像平滑方法[J].计算机与现代化,2004,121(5):8-10.
[57]叶晓东,朱兆达.中值滤波的快速算法[J].信号处理,1997,13(3):227-230.
[58] POLESEL A, RAMPONI G, Mathews V.Image Enhancement Via Adaptive Unsharp Masking[C].IEEE Transactions on Image Processing, 2000,9(3): 505-510.
[59]雷小丽,党群.一种新的非线性变换法实现图像增强的方法[J].光子学报,2007,36(6):346-348.
[60]付忠良.图像阈值选取方法—Ostu方法的推广[J].计算机应用,2000,20(5):37-39.
[61] SANKUR B, SEZGIN M.A Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation[J].Journal of Electronic Imaging, 2004, 13(1):146-165.
[62] LIFFNG L, SCLAROFF S.Indes Trees for Accelerating Deformable Temp- late Matching[J].Pattem Recognition Letters,2002,23(12):1483-1493.
[63]魏志成等.一种新的图像分割的自适应算法的研究[J].中国图像图形学报,2000,5(3):216-220.
[64]高求英,张利等.一种基于会读期望值的图像二值化算法[J].中国图像图形学报,1999,4(6):524-527.
[65] ZHOU X, He X R, Chen B, et al.Convergencc Cnhanced Genetic Algoritlm with Successive Zoom in Method for Solving Continuous Lptin Ization Probkms[J].Computers and Structures,2003,81(1):1715-1725.
[66] Su C T, Chiang C L.No Convex Power Coonomic Dispatch by Improved Genetic Algonithm with Multiplier Updating Metbod[J].Electric Power Components and Systems,2004,32(3):257-273.
[67]杨世达,李庆华,阮幼林.改进遗传算法全局收敛分析[J].计算机工程与设计,2005,7:1695-1697.
[68] SUDEEP S, KIM L B.On Optimal Infinite Impulse Response Edge Detecti- on Filter[J].IEEE Trans Pattern Analysis and Machine Intelligence,1991,11 (13):1154~1170.
[69] RAVI D.A New Active Contour Model for Shape Extraction[J].Math Meth Appl Sci,2000,223:709-722.
[70] OSAWA S.Profile Measurement Using Multi-Gray Scale Patterns Pro-jection[J].Journal of Japan Precision Engineering,1995,61(8):1101-1125.
[71] JACQUIN A, ELEFTHERIADIS A.Automatic Location Tracking of Faces and Facial Featcial Features in Video Sequences[C].IEEI Proc,Of Int,Workshop on Automatic Face and Gesture Recongnition,1995:142-147.
[72] CANNY J.A Computation Approach to Edge Detection[J].IEEE Trans on PAMI,1986,8(6):679-698.
[73] WANG P, LIU J, WU C Y, et al.Adaptive Model Based on Voting Probabilis-tic Models for Image Tracking Algorithm[C].Proceedings of WCICA, 2006: 9822-9826.
[74]王义文,刘献礼,谢晖.基于小波变换的显微图像清晰度评价函数及3-D自动调焦技术[J].光学精密工程,2006,14(6):1063-1069.
[75]李瑛.多元小波的结构及其应用[D].长春:吉林大学(博士学位论文),2004:41-50.
[76] LIU X L.The Measuration of Craster Wear of Cutting Tools Based on Image[C].Proceedings of the Fifth International Conference on Electronic Measurement&Instr7uments, Guilin China, 2001(18):622-625.
[77] GIROSI F, JONES M.Regularization Theory and Neural Networks Architec- tures[J].Neural Computation,1995,(7):219-269.
[78] BLANZIERI E.Theoretical Interpretations and Applications of Radial Basis Function Networks[J].Department of Information and Communication Tech- nology University of Trento,Italy,2003,230-242.
[79]王旭东,邵惠鹤.RBF神经网络理论及在控制中的应用[J].信息与控制,1997,26(4):272-284.
[80] TIANPING C, HONG C.Approximation Capability To Functions of Several Variables Nonlinear Functionals And Operators by Radial Basis Function Neural Networks[J].IEEE Transactions on Neural Networks,1995,6(4):904-910.
[81] SHANG Y, WAH B W.Global Optimization for Neural Network Training[J]. IEEE Computer,1996,29(3):45-54.
[82] YAO X.Evolving Artificial Neural Networks[C].PIEEE,Proceedings of the IEEE,1999,87(9):123-132.
[83] BANSAL K, VADHAVKAR S.Neural Networks Based Data Mining Applic- ation for Medical Inventory Problems[J].Brandeis Univrsity,2005,91-98.
[84]周俊武,孙传尧.径向基函数(RBF)网络的研究及实现[J].矿冶,2001,10(4):78-88.
[85]阎平凡,张长水.人工神经网络与模拟进化计算[M].第二版.北京:清华大学出版社,2005:45-47.
[86] PINKUS A.Approximation Theory of the MLP Model in Neural Networks[J]. Acta Numerica Cambridge University Press,1999,143-195.
[87] JAIN A K, MAO J.Artificial Neural Networks:A Tutorial[J].IEEE Compu- ter Special Issue on Neural Computing,1996:69~82.
[88] MURPHYP M, AHAD D W.UCI Repository Of Machine Learning Databases [OL].[2007,11].University of California,Irvine, http://www.ics. uci.edu/- mlearn/.
[89] ZEKKERIVA U, CUNEVT G.Analysis of Input-output Clustering for Dete- rmining Centers of RBF[J].IEEE Trans Neural Networks,2000,16(4):851-857.
[90]朱明星,张德龙.RBF网络基函数中心选取算法的研究[J].安徽大学学报:自然科学版,2000,24(1):72-78.
[91]孙延风,梁艳春,孟庆福.改进的神经网络最近邻聚类学习算法及其应用[J].吉林大学学报:信息科学版,2002,(1):63-66.
[92]陶红勇,王京,刘聪.基于RBF神经网络的板形缺陷识别[J].新疆钢铁,2003,(2):17-18,22.
[93] DENIS A L, FRED M, CHRISTOPHE D, et al.Vision System for Defect Iimaging Detection and Characterization on a Specular Surface of a 3D Object[J].Image and Vision Computing,2002,20:569-580.
[94] LE J, GUO J J.A Fast Defect-detecting Method for Smooth Hemispherical Shell Surface[J].Opto-Electronic Engineering,2004, 31(10):32-35.
[95] ZHANG J, CAI L.Profilometry Using an Optical Stylus with Interferometric readout[J].Measurement Science & Technology,1997,8:546-549.
[96]苏显渝.三维面形测量技术的新进展[J].物理,1996,25(10):614-620.
[97] ZENG L J, HIROKAZU M.Two-directional Scanning Method for Reducing the Shadow Effects in Laser Triangulation[J].Measurement Science & Technology,1997,8:262-266.
[98] JENS W.Ceranics A Milestone on the Way to the High-performance Rolling Bearing[C].Ceramic Forum International,2002,79(4):21-24.
[99] WANG Y, HADFIELD M.Failure Modes of Ceramic Rolling Elements With Surface Crack Defects[J].Wear,2004,256(1):208-219.
[100]WANG L, SNIDLE R W, Gu L.Rolling Contact Silicon Nitride Bearing Technology:A Review of Recent Research[J].Wear,2000,246(11):159-173.
[101]郭红燕.新型精密轴承球超精密研磨加工系统仿真与设计优化[D].南京:南京航空航天大学(硕士学位论文),2006:55-72.
[102]龚曙光.ANSYS工程应用实例解析[M].北京:机械工业出版社,2003:32-40.