钢球表面缺陷检测关键技术研究及样机研制
|
摘要
轴承是机械基础部件,而钢球作为滚动球轴承的关键零件,其表面缺陷情况直接影响轴承精度、动态性能和使用寿命。因此,对钢球表面缺陷检测技术的研究是具有非常重要的理论和实用价值。本文对基于图像技术的钢球表面缺陷检测仪开发中的光源选择、展开机构动力学仿真分析、钢球表面缺陷的模式识别等关键技术问题进行了深入的研究,并搭建了能够实际应用的样机,其主要研究内容如下:
进行了检测系统的光源优化研究。从钢球表面反光特性的分析入手,研究了钢球表面成像的难点,建立了钢球表面的光反射模型。通过对大面积漫反射平板光源、漫反射扁平环形光源、漫反射球面光源和同轴光源等LED光源大量的理论和实验分析,最终确定了由FPR光源、LDR光源组合的检测机构照明方案。该光源方案,有效地解决了光晕现象、周围景物映入等问题,提高了钢球图像的质量和有效检测面积,为后期的图像处理奠定了基础。
运用UG与ADAMS联合建立了检测系统展开机构的模型并进行了运动学和动力学仿真,较为真实的仿真出钢球在展开盘检测腔中的实际运动轨迹、受力及碰撞情况。钢球与检测腔侧壁存在碰撞导致钢球产生回弹运动,通过优化展开腔的直径、阻尼特性、摩擦盘与展开盘转速、摩擦盘搓动速度等结构参数和运动参数,可以改变钢球的运动状态,从而保证钢球表面能完全展开和检测效率最高。
进行了钢球缺陷识别及分类关键技术研究。首先研究了钢球表面图像采集及降噪增强的图像预处理方法。将原始图片经过两次小波消噪处理消去高频白噪声,再经图像平滑处理使消噪后的图片平滑,然后设定灰度阈值运用Canny算子对图片进行边缘检测,最后对图片进行形态学处理以及图像锐化处理,为钢球缺陷的特征提取奠定了基础。确定将缺陷面积、缺陷长短径比、缺陷周长以及欧拉数等作为钢球表面缺陷识别的特征参数,并提出了一种基于BP神经网络的钢球表面缺陷类型识别方法。通过对采集到的钢球表面缺陷图像进行图像处理及特征提取,得到学习样本和预测样本,运用MATLAB软件对学习样本分析并确定合理的神经网络结构,从而精确的识别出预测样本中钢球表面缺陷的类型,通过大量实验分析,验证了该识别方法的准确性及可行性。
最后在上述研究基础上,确定了光源系统、展开系统、基于单片机控制的控制系统等检测仪关键部分的设计方案,搭建了可以实际应用的基于图像技术的钢球检测仪样机,通过实验验证了所获得研究结论的正确性。
Bearing is basic mechanical components, and steel balls as the key parts of rolling ball bearings while its surface defects directly affect the precision bearings, dynamic performance and service life. Therefore, there is a very important theoretical and practical significance to research surface defect detection. This article has developed source selection of detector, dynamic simulation of the expand sector, steel ball surface defect pattern recognition and others of key technical issues in-depth study, and it has built a prototype for practical applications. The main contents are as follows:
Optimization studies of source in detection system have been done. Starting from analyzing reflective properties of steel ball surface, it has built the reflective model of steel ball surface. Through a large number of theoretical and experimental analyses on large area flat diffuse light sources, flat circular diffuse light source, sphere diffuse light source and coaxial light source, the combination of FPR source and LDR source has been decided as lighting schemes for testing institution. The lighting program effectively solves the problems of halo phenomena, surrounding scenery greet and inverted image of camera and so on.
The results greatly improved steel ball image quality and effective detection area, which lay good foundation for the later period image processing. The deployment mechanism model of detection system has been established by combing UG and ADAMS, and kinematics and dynamics simulation are also done, simulating the actual trajectory、force and impact conditions of steel ball in expand plate detect cavity. The ball has springback movement due to collision with sidewall, the motion state of steel ball has changed because of optimization diameter of expand cavity、damping、speed of friction cavity and expand cavity、rubbing speed of friction cavity and other structural and movement parameters, thus the device ensure the steel surface can completely expand and ensure detection efficiency is highest.
The key technology of defect recognition and its classification is done. First image preprocessing method of enhancing image acquisition and noise reduction of steel ball surface are researched. The original images go through two times the handling to eliminate high frequency white noise. Second the image smooth the image after denoising, and then setting gray threshold using canny operator to images on edge of the inspection. Finally, morphological image processing and image enhancement processing are done, which lay a foundation for defect feature extraction of steel ball. Defect area、defect length-diameter ratio、defect circumference and Euler number are determined as characteristic parameter, and it has proposed a method of the steel ball surface defect based on BP neural network. Collected by the steel ball surface defect images for image processing and feature extraction, by studying samples and prediction samples, to learn to analysis sample using matlab software, and determine a reasonable neural network structure, to forecast accurately identify samples of the type of steel ball surface defect, through a lot of the experimental analysis, verify the accuracy of identifying ways and feasibility.
Finally, combining the problem of research results, the study determined the design of the key parts of detector such as the light sources of the system、the expand system and the control system based on SCM, and ball detector prototype based on image technology has been built, the correctness of research conclusions is verified through experiments.
进行了检测系统的光源优化研究。从钢球表面反光特性的分析入手,研究了钢球表面成像的难点,建立了钢球表面的光反射模型。通过对大面积漫反射平板光源、漫反射扁平环形光源、漫反射球面光源和同轴光源等LED光源大量的理论和实验分析,最终确定了由FPR光源、LDR光源组合的检测机构照明方案。该光源方案,有效地解决了光晕现象、周围景物映入等问题,提高了钢球图像的质量和有效检测面积,为后期的图像处理奠定了基础。
运用UG与ADAMS联合建立了检测系统展开机构的模型并进行了运动学和动力学仿真,较为真实的仿真出钢球在展开盘检测腔中的实际运动轨迹、受力及碰撞情况。钢球与检测腔侧壁存在碰撞导致钢球产生回弹运动,通过优化展开腔的直径、阻尼特性、摩擦盘与展开盘转速、摩擦盘搓动速度等结构参数和运动参数,可以改变钢球的运动状态,从而保证钢球表面能完全展开和检测效率最高。
进行了钢球缺陷识别及分类关键技术研究。首先研究了钢球表面图像采集及降噪增强的图像预处理方法。将原始图片经过两次小波消噪处理消去高频白噪声,再经图像平滑处理使消噪后的图片平滑,然后设定灰度阈值运用Canny算子对图片进行边缘检测,最后对图片进行形态学处理以及图像锐化处理,为钢球缺陷的特征提取奠定了基础。确定将缺陷面积、缺陷长短径比、缺陷周长以及欧拉数等作为钢球表面缺陷识别的特征参数,并提出了一种基于BP神经网络的钢球表面缺陷类型识别方法。通过对采集到的钢球表面缺陷图像进行图像处理及特征提取,得到学习样本和预测样本,运用MATLAB软件对学习样本分析并确定合理的神经网络结构,从而精确的识别出预测样本中钢球表面缺陷的类型,通过大量实验分析,验证了该识别方法的准确性及可行性。
最后在上述研究基础上,确定了光源系统、展开系统、基于单片机控制的控制系统等检测仪关键部分的设计方案,搭建了可以实际应用的基于图像技术的钢球检测仪样机,通过实验验证了所获得研究结论的正确性。
Bearing is basic mechanical components, and steel balls as the key parts of rolling ball bearings while its surface defects directly affect the precision bearings, dynamic performance and service life. Therefore, there is a very important theoretical and practical significance to research surface defect detection. This article has developed source selection of detector, dynamic simulation of the expand sector, steel ball surface defect pattern recognition and others of key technical issues in-depth study, and it has built a prototype for practical applications. The main contents are as follows:
Optimization studies of source in detection system have been done. Starting from analyzing reflective properties of steel ball surface, it has built the reflective model of steel ball surface. Through a large number of theoretical and experimental analyses on large area flat diffuse light sources, flat circular diffuse light source, sphere diffuse light source and coaxial light source, the combination of FPR source and LDR source has been decided as lighting schemes for testing institution. The lighting program effectively solves the problems of halo phenomena, surrounding scenery greet and inverted image of camera and so on.
The results greatly improved steel ball image quality and effective detection area, which lay good foundation for the later period image processing. The deployment mechanism model of detection system has been established by combing UG and ADAMS, and kinematics and dynamics simulation are also done, simulating the actual trajectory、force and impact conditions of steel ball in expand plate detect cavity. The ball has springback movement due to collision with sidewall, the motion state of steel ball has changed because of optimization diameter of expand cavity、damping、speed of friction cavity and expand cavity、rubbing speed of friction cavity and other structural and movement parameters, thus the device ensure the steel surface can completely expand and ensure detection efficiency is highest.
The key technology of defect recognition and its classification is done. First image preprocessing method of enhancing image acquisition and noise reduction of steel ball surface are researched. The original images go through two times the handling to eliminate high frequency white noise. Second the image smooth the image after denoising, and then setting gray threshold using canny operator to images on edge of the inspection. Finally, morphological image processing and image enhancement processing are done, which lay a foundation for defect feature extraction of steel ball. Defect area、defect length-diameter ratio、defect circumference and Euler number are determined as characteristic parameter, and it has proposed a method of the steel ball surface defect based on BP neural network. Collected by the steel ball surface defect images for image processing and feature extraction, by studying samples and prediction samples, to learn to analysis sample using matlab software, and determine a reasonable neural network structure, to forecast accurately identify samples of the type of steel ball surface defect, through a lot of the experimental analysis, verify the accuracy of identifying ways and feasibility.
Finally, combining the problem of research results, the study determined the design of the key parts of detector such as the light sources of the system、the expand system and the control system based on SCM, and ball detector prototype based on image technology has been built, the correctness of research conclusions is verified through experiments.
引文
[1]潘洪平.钢球表面缺陷的自动检测与识别[J].中国机械工程:2001,(4):369-372.
[2]李伊文.钢球表面缺陷的电脑显微观测[J].轴承:1998,(10):32-35.
[3]蒋沂萍.钢球抽检最佳方案的确定[J].轴承:2002,23(11):25-28.
[4]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.
[5]赵刚,王保义,马松轩.Aviko K型钢球外观检验机中子午线展开机构的理论分析[J].四川大学学报:1997,34(5):635-639.
[6]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:2005,10:63-65.
[7]王保振.国外钢球制造技术简介[J].轴承:1999,20(3):40-42.
[8]张葵摘.日本NSK新型滚动轴承浅析[J].轴承:2000,21(9):36-39.
[9] Technical Description and Instructions for Attendance of Automatic Sorting Machine for Defect-metric Inspection of Bearing Ball Surfaces[R]. Types AVIKO K-06140 E AND AVIKO-1418 E. Made in SOMET Ltd. of Czech.1985.
[10]潘洪平.钢球表面质量自动评价体系建立及其应用的研究[D].哈尔滨:哈尔滨工业大学(博士学位论文),2000:1-2.
[11]王鹏.基于运动视觉技术的钢球表面缺陷检测[D].哈尔滨:哈尔滨理工大学(博士学位论文),2008:1-2.
[12] A.N.Lioulios,I.A.Antoniadis.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.
[13]蔺勇智.钢球检测机构运动仿真与表面缺陷检测算法设计[D].哈尔滨:哈尔滨理工大学(硕士学位论文),2010:2-6.
[14]张艳萍.钢球表面缺陷涡流探伤仪分析[J].轴承:2007,28(2):32-33.
[15]徐长英.钢球表面检测系统的研究[J].测控技术:2007,26(9):85-87.
[16]徐淑琼,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):44-46.
[17]余婷.利用地磁场检测钢球表面裂纹的可行性研究[J].无损检测:2001,23(8):330-333.
[18]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:2002,(5):45-46.
[19]梁华,谢倩,梁林霞.钢球表面缺陷分析[J].轴承:2004,(2):23-24
[20] A Rong-qing.Research and Manufacture of the Instrument of Bearing Ball's Nondestructive Testing[J].AVIATION PRECISION MANUFACTURING TECHNOLOGY, 2005 ,4(41):52-54.
[21]赵彦玲,王洪运.基于UG的钢球子午线展开轮参数化设计[J].哈尔滨理工大学学报:2007,12(3):141-143.
[22]赵彦玲,顾玉武,刘献礼.基于小波变换的钢球图像边缘检测[J].哈尔滨理工大学学报:2007,12(5):32-34.
[23] Aloimonos J.Purposive and qualitative active vision[C].The 10th International Conference of Pattern Recognition, 1990:246-360.
[24]刘洋.运动视觉中目标的精确提取与跟踪技术[D].西安:西安电子科技大学(博士学位论文),2007:2-4.
[25]郑世友.动态场景图像序列中运动目标检测与跟踪[D].南京:东南大学(博士学位论文),2005:1-2.
[26]潘洪平.钢球表面质量评价系统用展开轮的理论研究[J].轴承:2007,(12):28-30.
[27]潘洪平,梁迎春,董申.钢球表面质量评价系统[J].轴承:2000,(7):30-35.
[28]李春颖.基于图像处理的钢球外观检测系统[J].轴承:2007(9):36-38.
[29] Eun -Jung Holden, Robyn Owens.Segmenting Occluded Objects Using a Motion Snake[C] .Asian Conference on Computer Vision(ACCV),2007:347-355.
[30]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),2005:35-37.
[31] Alexei A Efros, Alexander C Berg, Greg Mori, Jitendra Malik.Recognizing Action at a Distance[C].International Conference on Computer Vision(ICCV), 2007:587-596.
[32] Jorge Badenas, Jose Miguel Sanchiz, Filiberto Pla.Motion-based segmentation and regiontracking in image sequence [J].Pattern Recognition, 2001, 34 ( 3):661-670.
[33]侯志强.视觉跟踪技术综述[J].自动化学报:2006,32(4):603-617.
[34]赵彦玲.基于图像技术的钢球表面缺陷分析与识别[D].哈尔滨:哈尔滨理工大学(博士学位论文),2008:3-4.
[35]张玲,韩建.基于自适应模板的匹配算法在跟踪系统中的应用[J].重庆大学学报:自然科学版,2005,28(6):74-76.
[36]顾静良,张卫,万敏.基于自适应模板匹配的红外弱小目标检测[J].电子技术应用:2005,32(5):5-7.
[37]许波,李正明.一种新的基于自适应模板的相关跟踪算法[J].光学与光电技术:2004,2(4):62-64.
[38] L.N.De Castro,F.J.Von Zuben.The Clonal Selection Algorithm with Engineering Applications[C].Proceedings of GECCO'00 Workshop on Artificial Immune Systems and Their Applications,2000:36-37.
[39]于习晓,杨孔雨.免疫算法及其应用研究进展[J].哈尔滨工程大学学报:2007,7(27):331-335.
[40] Jang-Sung Chun, Hyun-Kyo Jung,Song-Yop Hahn.A Study on Comparison of Optimization Performances between Immune Algorithm and Other Heuristic Algorithms[J].Magnetic,1998,34(5):2972-2975.
[41]郭子龙,王孙安.三种泥沌免疫优化组合算法性能之比较研究[J].系统仿真学报:2005,(2):72-75.
[42] Shyh-Jier Huang.An immune-based Optimization Method to Capacitor Placement in a Radial Distribution System [J].IEEE Transactions on Power Delivery,2000,15(2):744-749.
[43]陈旭,宋爱国.蚂蚁算法与免疫算法结合求解TSP问题[J].传感技术学报:2006,19(2):504-507.
[44]钱淑渠,张著洪.动态多目标免疫优化算法及性能测试研究[J].智能系统学报:2007,2(5):68-77.
[45]张伟.基于视觉的运动车辆检测与跟踪[D].上海交通大学博士学位论文,2007:13-15.
[46]余建军,孙树栋.单纯形免疫算法及其在高维非凸函数优化中的应用[J].机械科学与技术:2007,(3):296-303.
[47]谢锋,沈军.一种基于snake模型的边缘轮廓提取的改进算法[J].湖南文理学院学报:自然科学版,2007,19(1):75-77.
[48]王宏曼,欧宗瑛.自由差分运算与直交型Snake模型[J].计算机辅助设计与图形图像学学报:2005,17(3):448-454.
[49] Kass M, Witkin A, Terzopoulos D.Snakes: active contour models[J].International Journal of Computer Vision. 1987, 1(4): 321-331P
[50] Kass M, Witkin A, Rives P. A New Approach to Visual Servoing in Robotics [J].IEEE Trans. Robotics and Automation, 1993, 8(3): 13-320.
[51]李谦,李庆鹏.改进的主动轮廓模型在脑肿瘤MRI图像轮廓提取中的应用[J].计算机与数字工程:2007,35(11):89-92.
[52]朱玉辉.一种基于蚁群算法的Snake模型与MRI分割[J].计算机应用与软件:2006,23(6):112-114.
[53]杨莉.图像特征检测与运动目标分割算法的研究和实现[D].西安:西安电子科技大学(博士学位论文),2007:42-44.
[54] Junwei Tian, Yongxuan Huang. A Variable-Step Detecting Algorithm for Interested Boundary[C]. Proceedings of the World Congress on Intelligent Control and Automation, 2006:2: 10166-10170.
[55]洪浩.蚁群优化算法及其应用研究[D].合肥:中国科学技术大学(博士学位论文),2006:2-6.
[56]李士勇,赵宝江一种蚁群聚类算法[J].计算机测量与控制:2007,15(11):1590-1596.
[57] Zhiqiang Wei, Xiaopeng Ji and Peng Wang.Real-time moving object detection for video monitoring systems [J].Journal of Systems Engineering and Electronics, 2006:17( 4):731-736.
[58]冯景华,吴南星,余冬玲.机械系统动态仿真技术及ADAMS的理论基础研究[J].机械设计与制造.2004.
[59]陈韶丽.用微机模拟弹性碰撞[J].华中师范大学学报(自然科学版). 2006:04-02.
[60]司尧华,崔纪超.库仑摩擦定律局限性探讨[P].河南机电高等专科学校学报. 2005:08-19.
[61]王永辉,陈晓丽,李博,刘义良,李玉高,杨秉新.空间展开机构初步原理分析与方案构想[J].航天返回与遥感. 2007:02-06.
[62]刘志全,培琪,张鹏顺.滚动轴承油膜厚度及运动参数的测试[J] .轴承. CNKISUNCUCW0.1996:08-011.
[63]涂二生,王清辉.带时序控制的实时多任务程序设计方法[P].龙岩学院学报. 2007:08-30.
[64] Chen Jiaqing. Analysis of Computational Methods of Contact Para-meters in Journal Bearing [J]. Journal of Beijing Institufe of Petroc-hemical Technology.CNKI:SUN:BJSY0. 1998:02-020.
[65]赵霞基.于正交试验方法进行小波消噪参数选择[J].西安文理学院学报,2008:04.
[66]张国栋,彭刚,王钊,朱暾. BP神经网络在单桩承载力预测中的应用[J].三峡大学学报(自然科学版),2007:07.
[67]韦春桃,程晓宇.LOG算子进行边缘检测的研究[J].桂林工学院学报,1999:05.
[68]丰艳,王明辉,陈一民.利用图像像素灰度值变化速度的相似性进行图像分割[J].计算机应用与软件,2007:05.
[69]王发牛.基于偏微分方程的图像平滑技术及其应用研究[J].安徽大学,2002:05.
[70]梅豪,梅杰.光电开关原理及应用[J].电子技术,1994:04.
[71]章锐,张磊,吴郁峰,朱喆,张征荣,朱燕青.一种单片机消磁器:中国,CN201237961.2009:09.
[72] Christian Micheloni and Gian Luca Foresti.Real-time image processing for active monitoring of wide areas [J].Journal of Visual Communication and Image Representation, 2006, 17(3):589-604.
[73]方菁.基于模糊神经网络直接转矩控制系统设计[J].机械工程学报:2010,14(2):19-23.
[74] Hartley R.Self calibration of stationary cameras.International Journal of Computer Vision[J].1997,22(1):5-23.
[75] Z Zhang.Camera calibration with dimensional objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(7):892-899.
[76]黄祯祥,吴俊.模糊神经网络在直接转矩控制系统速度调节器中的应用[J].矿山机械,2006,33(2):73~74.
[77] M.Sezgin,B.Sankur.Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation[J].Journal of Electronic Imaging,2004,13(1):146-165.
[78]赵汉卿,戚金清,王兢,征进,吴微.基于小波变换的双并联神经网络在混合气体浓度预测中的应用.传感技术学报. 2010,23(5): 744~747.
[79]王海川,张立明.一种新的Adaboost快速训练算法[J].复旦学报(自然科学版),2004,43(1):27-33.
[80]吴晓波,安文斗,杨钢.图像测量系统中的误差分析及提高测量精度的途径[J].光学精密工程:1997,5(1):133-141.
[81]孔明.颗粒粒径和形态计算机视觉测量方法研究[D].南京:东南大学(博士学位论文),2005:31-34.
[82]李为民.大尺度范围内视觉测量技术研究[D].合肥:中国科学技术大学(博士学位论文),2006:53-57.
[83]姜大志,郁倩,王冰洋,丁秋林,计算机视觉成像的非线性畸变研究与综述[J].计算机工程:2001,27(12):108-110.
[84]杜亚娟.基于不变矩理论的自动目标识别技术研究[D].西北工业大学博士学位论文,2000:3-5.
[85] R.Cucchiara, C.Crana, M.Piccardi, A. Prati,S .Sirotti. Improving Shadow Suppression in Moving Object Detection with HSV Color Iinformation[C].The Proc of IEEE International Conference on Intelligent Transportation Systems, 2001:334-339.
[86]田旭光,宋彤,刘宇新.结合遗传算法优化BP神经网络的结构和参数[J].计算机应用与软件, 2004, 21 (6) : 69~71.
[87]马义德,齐春亮,杜鸿飞.一种基于分类的改进BP神经网络图像的压缩方法[J].兰州大学学报:自然科学版, 2005, 41(4) : 70~72.
[88]金聪.前馈神经网络误差函数的结构形式[J].计算机研究与发展.2003 (7): 913~917.
[89] Y Wang. R. E. Van Dyck. J. F. Doherty.Tracking Moving Objects in Video Sequences[C]. Proc. Conference on Information Sciences and Svstems. Princeton, 2000:5.
[90]刘亚,艾海舟,徐光佑.基于主运动分析的野外视觉侦察系统—运动目标检测、跟踪及全景图的生成[J].机器人:2001,23(3):250-256.
[91] WANG Kai, WANG Qing2ren. Training and learning algorithms for neural networks2a margin maximization training algorithm for BP network [J]. Lecture Notes in Computer Science, 2007, 4492: 406-413.
[92] Park H W, Schoepflin T, Kim Y.Active Contour Models with Gradient Directional Information:Directional Snake[J].IEEE Transactions on Circuit and Systrnes for Videl Technology, 2001,11(2):252-254.
[93] DUFAUX F. KONRAD J.Efficient, robust, and fast global motion estimation for video coding [J]. IEEE Trans Image Processing, 2000, 9(3): 497-501.
[94]赵汉卿,戚金清,王兢,征进,吴微.基于小波变换的双并联神经网络在混合气体浓度预测中的应用.传感技术学报. 2010,23(5): 744~747.
[95] Q.Zang and R.Klette. Robust background subtraction and maintenance[C]. Proceedings of International Conference on Pattern Recognition(ICPR), 2004,(2):90-93.
[96] K-T-P.Pakorn and B.Richard.A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes[J].Image and Vision Computing, 2003,(21):913-929.
[97]高常青,黄克正,赵方.基于实例推理的原理及结构快速创新设计的研究与实现[J].中国机械工程,2007, 18 (24) : 2907-2913.
[98]凌卫青,赵艾萍,谢友柏.基于实例的产品设计知识获取方法及实现[J].计算机辅助设计与图形学学报, 2002, 14 (11) : 1014 - 1019.
[99]钟佩思,高国安.基于神经网络块的混合型方案设计知识库系统[ J ].机械设计, 1999, 16 (5) : 1-2.
[100]Tsai D M, Huang T Y. Automated surface inspection for statistical textures [J]. Image and Vision Computing, 2003, 21(4): 307-323.
[101]冯珊,熊然,郭四海.面向多学科虚拟样机的概念设计工具研究[J].武汉理工大学学报:信息与管理工程版, 2005, 27 (1): 1-5.
[102]杨明顺,罗时飞,林志航.概念设计方案评估中顾客满意度确定的一种方法[J].工程图学学报, 2003,24 (2) : 52 - 59.
[103] L iu J , Igoshi M, Arai E. Kinematic simulation using qualitative mechanism model[ J ]. American Society of Mechanical Engineers, 1995, 83 (2) : 679 - 686.
[104]孙守迁,黄琦,潘云鹤.计算机辅助概念设计研究进展[J].计算机辅助设计与图形学学报, 2003, 15
[2]李伊文.钢球表面缺陷的电脑显微观测[J].轴承:1998,(10):32-35.
[3]蒋沂萍.钢球抽检最佳方案的确定[J].轴承:2002,23(11):25-28.
[4]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.
[5]赵刚,王保义,马松轩.Aviko K型钢球外观检验机中子午线展开机构的理论分析[J].四川大学学报:1997,34(5):635-639.
[6]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:2005,10:63-65.
[7]王保振.国外钢球制造技术简介[J].轴承:1999,20(3):40-42.
[8]张葵摘.日本NSK新型滚动轴承浅析[J].轴承:2000,21(9):36-39.
[9] Technical Description and Instructions for Attendance of Automatic Sorting Machine for Defect-metric Inspection of Bearing Ball Surfaces[R]. Types AVIKO K-06140 E AND AVIKO-1418 E. Made in SOMET Ltd. of Czech.1985.
[10]潘洪平.钢球表面质量自动评价体系建立及其应用的研究[D].哈尔滨:哈尔滨工业大学(博士学位论文),2000:1-2.
[11]王鹏.基于运动视觉技术的钢球表面缺陷检测[D].哈尔滨:哈尔滨理工大学(博士学位论文),2008:1-2.
[12] A.N.Lioulios,I.A.Antoniadis.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.
[13]蔺勇智.钢球检测机构运动仿真与表面缺陷检测算法设计[D].哈尔滨:哈尔滨理工大学(硕士学位论文),2010:2-6.
[14]张艳萍.钢球表面缺陷涡流探伤仪分析[J].轴承:2007,28(2):32-33.
[15]徐长英.钢球表面检测系统的研究[J].测控技术:2007,26(9):85-87.
[16]徐淑琼,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):44-46.
[17]余婷.利用地磁场检测钢球表面裂纹的可行性研究[J].无损检测:2001,23(8):330-333.
[18]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:2002,(5):45-46.
[19]梁华,谢倩,梁林霞.钢球表面缺陷分析[J].轴承:2004,(2):23-24
[20] A Rong-qing.Research and Manufacture of the Instrument of Bearing Ball's Nondestructive Testing[J].AVIATION PRECISION MANUFACTURING TECHNOLOGY, 2005 ,4(41):52-54.
[21]赵彦玲,王洪运.基于UG的钢球子午线展开轮参数化设计[J].哈尔滨理工大学学报:2007,12(3):141-143.
[22]赵彦玲,顾玉武,刘献礼.基于小波变换的钢球图像边缘检测[J].哈尔滨理工大学学报:2007,12(5):32-34.
[23] Aloimonos J.Purposive and qualitative active vision[C].The 10th International Conference of Pattern Recognition, 1990:246-360.
[24]刘洋.运动视觉中目标的精确提取与跟踪技术[D].西安:西安电子科技大学(博士学位论文),2007:2-4.
[25]郑世友.动态场景图像序列中运动目标检测与跟踪[D].南京:东南大学(博士学位论文),2005:1-2.
[26]潘洪平.钢球表面质量评价系统用展开轮的理论研究[J].轴承:2007,(12):28-30.
[27]潘洪平,梁迎春,董申.钢球表面质量评价系统[J].轴承:2000,(7):30-35.
[28]李春颖.基于图像处理的钢球外观检测系统[J].轴承:2007(9):36-38.
[29] Eun -Jung Holden, Robyn Owens.Segmenting Occluded Objects Using a Motion Snake[C] .Asian Conference on Computer Vision(ACCV),2007:347-355.
[30]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),2005:35-37.
[31] Alexei A Efros, Alexander C Berg, Greg Mori, Jitendra Malik.Recognizing Action at a Distance[C].International Conference on Computer Vision(ICCV), 2007:587-596.
[32] Jorge Badenas, Jose Miguel Sanchiz, Filiberto Pla.Motion-based segmentation and regiontracking in image sequence [J].Pattern Recognition, 2001, 34 ( 3):661-670.
[33]侯志强.视觉跟踪技术综述[J].自动化学报:2006,32(4):603-617.
[34]赵彦玲.基于图像技术的钢球表面缺陷分析与识别[D].哈尔滨:哈尔滨理工大学(博士学位论文),2008:3-4.
[35]张玲,韩建.基于自适应模板的匹配算法在跟踪系统中的应用[J].重庆大学学报:自然科学版,2005,28(6):74-76.
[36]顾静良,张卫,万敏.基于自适应模板匹配的红外弱小目标检测[J].电子技术应用:2005,32(5):5-7.
[37]许波,李正明.一种新的基于自适应模板的相关跟踪算法[J].光学与光电技术:2004,2(4):62-64.
[38] L.N.De Castro,F.J.Von Zuben.The Clonal Selection Algorithm with Engineering Applications[C].Proceedings of GECCO'00 Workshop on Artificial Immune Systems and Their Applications,2000:36-37.
[39]于习晓,杨孔雨.免疫算法及其应用研究进展[J].哈尔滨工程大学学报:2007,7(27):331-335.
[40] Jang-Sung Chun, Hyun-Kyo Jung,Song-Yop Hahn.A Study on Comparison of Optimization Performances between Immune Algorithm and Other Heuristic Algorithms[J].Magnetic,1998,34(5):2972-2975.
[41]郭子龙,王孙安.三种泥沌免疫优化组合算法性能之比较研究[J].系统仿真学报:2005,(2):72-75.
[42] Shyh-Jier Huang.An immune-based Optimization Method to Capacitor Placement in a Radial Distribution System [J].IEEE Transactions on Power Delivery,2000,15(2):744-749.
[43]陈旭,宋爱国.蚂蚁算法与免疫算法结合求解TSP问题[J].传感技术学报:2006,19(2):504-507.
[44]钱淑渠,张著洪.动态多目标免疫优化算法及性能测试研究[J].智能系统学报:2007,2(5):68-77.
[45]张伟.基于视觉的运动车辆检测与跟踪[D].上海交通大学博士学位论文,2007:13-15.
[46]余建军,孙树栋.单纯形免疫算法及其在高维非凸函数优化中的应用[J].机械科学与技术:2007,(3):296-303.
[47]谢锋,沈军.一种基于snake模型的边缘轮廓提取的改进算法[J].湖南文理学院学报:自然科学版,2007,19(1):75-77.
[48]王宏曼,欧宗瑛.自由差分运算与直交型Snake模型[J].计算机辅助设计与图形图像学学报:2005,17(3):448-454.
[49] Kass M, Witkin A, Terzopoulos D.Snakes: active contour models[J].International Journal of Computer Vision. 1987, 1(4): 321-331P
[50] Kass M, Witkin A, Rives P. A New Approach to Visual Servoing in Robotics [J].IEEE Trans. Robotics and Automation, 1993, 8(3): 13-320.
[51]李谦,李庆鹏.改进的主动轮廓模型在脑肿瘤MRI图像轮廓提取中的应用[J].计算机与数字工程:2007,35(11):89-92.
[52]朱玉辉.一种基于蚁群算法的Snake模型与MRI分割[J].计算机应用与软件:2006,23(6):112-114.
[53]杨莉.图像特征检测与运动目标分割算法的研究和实现[D].西安:西安电子科技大学(博士学位论文),2007:42-44.
[54] Junwei Tian, Yongxuan Huang. A Variable-Step Detecting Algorithm for Interested Boundary[C]. Proceedings of the World Congress on Intelligent Control and Automation, 2006:2: 10166-10170.
[55]洪浩.蚁群优化算法及其应用研究[D].合肥:中国科学技术大学(博士学位论文),2006:2-6.
[56]李士勇,赵宝江一种蚁群聚类算法[J].计算机测量与控制:2007,15(11):1590-1596.
[57] Zhiqiang Wei, Xiaopeng Ji and Peng Wang.Real-time moving object detection for video monitoring systems [J].Journal of Systems Engineering and Electronics, 2006:17( 4):731-736.
[58]冯景华,吴南星,余冬玲.机械系统动态仿真技术及ADAMS的理论基础研究[J].机械设计与制造.2004.
[59]陈韶丽.用微机模拟弹性碰撞[J].华中师范大学学报(自然科学版). 2006:04-02.
[60]司尧华,崔纪超.库仑摩擦定律局限性探讨[P].河南机电高等专科学校学报. 2005:08-19.
[61]王永辉,陈晓丽,李博,刘义良,李玉高,杨秉新.空间展开机构初步原理分析与方案构想[J].航天返回与遥感. 2007:02-06.
[62]刘志全,培琪,张鹏顺.滚动轴承油膜厚度及运动参数的测试[J] .轴承. CNKISUNCUCW0.1996:08-011.
[63]涂二生,王清辉.带时序控制的实时多任务程序设计方法[P].龙岩学院学报. 2007:08-30.
[64] Chen Jiaqing. Analysis of Computational Methods of Contact Para-meters in Journal Bearing [J]. Journal of Beijing Institufe of Petroc-hemical Technology.CNKI:SUN:BJSY0. 1998:02-020.
[65]赵霞基.于正交试验方法进行小波消噪参数选择[J].西安文理学院学报,2008:04.
[66]张国栋,彭刚,王钊,朱暾. BP神经网络在单桩承载力预测中的应用[J].三峡大学学报(自然科学版),2007:07.
[67]韦春桃,程晓宇.LOG算子进行边缘检测的研究[J].桂林工学院学报,1999:05.
[68]丰艳,王明辉,陈一民.利用图像像素灰度值变化速度的相似性进行图像分割[J].计算机应用与软件,2007:05.
[69]王发牛.基于偏微分方程的图像平滑技术及其应用研究[J].安徽大学,2002:05.
[70]梅豪,梅杰.光电开关原理及应用[J].电子技术,1994:04.
[71]章锐,张磊,吴郁峰,朱喆,张征荣,朱燕青.一种单片机消磁器:中国,CN201237961.2009:09.
[72] Christian Micheloni and Gian Luca Foresti.Real-time image processing for active monitoring of wide areas [J].Journal of Visual Communication and Image Representation, 2006, 17(3):589-604.
[73]方菁.基于模糊神经网络直接转矩控制系统设计[J].机械工程学报:2010,14(2):19-23.
[74] Hartley R.Self calibration of stationary cameras.International Journal of Computer Vision[J].1997,22(1):5-23.
[75] Z Zhang.Camera calibration with dimensional objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(7):892-899.
[76]黄祯祥,吴俊.模糊神经网络在直接转矩控制系统速度调节器中的应用[J].矿山机械,2006,33(2):73~74.
[77] M.Sezgin,B.Sankur.Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation[J].Journal of Electronic Imaging,2004,13(1):146-165.
[78]赵汉卿,戚金清,王兢,征进,吴微.基于小波变换的双并联神经网络在混合气体浓度预测中的应用.传感技术学报. 2010,23(5): 744~747.
[79]王海川,张立明.一种新的Adaboost快速训练算法[J].复旦学报(自然科学版),2004,43(1):27-33.
[80]吴晓波,安文斗,杨钢.图像测量系统中的误差分析及提高测量精度的途径[J].光学精密工程:1997,5(1):133-141.
[81]孔明.颗粒粒径和形态计算机视觉测量方法研究[D].南京:东南大学(博士学位论文),2005:31-34.
[82]李为民.大尺度范围内视觉测量技术研究[D].合肥:中国科学技术大学(博士学位论文),2006:53-57.
[83]姜大志,郁倩,王冰洋,丁秋林,计算机视觉成像的非线性畸变研究与综述[J].计算机工程:2001,27(12):108-110.
[84]杜亚娟.基于不变矩理论的自动目标识别技术研究[D].西北工业大学博士学位论文,2000:3-5.
[85] R.Cucchiara, C.Crana, M.Piccardi, A. Prati,S .Sirotti. Improving Shadow Suppression in Moving Object Detection with HSV Color Iinformation[C].The Proc of IEEE International Conference on Intelligent Transportation Systems, 2001:334-339.
[86]田旭光,宋彤,刘宇新.结合遗传算法优化BP神经网络的结构和参数[J].计算机应用与软件, 2004, 21 (6) : 69~71.
[87]马义德,齐春亮,杜鸿飞.一种基于分类的改进BP神经网络图像的压缩方法[J].兰州大学学报:自然科学版, 2005, 41(4) : 70~72.
[88]金聪.前馈神经网络误差函数的结构形式[J].计算机研究与发展.2003 (7): 913~917.
[89] Y Wang. R. E. Van Dyck. J. F. Doherty.Tracking Moving Objects in Video Sequences[C]. Proc. Conference on Information Sciences and Svstems. Princeton, 2000:5.
[90]刘亚,艾海舟,徐光佑.基于主运动分析的野外视觉侦察系统—运动目标检测、跟踪及全景图的生成[J].机器人:2001,23(3):250-256.
[91] WANG Kai, WANG Qing2ren. Training and learning algorithms for neural networks2a margin maximization training algorithm for BP network [J]. Lecture Notes in Computer Science, 2007, 4492: 406-413.
[92] Park H W, Schoepflin T, Kim Y.Active Contour Models with Gradient Directional Information:Directional Snake[J].IEEE Transactions on Circuit and Systrnes for Videl Technology, 2001,11(2):252-254.
[93] DUFAUX F. KONRAD J.Efficient, robust, and fast global motion estimation for video coding [J]. IEEE Trans Image Processing, 2000, 9(3): 497-501.
[94]赵汉卿,戚金清,王兢,征进,吴微.基于小波变换的双并联神经网络在混合气体浓度预测中的应用.传感技术学报. 2010,23(5): 744~747.
[95] Q.Zang and R.Klette. Robust background subtraction and maintenance[C]. Proceedings of International Conference on Pattern Recognition(ICPR), 2004,(2):90-93.
[96] K-T-P.Pakorn and B.Richard.A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes[J].Image and Vision Computing, 2003,(21):913-929.
[97]高常青,黄克正,赵方.基于实例推理的原理及结构快速创新设计的研究与实现[J].中国机械工程,2007, 18 (24) : 2907-2913.
[98]凌卫青,赵艾萍,谢友柏.基于实例的产品设计知识获取方法及实现[J].计算机辅助设计与图形学学报, 2002, 14 (11) : 1014 - 1019.
[99]钟佩思,高国安.基于神经网络块的混合型方案设计知识库系统[ J ].机械设计, 1999, 16 (5) : 1-2.
[100]Tsai D M, Huang T Y. Automated surface inspection for statistical textures [J]. Image and Vision Computing, 2003, 21(4): 307-323.
[101]冯珊,熊然,郭四海.面向多学科虚拟样机的概念设计工具研究[J].武汉理工大学学报:信息与管理工程版, 2005, 27 (1): 1-5.
[102]杨明顺,罗时飞,林志航.概念设计方案评估中顾客满意度确定的一种方法[J].工程图学学报, 2003,24 (2) : 52 - 59.
[103] L iu J , Igoshi M, Arai E. Kinematic simulation using qualitative mechanism model[ J ]. American Society of Mechanical Engineers, 1995, 83 (2) : 679 - 686.
[104]孙守迁,黄琦,潘云鹤.计算机辅助概念设计研究进展[J].计算机辅助设计与图形学学报, 2003, 15