基于导轨面图像特征雷达图的磨损状况识别

摘要/Abstract

摘要：

为解决精密机床导轨面磨损缺陷及缺陷程度的识别问题，提出一种基于导轨面图像数据雷达图重心特征的表面磨损识别方法。首先提取导轨面图像数据的灰度均值、歪度、峭度、扁度和投影方差作为磨损状况识别的原始特征；然后采用雷达图技术将特征数据可视化，并提取雷达图的重心特征；最后采用支持向量机技术设计分类器，同时采用雷达图重心特征和磨损缺陷原始特征进行分类,并与实验检测的导轨面磨损数据进行对比分析。计算和实验结果表明: 基于雷达图的图像数据重心特征可有效地识别导轨面是否磨损,并能在一定程度上判别导轨面的磨损程度。

关键词: 导轨面, 磨损缺陷, 特征提取, 数据可视化, 图表示

Abstract:

To solve the wear recognition problem of machine tool guide surfaces, a new machine tool guide surface recognition method was presented herein based on the radar-graph barycentre feature. Firstly, the gray mean value, skewness, kurtosis, flat degrees and projection variance features of the guide surface image data were defined as primary characteristics. Secondly, data visualization technology based on radar graph was used. The visual barycentre graphical feature was demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology was used, the radar-graph barycentre feature and wear original feature were put into the classifier separately for classification and comparative analysis of classification and experimental results. The calculation and experimental outcomes show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Key words: guide surface, wear defect, feature extraction, data visualization, graphical representation

中图分类号:

TH117.1

周友行, 喻思亮, 张俏, 周健. 基于导轨面图像特征雷达图的磨损状况识别[J]. 中国机械工程, 2015, 26(5): 647-652.

Zhou Youhang, Yu Siliang, Zhang Qiao, Zhou Jian. Wear Recognition on Guide Surface Based on Feature of Radar Graph[J]. China Mechanical Engineering, 2015, 26(5): 647-652.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/

http://www.cmemo.org.cn/CN/Y2015/V26/I5/647

参考文献

[1]关朝亮,戴一帆,王建敏,等.基于直线电机驱动的空气静压导轨动静态倾覆特性研究[J].机械科学与技术, 2010, 9(9): 1182-1186.
Guan Chaoliang, Dai Yifan, Wang Jianmin,et al. Static and Dynamic Characteristics of an Air Bearing Guide Driven by a Linear Motor[J]. Mechanical Science and Technology, 2010, 9(9): 1182-1186.
[2]李传乾.机床导轨按磨损规律设计计算的研究[J].湖南大学学报，1997,6(3)：56-75.
Li Chuanqian. Research of Machine Tool Guideway Based on the Wear Rules Design[J]. Journal of Hunan University, 1997,6(3)：56-75.
[3]张从鹏,刘强.基于静压气浮导轨的直线电机高性能工作台的研制[J].机械科学与技术,2006,10(10):1212-1216.
Zhang Congpeng, Liu Qiang. Development of High-performance Linear Motor Stage Based on Static-pressure Air-bearing Slider[J]. Mechanical Science and Technology, 2006, 10(10): 1212-1216.
[4]李永祥,焦万堂,武文斌.机床导轨误差对零件加工精度的影响[J].制造技术与机床,2005,5(8)：34-40.
Li Yongxiang, Jiao Wantang, Wu Wenbin. Influence of Lathe Guide Errors on Machining Accuracy[J]. Manufacturing Technology and Machine Tools, 2005, 5(8)：34-40.
[5]丛家慧，颜云辉.视觉注意机制在带钢表面缺陷检测中的应用[J].中国机械工程,2011,22(10):1189-1192.
Cong Jiahui, Yan Yunhui. Application of Human Visual Attention Mechanism in Surface Defect Inspection of Steel Strip[J]. The Chinese Mechanical Engineering, 2011, 22(10):1189-1192.
[6]俞翔,胡志强.基于局部纹理特征的钢卷侧面缺陷检测方法研究[J].计算机工程与设计,2009,30(24):30-24.
Yu Xiang, Hu Zhiqiang. Study of Side Image of Steel Coil Defects Detection Based on Local Textural Feature[J]. Computer Engineering and Design, 2009,30(24):30-24.
[7]Kerr D,Pengilley J, Garwood R. Assessment and Visualisation of Machine Tool Wear Using Computer Vision[J]. Manuf. Technol., 2006,28(7/8): 781-791.
[8]唐开勇.机床床身导轨的磨损及其对机床精度的影响[J].机械研究与应用,2006,10(5):12-14.
Tang Kaiyong. The Abrasion of the Slideway of the Machine Tool and Its Influence on the Precision of the Machine Tool[J]. Mechanical Research and Application, 2006, 10(5):12-14.
[9]EllisT J,Hill W J. Automatic Inspection of Cold-rolled Steel Strip[C]//Proc.IEEE Int. Conf. on Image Processing.New York,1982: 134-138.
[10]韩芳芳.表面缺陷视觉在线检测关键技术研究[D].天津：天津大学,2011.
[11]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):622-633.
Liu Li, Kuang Gangyao. Overview of Image Textural Feature Extraction Methods[J]. Chinese Journal of Image and Graphics, 2009, 14(4):622-633.
[12]王金甲,李静,张涛,等.二次映射和遗传算法用于可视化特征提取[J].系统仿真学报,2009,8(16):80-83.
Wang Jinjia, Li Jing, Zhang Tao, et al. Distinguishing Visual Feature Extraction Method Using Quadratic Map and Genetic Algorithm[J]. Journal of System Simulation, 2009,8(16):80-83.
[13]Chen M, Ebert D, Hagen H, et al. Data Information and Knowledge in Visualization[J].IEEE Computer Graphics and Applications, 2009,29(1): 12-19.
[14]洪文学，高海波, 崔建新,等.多元图图形基元和特征基元提取与表示方法[J].燕山大学学报, 2008(9):405-411.
Hong Wenxue, Gao Haibo, Cui Jianxin, et al. The Extraction and Representation of Multiple Graphical Primitives and the Characteristics of Primitives[J]. Journal of Yanshan University, 2008(9):405-411.
[15]刘文远,李芳.洪文学.基于多维数据雷达图表示的图形分类器研究[J].计算机工程与应用，2007（22）:75-78.
Liu Wenyuan, Li Fang, Hong Wenxue. The Research of Radar Map Graphics Classifier Based on the Multidimensional Data[J]. Computer Engineering and Application, 2007（22）:75-78.