基于显微视觉的刀具磨损状态监测技术研究
|
摘要
刀具磨损状态监测技术是实现现代生产自动化、智能化的一项重要技术。本文结合显微视觉对刀具磨损监测关键技术：显微自动聚焦技术、刀具磨损区域分割技术与工件纹理分析技术进行了深入研究与探讨，为实现刀具磨损监测系统实用化奠定了基础。
本文的主要创新性工作如下：
⑴针对强噪声环境下传统聚焦评价函数无法满足需要的状况，提出了一种改进的聚焦评价函数处理方式，即对图像采用预处理后，利用分水岭技术把图像分成区域块，并以区域块灰度均值代替此区域内像素灰度值，以此降低噪声对聚焦评价函数的影响，实验验证了此处理方式的有效性。
⑵针对传统焦平面搜索算法存在误判及实时性较差的问题，提出了一种改进自适应步长搜索爬山法，此搜索算法设置两个阈值，根据相邻位置的斜率与两阈值及局部极值因子间的关系，确定搜索步长值，步长分为小步距、中步距与大步距三种情况，在确定步长值时，考虑了陡峭区宽度因子，因此这种自适应步长搜索算法既可以降低把局部极值位置作为焦平面位置的情况，又可降低在大步距搜索时，越过焦平面位置的情况，同时降低了计算量，提高了系统实时性。
⑶针对传统马尔可夫随机场在刀具磨损区域分割时计算量大且对噪声敏感的问题，提出了一种自适应区域马尔可夫随机场分割算法。此算法利用分水岭技术把预处理图像分割成区域块，利用区域块均值与方差作为特征参数，参与图像初分割；势函数连接参数根据当前区域块与其相邻区域块的连接紧密程度自适应地确定其数值，自适应连接参数符合图像分割机理，实验验证此算法应用于刀具磨损区域分割时，提高了边界分割的精确性与鲁棒性。
⑷针对低对比度图像采用传统阈值分割算法分割效果欠佳的状况，提出了一种像素邻域灰度共生矩阵分割算法，此算法利用像素点灰度值与其邻域灰度加权平均值构造共生矩阵，进而确定图像分割阈值；生成步长值是构造共生矩阵的一个关键参数，提出利用不同步长值分别构造共生矩阵，并对这些共生矩阵特征参数进行仿真，特征参数仿真曲线第一周期极值位置所对应的步长值即为最佳生成步长值，实验验证，利用最佳生成步长值构造的共生矩阵，利于刀具磨损程度的判断。
⑸为了提高刀具磨损状态监测的准确性与稳定性，综合利用刀具磨损值与工件纹理特征参数对刀具磨损程度进行监测，较单一判据相比，其准确性与稳定性较高。
Tool wear monitoring technique is important to realize automation and intelligent ofmodern production. The key techniques of tool wear monitoring based on micro-vision aredeep researched and discussed. The key techniques include microscope autofocus, thesegmentation of tool wear area and the analysis of workpiece texture which are deepresearched. The research provides a base to realize the system of tool wear monitoringpractically.
The major innovations of this paper are as follows:
(1) Aiming at an image with strong noise environment, the traditional focus evaluationfunction can not satisfy the focus need. An improved processing of focus evaluationfunction is provided. The image is preprocessed firstly. Then this image is over-segmentedinto many blocks with watershed technique.The gray values of pixels in a certain block arereplaced by the mean gray of this block which can reduce the noise influence on focusevaluation function. The experimental results indicate the availability and practicability ofthis algorithm.
(2) Aiming at the misjudgment and poor real-time of the traditional searchingalgorithm, an improved hill climbing method with adaptive-step is proposed. Twothresholds are set in this search algorithm. The value of search step is dependent on therelationship among the slope of adjacent positions, the two thresholds and the factor oflocal extreme. The step value is divided into three conditions, large step, medium step andsmall step. This searching algorithm can not only reduce the situation that the local extremeposition viewed as the focal plane but also can reduce the situation of the focal planemissed when searching with large step. This algorithm has lower computation and betterreal-time performance.
(3) The traditional Markov random field has huge computation and is sensitive tonoise when used for the segmentation of tool wear area. A new algorithm of self-adaptiveMarkov random field based on region is proposed. The preprocessed image is divided intoblocks with watershed technique. The mean gray and variance of regional block are viewedas feature parameters for initial segmentation. The connection parameter of potentialfunction is determined adaptively in terms of the close connection degree between the current block and its adjacent block. It satisfies the mechanism of image segmentation. Thisalgorithm is more accurate for the edge segmentation of tool wear area. Throughexperiments, accuracy and robustness are improved.
(4) In view of the low contrast images, the traditional threshold segmentationalgorithm has performance, so an improved segmentation technology of gray levelco-occurrence matrix is proposed. The improved gray level co-occurrence matrix isconstructed by the pixel value and weighted average value of its neighborhood. Then thethreshold is obtained by this improved gray level co-occurrence matrix. The generating stepvalue is a key parameter to construct gray level co-occurrence matrix. The featureparameters of co-occurrence matrix are simulated with different steps. The extreme positionof simulation curve in the first cycle is the best step value. Experiments show that the beststep value is better for the analysis of tool wear.
(5) In order to improve the accuracy and robustness of tool wear monitoring, the valueof tool wear area and the feature parameter of worpiece texture are comprehensivelyutilized. Compared with single criterion, this method has higher accurate and robust.
本文的主要创新性工作如下：
⑴针对强噪声环境下传统聚焦评价函数无法满足需要的状况，提出了一种改进的聚焦评价函数处理方式，即对图像采用预处理后，利用分水岭技术把图像分成区域块，并以区域块灰度均值代替此区域内像素灰度值，以此降低噪声对聚焦评价函数的影响，实验验证了此处理方式的有效性。
⑵针对传统焦平面搜索算法存在误判及实时性较差的问题，提出了一种改进自适应步长搜索爬山法，此搜索算法设置两个阈值，根据相邻位置的斜率与两阈值及局部极值因子间的关系，确定搜索步长值，步长分为小步距、中步距与大步距三种情况，在确定步长值时，考虑了陡峭区宽度因子，因此这种自适应步长搜索算法既可以降低把局部极值位置作为焦平面位置的情况，又可降低在大步距搜索时，越过焦平面位置的情况，同时降低了计算量，提高了系统实时性。
⑶针对传统马尔可夫随机场在刀具磨损区域分割时计算量大且对噪声敏感的问题，提出了一种自适应区域马尔可夫随机场分割算法。此算法利用分水岭技术把预处理图像分割成区域块，利用区域块均值与方差作为特征参数，参与图像初分割；势函数连接参数根据当前区域块与其相邻区域块的连接紧密程度自适应地确定其数值，自适应连接参数符合图像分割机理，实验验证此算法应用于刀具磨损区域分割时，提高了边界分割的精确性与鲁棒性。
⑷针对低对比度图像采用传统阈值分割算法分割效果欠佳的状况，提出了一种像素邻域灰度共生矩阵分割算法，此算法利用像素点灰度值与其邻域灰度加权平均值构造共生矩阵，进而确定图像分割阈值；生成步长值是构造共生矩阵的一个关键参数，提出利用不同步长值分别构造共生矩阵，并对这些共生矩阵特征参数进行仿真，特征参数仿真曲线第一周期极值位置所对应的步长值即为最佳生成步长值，实验验证，利用最佳生成步长值构造的共生矩阵，利于刀具磨损程度的判断。
⑸为了提高刀具磨损状态监测的准确性与稳定性，综合利用刀具磨损值与工件纹理特征参数对刀具磨损程度进行监测，较单一判据相比，其准确性与稳定性较高。
Tool wear monitoring technique is important to realize automation and intelligent ofmodern production. The key techniques of tool wear monitoring based on micro-vision aredeep researched and discussed. The key techniques include microscope autofocus, thesegmentation of tool wear area and the analysis of workpiece texture which are deepresearched. The research provides a base to realize the system of tool wear monitoringpractically.
The major innovations of this paper are as follows:
(1) Aiming at an image with strong noise environment, the traditional focus evaluationfunction can not satisfy the focus need. An improved processing of focus evaluationfunction is provided. The image is preprocessed firstly. Then this image is over-segmentedinto many blocks with watershed technique.The gray values of pixels in a certain block arereplaced by the mean gray of this block which can reduce the noise influence on focusevaluation function. The experimental results indicate the availability and practicability ofthis algorithm.
(2) Aiming at the misjudgment and poor real-time of the traditional searchingalgorithm, an improved hill climbing method with adaptive-step is proposed. Twothresholds are set in this search algorithm. The value of search step is dependent on therelationship among the slope of adjacent positions, the two thresholds and the factor oflocal extreme. The step value is divided into three conditions, large step, medium step andsmall step. This searching algorithm can not only reduce the situation that the local extremeposition viewed as the focal plane but also can reduce the situation of the focal planemissed when searching with large step. This algorithm has lower computation and betterreal-time performance.
(3) The traditional Markov random field has huge computation and is sensitive tonoise when used for the segmentation of tool wear area. A new algorithm of self-adaptiveMarkov random field based on region is proposed. The preprocessed image is divided intoblocks with watershed technique. The mean gray and variance of regional block are viewedas feature parameters for initial segmentation. The connection parameter of potentialfunction is determined adaptively in terms of the close connection degree between the current block and its adjacent block. It satisfies the mechanism of image segmentation. Thisalgorithm is more accurate for the edge segmentation of tool wear area. Throughexperiments, accuracy and robustness are improved.
(4) In view of the low contrast images, the traditional threshold segmentationalgorithm has performance, so an improved segmentation technology of gray levelco-occurrence matrix is proposed. The improved gray level co-occurrence matrix isconstructed by the pixel value and weighted average value of its neighborhood. Then thethreshold is obtained by this improved gray level co-occurrence matrix. The generating stepvalue is a key parameter to construct gray level co-occurrence matrix. The featureparameters of co-occurrence matrix are simulated with different steps. The extreme positionof simulation curve in the first cycle is the best step value. Experiments show that the beststep value is better for the analysis of tool wear.
(5) In order to improve the accuracy and robustness of tool wear monitoring, the valueof tool wear area and the feature parameter of worpiece texture are comprehensivelyutilized. Compared with single criterion, this method has higher accurate and robust.
引文
[1]申志刚.高速切削刀具磨损状态的智能监测技术研究[D].南京航空航天大学博士论文,2009.
[2] B. Dhanasekar, B. Ramamoorthy. Restoration of blurred images for surface roughness evaluationusing machine vision[J]. Tribology International,2010,43:268-276
[3] Ghassan A. Al-Kindi, Bijan Shirinzadeh. Feasibility assessment of vision-based surface roughnessparameters acquisition for different types of machined specimens[J]. Image and VisionComputing,2009,27:444-458
[4] A. Devillez, S. Lesko, W. Mozer. Cutting tool crater wear measurement with white lightinterferometry[J].wear,2004,256:56-65
[5] Rajneesh Kumar, P. Kulashekar, B. Dhanasekar. Application of digital image magnification forsurface roughness evaluation using machine vision[J]. International Journal of Machine Tools&Manufacture,2005,45:228–234
[6]熊四昌.基于计算机视觉的刀具磨损状态监测技术的研究[D].浙江大学博士论文,2003.
[7] B.Y. Lee, S.F. Yu, H. Juan. The model of surface roughness inspection by vision system in turning[J].Mechatronics,2004,14:129-141
[8] S. Dutta, A. Datta, N. Das Chakladar,et al. Detection of tool condition from the turned surface imagesusing an accurate grey level co-occurrence technique[J]. Precision Engineering,2012,36:458-466
[9] M. Castejon, E. Alegre, J. Barreiro, et al. On-line tool wear monitoring using geometric descriptorsfrom digital images[J]. International Journal of Machine Tools&Manufacture,2007,47:1847-1853.
[10] Zhen Liu, Junhua Sun, Heng Wang. Simple and fast rail wear measurement method based onstructured light[J]. Optics and Lasers in Engineering,2011,49:1343-1351
[11] T.Y. Lim, M.M. Ratnam. Edge detection and measurement of nose radii of cutting tool inserts fromscanned2-D images[J]. Optics and Lasers in Engineering,2011,49:1259-1267.
[12] W. Wang, Y.S. Wong, G.S. Hong. Flank wear measurement by successive image analysis[J].Computers in Industry,2005,56:816–830
[13] M.A. Mannan, Ashraf A. Kassim, Ma Jing. Application of image and sound analysis techniques tomonitor the condition of cutting tools[J]. Pattern Recognition Letters,2000,21:969-979
[14] Dimla D E, Lister P M, Leighton N J. Neural network solutions to the tool condition monitoringproblem in metal cutting: a critical review of methods[J]. International journal of machine tools&manufacture,1997,37:1219-1241.
[15] M.Sortino. Application of statistical filtering for optical detection of tool wear[J]. InternationalJournal of Machine Tools&Manufacture,2003,43:493–497
[16] Ghassan A. Al-Kindi, Bijan Shirinzadeh. An evaluation of surface roughness parametersmeasurement using vision-based data[J]. International Journal of Machine Tools&Manufacture,2007,47:697–708
[17] Jeon-Ha Kim, Deok-Kyu Moon,Deuk-Woo Lee, et al. Tool wear measuring technique on themachine using CCD and exclusive jig[J]. Journal of Materials Processing Technology,2002,668-674
[18] Yu Zuyuan, Ma Chunshi, An Chengming, et al. Prediction of tool wear in micro USM[J]. CIRPAnnals-Manufacturing Technology,2012,61:227-230.
[19] Chang Dar-Yuan, Lin Shu-Yi. Tool Wear, Hole Characteristics, and Manufacturing Tolerance inAlumina Ceramic Microdrilling Process[J]. Materials and Manufacturing Processes,2012,27(3):306-313
[20] A.R. Zareena, S.C. Veldhuis. Tool wear mechanisms and tool life enhancement in ultra-precisionmachining of titanium[J]. Journal of Materials Processing Technology,2012,212:560-570.
[21] T.J. Ko, D.W. Cho,Y. Jung. On-Line Monitoring of Tool Breakage in Face Milling Using aSelf-Organized Neural Network[J]. Journal of Manufacturing Systems,1995,14(2):80-90.
[22] W.H. Wang,G.S. Hong, Y.S. Wong. Flank wear measurement by a threshold independent methodwith sub-pixel accuracy[J]. International Journal of Machine Tools&Manufacture,2006,46:199-207.
[23] Won-sik Kim.A New Methodology for Predictive Tool Wear[D]. Michigan State University Doctorpaper,2001
[24] Bennett desfosses. An improved power threshold method for estimating tool wear during milling[D].University of New Hampshire master paper,2007.5
[25] Cui Yanjun. Tool Wear Monitoring For Milling by Trackiing Cutting Force ModelCoefficients[D].University of New Hampshire master paper,2008.12
[26] Huseyin M.Ertunc. Techniques for tool wear condition monitoring in drilling operations[D].CaseWestern Reserve University Doctor paper,1999.8
[27] Ya-Tsun Hslao. In-process evaluation of tool wear effects on surface roughness variation in hardturning[D]. University of Missouri-Columbia Doctor paper,1998.7
[28] Sultan Binsaeid,Shihab Asfour,Sohyung Cho,et al. Machine ensemble approach for simultaneousdetection of transient and gradual abnormalities in end milling using multisensor fusion[J]. Journal ofMaterials Processing Technology,2009,209:4728–4738
[29] Nidal H, Abu-Zahra, Gang Yu. Analytical model for tool wear monitoring in turning operationsusing ultrasound waves[J]. International Journal of Machine Tools&Manufacture,2000,40:1619–1635.
[30] M.Kious, A.Ouahabi,M.Boudraa. Detection process approach of tool wear in high speed milling[J].Measurement,2010,43:1439-1446.
[31] Bovic Kilundu,Pierre Dehombreux,Xavier Chiementin. Tool wear monitoring by machine learningtechniques and singular spectrum analysis[J]. Mechanical Systems and Signal Processing.2011,25:400-415.
[32] Francois Girardin，Didier Remond，Jean-Francois Rigal. Tool wear detection in milling--Anoriginal approach with a non-dedicated sensor[J]. Mechanical Systems and Signal Processing,2010,24:1907–1920
[33] J.A.Ghani, M.Rizal, M.Z.Nuawi, et al. Monitoring online cutting tool wear using low-costtechnique and user-friendly GUI[J]. Wear,2011,271:2619–2624.
[34] Ibrahim N,Tansel,Benjamin L,et al. Wear estimation by testing the elastic behavior of tool surface[J].International Journal of Machine Tools&Manufacture,2011,51:745–752
[35] Xiaoli Li,Alexandar Djordjevich,Patri K,et al. Current-Sensor-Based Feed Cutting Force IntelligentEstimation and Tool Wear Condition Monitoring[J]. IEEE Transactions on industrial electronics,2000,47(3):697-702.
[36]张翔.小型五轴联动机床介观尺寸铣削加工及其相关模型的研究[D]，哈尔滨工业大学博士论文，2011.6
[37] Shan Guan,Long-shan Wang. Study on Identification Method of Tool Wear Based on Feature Fusionand Least Squares Support Vector Machine[C].20103rd International Congress on Image and SignalProcessing,2010:3044-3048.
[38] Xihui Liu,Chen Zhang,Jiwen Fang,et al. A New Method of Tool Wear Measurement[C].2010International Conference on Electrical and Control Engineering,2010:2606-2609.
[39]范依航.高效切削钛合金Ti6Al4V刀具磨损特性及切削性能研究[D]，哈尔滨理工大学博士论文，2011.6
[40]刘路，王太勇，蒋永翔.基于超球面支持向量机的刀具磨损状态识别农业机械学报[J]，2011,42(1):218-222
[41]申志刚.高速切削刀具磨损状态的智能监测技术研究[J],南京航空航天大学博士学位论文,2009,11
[42]申志刚,何宁,李亮.高速硬铣削加工刀具磨损监测研究[J].中国机械工程,2009,20(13):1582-1586
[43]蒲宇亭.基于小波分析的高速CNC集成制造工况健康监控技术研究[D]，河北工业大学硕士论文，2010.11
[44]李敏.基于粒子群优化神经网络的刀具磨损状态监测技术研究[D]，西南交通大学硕士论文，2012.5
[45]谢秀娴,付攀,曹伟青.声发射和小波包分解技术在刀具磨损状态中的应用[J].中国测试技术,2006,32(2):40-42
[46]张宗阳.基于最小表面磨损率的刀具磨损及加工表面层特性研究[D]，山东大学博士论文，2012.4
[47]张宗阳,艾兴,刘战强.高效切削铁基高温合金刀具磨损特性研究[J],制造业自动化，2011,33(10):48-52
[48]邵强.切削加工过程中颤振的监测与识别方法研究[D]，大连理工大学博士论文，2010.3
[49]王利伟，王姣.云-SVM模型及在数控机床刀具磨损状态预测中的应用[J].组合机床与自动化加工技术,2012,9:25-31
[50]李斌、丁玉发、刘红奇.小波包分析技术在电流刀具磨损监测系统中的应用[J].心智与计算,2010,4(4):258-264
[51]李斌,张琛,刘红奇.基于主轴电流的铣削力间接测量方法研究[J].华中科技大学学报(自然科学版),2008,36(3):5-11
[52]李鹏阳,郝重阳,祝双武.基于图像连通区域数的刀具磨损状态特征提取实验研究[J].中国图象图形学报,2008,13(8):1476-1480
[53] T. Pfeifer, L. Wiegers.Reliable tool wear monitoring by optimized image and illumination control inmachine vision[J], Measurement,2000,28:209–218
[54] M.Lanzetta.A new flexible high-resolution vision sensor for tool condition monitoring[J]. Journal ofMaterial Processing Technology,2001,119:73-82.
[55] J.Barreiro,M.Castejon, E.Alegre,et al. Use of descriptors based on moments from digital images fortool wear monitoring[J]. International Journal of Machine Tools&Manufacture,2008,48:1005-1013.
[56] J.Jurkovic, M.Korosec,J.Kopac. New approach in tool wear measuring technique using CCD visionsystem[J]. International Journal of Machine Tools&Manufacture,2005,45:1023–1030.
[57] Yongjin Kwon, Gary W.Fischer. A novel approach to quantifying tool wear and tool lifemeasurements for optimal tool management[J]. International Journal of Machine Tools&Manufacture,2003,43:359–368.
[58] A.A.Kassim，M.A.Mannan，Zhu Mian. Texture analysis methods for tool condition monitoring[J].Image and Vision Computing,2007,25:1080–1090
[59] H.Kashiwagi,Y.Nagayama,K.Shibuta. Estimation of Tool Wear by use of Image Processing ofCutting Dust[C]. SICE Annual Conference in Fukui,2003:1723-1726.
[60] Svetlana Antoshchuk, Alexandr Derevianchenko, Elena Tkachenko.The Hierarchical ObjectsAnalysis on Images of Cutting Tool Wear Zones[C]. TCSET,2006:253-255.
[61] Yu-Teng Liang,Yih-Chih Chiou. Vision-Based Automatic Tool Wear Monitoring System[C].Proceedings of the7th World Congress on Intelligent Control and Automation,2008:6031-6035.
[62] T.Kalaichelvi,Dr.P.Rangarajan. Automated Intelligent Machine Vision System for Monitoring theImage[C].2010International Conference on Signal and Image Processing,2010:462-466.
[63] A. Karthik, S. Chandra, B. Ramamoorthy,et al.3D tool wear measurement and visualization usingstereo imaging[J].2009,37(11):1573-1581.
[64] J.C. Su, C.K. Huang, Y.S. Tarng. An automated flank wear measurement of microdrills usingmachine vision[J]. Journal of Materials Processing Technology,2006,180:328–335
[65] Liao Yi, Stephenson, David A.,et al. A multifeature approach to tool wear estimation using3Dworkpiece surface texture parameters[J]. Journal of Manufacturing Science and Engineering,Transactions of the ASME,2010,132(6):0610081-0610087
[66] Li Pengyang, Li Yan,Yang Mingshun. Monitoring Technology Research of Tool Wear ConditionBased on Machine Vision[C]. Proceedings of the7th World Congress on Intelligent Control andAutomation,2008,6:2783-2787.
[67]王阳俊. SiCp/Al复合材料高速铣削表面质量及刀具磨损研究[D]，哈尔滨工业大学博士学位论文，2012.1
[68]朱孔凤.自动聚焦区域选择算法[J].安徽大学学报(自然科学版),2009,33(2):31-34.
[69]王彦芳.自动聚焦系统中评价函数性能与动态区域选取的研究[D].山东大学硕士论文,2011.4
[70]张乐,姜威,高赞.数字图像一阶矩的自动聚焦区域选择算法[J]，光学技术，2008,34(2):163-169.
[71]翟永平,周东翔,刘云辉等.聚焦函数性能评价指标设计及最优函数选取[J].光学学报，2011,31(4)：0418002-1-0418002-11。
[72]宗光华,孙明磊,毕树生等.显微视觉自动聚焦研究[J].光学学报,2005,25(9):1225-1232
[73] Chen Chih-Yung, Hwang Rey-Chue, Chen Yu-Ju. A passive auto-focus camera control system[J].Applied Soft Computing,2010,10:296-303.
[74]朱铮涛,黎绍发,陈华平.基于图像熵的自动聚焦函数研究[J].光学精密工程,2004,12(5):537-542.
[75]周贤.自动聚焦算法研究与验证平台设计[D].山东大学硕士学位论文,2006.4
[76]卢振华.扫描式遥感相机基于图像的实时自动调焦研究[D]，中国科学院博士论文,2012.5
[77]李旭超,朱善安.图像分割中的马尔可夫随机场方法综述[J].中国图象图形学报,2007,12(5):789-798.
[78]陈华杰,吴香伟.强噪声背景下基于非网格MRF的SAR图像快速分割方法[J].光电工程，2010,37(12):75-82
[79]宋晓峰,王爽,刘芳.基于区域MRF和贝叶斯置信传播的SAR图像分割[J].电子学报,2010,38(12):2810-2815
[80]张印辉.多尺度马可夫随机场图像分割方法研究[D].昆明理工大学博士论文,2010
[81] Besag J. Spatial interaction and the statistical analysis of lattice systems[J]. Journal of the RoyalStatistical Society,1974,36(2):192-236
[82]柏柯嘉,刘伟铭.模糊马尔可夫随机场理论在阴影检测中的应用[J].中国图象图形学报,2010,15(3):409-416
[83]刘峰,龚健雅.一种结合能量最小和马尔可夫随机场的图像分割方法[J].地理与地理信息科学,2011,27(2):38-40
[84]齐美彬,杨立宾,蒋建国.自适应权值的MRF分割与跟踪方法[J].中国图象图形学报,2011,16(4):572-578
[85] Haralick R M. Statistical and structural approaches to texture[J].Proceedings of theIEEE,1979,67(5):786-804.
[86] Haralick R M,Shanmugam K,Dinstein I. Textural feature for image classification[J]. IEEETransaction on Systems, Man and Cybemetics Part A,1973,3(6):610-612.
[87] Ahuja N, Rosenfeld A. A note on the use of second-order graylevel statistics for threshold selection[J]. IEEE Trans SMC,1978,8(12):859-898.
[88] Weszka J S,Rosenfeld A.Threshold evaluation technique[J].IEEE Trans SMC,1978,8(7):622-629.
[89]范九伦,任静.基于平方距离的对称共生矩阵阈值法[J]，电子学报，2011,39(10):2277-2281.
[90]李伯宇.图像纹理分析及分类方法研究[D].复旦大学博士论文,2007
[91]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-630
[92] Ojala T,Pietikainen M.Unsupervised texture segmentation using feature distributions[J].PatternRecognition,1999,32(2):477-486
[93] Ojala T,Pietikainen M.Multiresolution gray-scale and rotation invariant texture classification withlocal binary Patterns[J].IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(17):971-987.
[94] Tang Y Y,Tao Y,Lam E C M.New method for feature extraction based on fractal behavior[J].PatternRecognition Letters,2002,35(5):1071-1081
[95]陈美龙,戴声奎.基于GLCM算法的图像纹理特征分析[J].通信技术,2012,45(2):108-111
[96] Ulaby FT, Kouyate F, Brisco B, et al. Textural information in SAR Images[J]. IEEE Transactions onGeoscience and Remote Sensing,1986,24(2):235-245.
[97] Pearson K. on lins and planes of elosest fit to systems of points in spaee[J]. PhilosophicalMagazine,1901:559-572.
[98] Samik Dutta,Arpan Das,Kaustav Barat,Himadri Roy. Automatic characterization of fracturesurfaces of AISI304LN stainless steel using image texture analysis[J],Measurement,2012,45:1140-1150
[99] Ulaby FT, Kouyate F, Brisco B, et al. Textural information in SAR Images[J]. IEEE Transactions onGeoscience and Remote Sensing,1986,24(2):235-245
[100]王辉.基于灰度共生矩阵木材表面纹理模式识别方法的研究[D].东北林业大学硕士论文,2007.6
[101] Mousumi Gupta,Debasish Bhaskar,Rabindranath Bera,et al. Target detection of ISAR data byprincipal component transform on co-occurrence matrix[J]. Pattern Recognition Letters,2012,33:1682-1688.
[102]熊四昌,计时鸣,樊炜.基于马尔可夫随机场工件表面纹理模型的刀具状态监测[J].中国机械工程,2004,15(8):678-680
[103] Haindl, M., Simberova, S.. Theory&Applications of Image Analysis: A Multispectral Image LineReconstruction Method[M]. Singapore: World Scientific Publishing Co.,1992,306–315.
[104] Pavel Vacha,Michal Haindl, Tomas Suk. Colour and rotation invariant textural features based onMarkov random fields[J]. Pattern Recognition Letters,2011,32:771-779
[2] B. Dhanasekar, B. Ramamoorthy. Restoration of blurred images for surface roughness evaluationusing machine vision[J]. Tribology International,2010,43:268-276
[3] Ghassan A. Al-Kindi, Bijan Shirinzadeh. Feasibility assessment of vision-based surface roughnessparameters acquisition for different types of machined specimens[J]. Image and VisionComputing,2009,27:444-458
[4] A. Devillez, S. Lesko, W. Mozer. Cutting tool crater wear measurement with white lightinterferometry[J].wear,2004,256:56-65
[5] Rajneesh Kumar, P. Kulashekar, B. Dhanasekar. Application of digital image magnification forsurface roughness evaluation using machine vision[J]. International Journal of Machine Tools&Manufacture,2005,45:228–234
[6]熊四昌.基于计算机视觉的刀具磨损状态监测技术的研究[D].浙江大学博士论文,2003.
[7] B.Y. Lee, S.F. Yu, H. Juan. The model of surface roughness inspection by vision system in turning[J].Mechatronics,2004,14:129-141
[8] S. Dutta, A. Datta, N. Das Chakladar,et al. Detection of tool condition from the turned surface imagesusing an accurate grey level co-occurrence technique[J]. Precision Engineering,2012,36:458-466
[9] M. Castejon, E. Alegre, J. Barreiro, et al. On-line tool wear monitoring using geometric descriptorsfrom digital images[J]. International Journal of Machine Tools&Manufacture,2007,47:1847-1853.
[10] Zhen Liu, Junhua Sun, Heng Wang. Simple and fast rail wear measurement method based onstructured light[J]. Optics and Lasers in Engineering,2011,49:1343-1351
[11] T.Y. Lim, M.M. Ratnam. Edge detection and measurement of nose radii of cutting tool inserts fromscanned2-D images[J]. Optics and Lasers in Engineering,2011,49:1259-1267.
[12] W. Wang, Y.S. Wong, G.S. Hong. Flank wear measurement by successive image analysis[J].Computers in Industry,2005,56:816–830
[13] M.A. Mannan, Ashraf A. Kassim, Ma Jing. Application of image and sound analysis techniques tomonitor the condition of cutting tools[J]. Pattern Recognition Letters,2000,21:969-979
[14] Dimla D E, Lister P M, Leighton N J. Neural network solutions to the tool condition monitoringproblem in metal cutting: a critical review of methods[J]. International journal of machine tools&manufacture,1997,37:1219-1241.
[15] M.Sortino. Application of statistical filtering for optical detection of tool wear[J]. InternationalJournal of Machine Tools&Manufacture,2003,43:493–497
[16] Ghassan A. Al-Kindi, Bijan Shirinzadeh. An evaluation of surface roughness parametersmeasurement using vision-based data[J]. International Journal of Machine Tools&Manufacture,2007,47:697–708
[17] Jeon-Ha Kim, Deok-Kyu Moon,Deuk-Woo Lee, et al. Tool wear measuring technique on themachine using CCD and exclusive jig[J]. Journal of Materials Processing Technology,2002,668-674
[18] Yu Zuyuan, Ma Chunshi, An Chengming, et al. Prediction of tool wear in micro USM[J]. CIRPAnnals-Manufacturing Technology,2012,61:227-230.
[19] Chang Dar-Yuan, Lin Shu-Yi. Tool Wear, Hole Characteristics, and Manufacturing Tolerance inAlumina Ceramic Microdrilling Process[J]. Materials and Manufacturing Processes,2012,27(3):306-313
[20] A.R. Zareena, S.C. Veldhuis. Tool wear mechanisms and tool life enhancement in ultra-precisionmachining of titanium[J]. Journal of Materials Processing Technology,2012,212:560-570.
[21] T.J. Ko, D.W. Cho,Y. Jung. On-Line Monitoring of Tool Breakage in Face Milling Using aSelf-Organized Neural Network[J]. Journal of Manufacturing Systems,1995,14(2):80-90.
[22] W.H. Wang,G.S. Hong, Y.S. Wong. Flank wear measurement by a threshold independent methodwith sub-pixel accuracy[J]. International Journal of Machine Tools&Manufacture,2006,46:199-207.
[23] Won-sik Kim.A New Methodology for Predictive Tool Wear[D]. Michigan State University Doctorpaper,2001
[24] Bennett desfosses. An improved power threshold method for estimating tool wear during milling[D].University of New Hampshire master paper,2007.5
[25] Cui Yanjun. Tool Wear Monitoring For Milling by Trackiing Cutting Force ModelCoefficients[D].University of New Hampshire master paper,2008.12
[26] Huseyin M.Ertunc. Techniques for tool wear condition monitoring in drilling operations[D].CaseWestern Reserve University Doctor paper,1999.8
[27] Ya-Tsun Hslao. In-process evaluation of tool wear effects on surface roughness variation in hardturning[D]. University of Missouri-Columbia Doctor paper,1998.7
[28] Sultan Binsaeid,Shihab Asfour,Sohyung Cho,et al. Machine ensemble approach for simultaneousdetection of transient and gradual abnormalities in end milling using multisensor fusion[J]. Journal ofMaterials Processing Technology,2009,209:4728–4738
[29] Nidal H, Abu-Zahra, Gang Yu. Analytical model for tool wear monitoring in turning operationsusing ultrasound waves[J]. International Journal of Machine Tools&Manufacture,2000,40:1619–1635.
[30] M.Kious, A.Ouahabi,M.Boudraa. Detection process approach of tool wear in high speed milling[J].Measurement,2010,43:1439-1446.
[31] Bovic Kilundu,Pierre Dehombreux,Xavier Chiementin. Tool wear monitoring by machine learningtechniques and singular spectrum analysis[J]. Mechanical Systems and Signal Processing.2011,25:400-415.
[32] Francois Girardin，Didier Remond，Jean-Francois Rigal. Tool wear detection in milling--Anoriginal approach with a non-dedicated sensor[J]. Mechanical Systems and Signal Processing,2010,24:1907–1920
[33] J.A.Ghani, M.Rizal, M.Z.Nuawi, et al. Monitoring online cutting tool wear using low-costtechnique and user-friendly GUI[J]. Wear,2011,271:2619–2624.
[34] Ibrahim N,Tansel,Benjamin L,et al. Wear estimation by testing the elastic behavior of tool surface[J].International Journal of Machine Tools&Manufacture,2011,51:745–752
[35] Xiaoli Li,Alexandar Djordjevich,Patri K,et al. Current-Sensor-Based Feed Cutting Force IntelligentEstimation and Tool Wear Condition Monitoring[J]. IEEE Transactions on industrial electronics,2000,47(3):697-702.
[36]张翔.小型五轴联动机床介观尺寸铣削加工及其相关模型的研究[D]，哈尔滨工业大学博士论文，2011.6
[37] Shan Guan,Long-shan Wang. Study on Identification Method of Tool Wear Based on Feature Fusionand Least Squares Support Vector Machine[C].20103rd International Congress on Image and SignalProcessing,2010:3044-3048.
[38] Xihui Liu,Chen Zhang,Jiwen Fang,et al. A New Method of Tool Wear Measurement[C].2010International Conference on Electrical and Control Engineering,2010:2606-2609.
[39]范依航.高效切削钛合金Ti6Al4V刀具磨损特性及切削性能研究[D]，哈尔滨理工大学博士论文，2011.6
[40]刘路，王太勇，蒋永翔.基于超球面支持向量机的刀具磨损状态识别农业机械学报[J]，2011,42(1):218-222
[41]申志刚.高速切削刀具磨损状态的智能监测技术研究[J],南京航空航天大学博士学位论文,2009,11
[42]申志刚,何宁,李亮.高速硬铣削加工刀具磨损监测研究[J].中国机械工程,2009,20(13):1582-1586
[43]蒲宇亭.基于小波分析的高速CNC集成制造工况健康监控技术研究[D]，河北工业大学硕士论文，2010.11
[44]李敏.基于粒子群优化神经网络的刀具磨损状态监测技术研究[D]，西南交通大学硕士论文，2012.5
[45]谢秀娴,付攀,曹伟青.声发射和小波包分解技术在刀具磨损状态中的应用[J].中国测试技术,2006,32(2):40-42
[46]张宗阳.基于最小表面磨损率的刀具磨损及加工表面层特性研究[D]，山东大学博士论文，2012.4
[47]张宗阳,艾兴,刘战强.高效切削铁基高温合金刀具磨损特性研究[J],制造业自动化，2011,33(10):48-52
[48]邵强.切削加工过程中颤振的监测与识别方法研究[D]，大连理工大学博士论文，2010.3
[49]王利伟，王姣.云-SVM模型及在数控机床刀具磨损状态预测中的应用[J].组合机床与自动化加工技术,2012,9:25-31
[50]李斌、丁玉发、刘红奇.小波包分析技术在电流刀具磨损监测系统中的应用[J].心智与计算,2010,4(4):258-264
[51]李斌,张琛,刘红奇.基于主轴电流的铣削力间接测量方法研究[J].华中科技大学学报(自然科学版),2008,36(3):5-11
[52]李鹏阳,郝重阳,祝双武.基于图像连通区域数的刀具磨损状态特征提取实验研究[J].中国图象图形学报,2008,13(8):1476-1480
[53] T. Pfeifer, L. Wiegers.Reliable tool wear monitoring by optimized image and illumination control inmachine vision[J], Measurement,2000,28:209–218
[54] M.Lanzetta.A new flexible high-resolution vision sensor for tool condition monitoring[J]. Journal ofMaterial Processing Technology,2001,119:73-82.
[55] J.Barreiro,M.Castejon, E.Alegre,et al. Use of descriptors based on moments from digital images fortool wear monitoring[J]. International Journal of Machine Tools&Manufacture,2008,48:1005-1013.
[56] J.Jurkovic, M.Korosec,J.Kopac. New approach in tool wear measuring technique using CCD visionsystem[J]. International Journal of Machine Tools&Manufacture,2005,45:1023–1030.
[57] Yongjin Kwon, Gary W.Fischer. A novel approach to quantifying tool wear and tool lifemeasurements for optimal tool management[J]. International Journal of Machine Tools&Manufacture,2003,43:359–368.
[58] A.A.Kassim，M.A.Mannan，Zhu Mian. Texture analysis methods for tool condition monitoring[J].Image and Vision Computing,2007,25:1080–1090
[59] H.Kashiwagi,Y.Nagayama,K.Shibuta. Estimation of Tool Wear by use of Image Processing ofCutting Dust[C]. SICE Annual Conference in Fukui,2003:1723-1726.
[60] Svetlana Antoshchuk, Alexandr Derevianchenko, Elena Tkachenko.The Hierarchical ObjectsAnalysis on Images of Cutting Tool Wear Zones[C]. TCSET,2006:253-255.
[61] Yu-Teng Liang,Yih-Chih Chiou. Vision-Based Automatic Tool Wear Monitoring System[C].Proceedings of the7th World Congress on Intelligent Control and Automation,2008:6031-6035.
[62] T.Kalaichelvi,Dr.P.Rangarajan. Automated Intelligent Machine Vision System for Monitoring theImage[C].2010International Conference on Signal and Image Processing,2010:462-466.
[63] A. Karthik, S. Chandra, B. Ramamoorthy,et al.3D tool wear measurement and visualization usingstereo imaging[J].2009,37(11):1573-1581.
[64] J.C. Su, C.K. Huang, Y.S. Tarng. An automated flank wear measurement of microdrills usingmachine vision[J]. Journal of Materials Processing Technology,2006,180:328–335
[65] Liao Yi, Stephenson, David A.,et al. A multifeature approach to tool wear estimation using3Dworkpiece surface texture parameters[J]. Journal of Manufacturing Science and Engineering,Transactions of the ASME,2010,132(6):0610081-0610087
[66] Li Pengyang, Li Yan,Yang Mingshun. Monitoring Technology Research of Tool Wear ConditionBased on Machine Vision[C]. Proceedings of the7th World Congress on Intelligent Control andAutomation,2008,6:2783-2787.
[67]王阳俊. SiCp/Al复合材料高速铣削表面质量及刀具磨损研究[D]，哈尔滨工业大学博士学位论文，2012.1
[68]朱孔凤.自动聚焦区域选择算法[J].安徽大学学报(自然科学版),2009,33(2):31-34.
[69]王彦芳.自动聚焦系统中评价函数性能与动态区域选取的研究[D].山东大学硕士论文,2011.4
[70]张乐,姜威,高赞.数字图像一阶矩的自动聚焦区域选择算法[J]，光学技术，2008,34(2):163-169.
[71]翟永平,周东翔,刘云辉等.聚焦函数性能评价指标设计及最优函数选取[J].光学学报，2011,31(4)：0418002-1-0418002-11。
[72]宗光华,孙明磊,毕树生等.显微视觉自动聚焦研究[J].光学学报,2005,25(9):1225-1232
[73] Chen Chih-Yung, Hwang Rey-Chue, Chen Yu-Ju. A passive auto-focus camera control system[J].Applied Soft Computing,2010,10:296-303.
[74]朱铮涛,黎绍发,陈华平.基于图像熵的自动聚焦函数研究[J].光学精密工程,2004,12(5):537-542.
[75]周贤.自动聚焦算法研究与验证平台设计[D].山东大学硕士学位论文,2006.4
[76]卢振华.扫描式遥感相机基于图像的实时自动调焦研究[D]，中国科学院博士论文,2012.5
[77]李旭超,朱善安.图像分割中的马尔可夫随机场方法综述[J].中国图象图形学报,2007,12(5):789-798.
[78]陈华杰,吴香伟.强噪声背景下基于非网格MRF的SAR图像快速分割方法[J].光电工程，2010,37(12):75-82
[79]宋晓峰,王爽,刘芳.基于区域MRF和贝叶斯置信传播的SAR图像分割[J].电子学报,2010,38(12):2810-2815
[80]张印辉.多尺度马可夫随机场图像分割方法研究[D].昆明理工大学博士论文,2010
[81] Besag J. Spatial interaction and the statistical analysis of lattice systems[J]. Journal of the RoyalStatistical Society,1974,36(2):192-236
[82]柏柯嘉,刘伟铭.模糊马尔可夫随机场理论在阴影检测中的应用[J].中国图象图形学报,2010,15(3):409-416
[83]刘峰,龚健雅.一种结合能量最小和马尔可夫随机场的图像分割方法[J].地理与地理信息科学,2011,27(2):38-40
[84]齐美彬,杨立宾,蒋建国.自适应权值的MRF分割与跟踪方法[J].中国图象图形学报,2011,16(4):572-578
[85] Haralick R M. Statistical and structural approaches to texture[J].Proceedings of theIEEE,1979,67(5):786-804.
[86] Haralick R M,Shanmugam K,Dinstein I. Textural feature for image classification[J]. IEEETransaction on Systems, Man and Cybemetics Part A,1973,3(6):610-612.
[87] Ahuja N, Rosenfeld A. A note on the use of second-order graylevel statistics for threshold selection[J]. IEEE Trans SMC,1978,8(12):859-898.
[88] Weszka J S,Rosenfeld A.Threshold evaluation technique[J].IEEE Trans SMC,1978,8(7):622-629.
[89]范九伦,任静.基于平方距离的对称共生矩阵阈值法[J]，电子学报，2011,39(10):2277-2281.
[90]李伯宇.图像纹理分析及分类方法研究[D].复旦大学博士论文,2007
[91]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-630
[92] Ojala T,Pietikainen M.Unsupervised texture segmentation using feature distributions[J].PatternRecognition,1999,32(2):477-486
[93] Ojala T,Pietikainen M.Multiresolution gray-scale and rotation invariant texture classification withlocal binary Patterns[J].IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(17):971-987.
[94] Tang Y Y,Tao Y,Lam E C M.New method for feature extraction based on fractal behavior[J].PatternRecognition Letters,2002,35(5):1071-1081
[95]陈美龙,戴声奎.基于GLCM算法的图像纹理特征分析[J].通信技术,2012,45(2):108-111
[96] Ulaby FT, Kouyate F, Brisco B, et al. Textural information in SAR Images[J]. IEEE Transactions onGeoscience and Remote Sensing,1986,24(2):235-245.
[97] Pearson K. on lins and planes of elosest fit to systems of points in spaee[J]. PhilosophicalMagazine,1901:559-572.
[98] Samik Dutta,Arpan Das,Kaustav Barat,Himadri Roy. Automatic characterization of fracturesurfaces of AISI304LN stainless steel using image texture analysis[J],Measurement,2012,45:1140-1150
[99] Ulaby FT, Kouyate F, Brisco B, et al. Textural information in SAR Images[J]. IEEE Transactions onGeoscience and Remote Sensing,1986,24(2):235-245
[100]王辉.基于灰度共生矩阵木材表面纹理模式识别方法的研究[D].东北林业大学硕士论文,2007.6
[101] Mousumi Gupta,Debasish Bhaskar,Rabindranath Bera,et al. Target detection of ISAR data byprincipal component transform on co-occurrence matrix[J]. Pattern Recognition Letters,2012,33:1682-1688.
[102]熊四昌,计时鸣,樊炜.基于马尔可夫随机场工件表面纹理模型的刀具状态监测[J].中国机械工程,2004,15(8):678-680
[103] Haindl, M., Simberova, S.. Theory&Applications of Image Analysis: A Multispectral Image LineReconstruction Method[M]. Singapore: World Scientific Publishing Co.,1992,306–315.
[104] Pavel Vacha,Michal Haindl, Tomas Suk. Colour and rotation invariant textural features based onMarkov random fields[J]. Pattern Recognition Letters,2011,32:771-779
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |