期刊文献+

基于脉冲耦合神经网络的刀具磨损检测 被引量:8

Tool Wear Detection Based on PCNN
下载PDF
导出
摘要 将仿生学中的脉冲耦合神经网络(PCNN)引入刀具磨损检测中,利用刀具磨损区域灰度强度明显高于刀体和背景区域灰度强度的特点,通过空间邻近和灰度相似集群像素获得分割的二值图像,从而达到对刀具磨损区域进行检测的目的。对车削加工中刀具不同磨损阶段的磨损图像进行分割试验,证明了该算法可以有效地判断刀具的磨损状态。 The pulse-couple neutral network(PCNN) in the bionics was introduced into the tool wear monitoring for the first time herein. According to gray intensity in the region of tool wear is higher than that of the tool body and background,using the spatial neighbor and similar cluster gray of pixel,the binary image of the tool wear was segmented,and the region of tool wear was detected. This algorithm and the validity of this method are proved by experimental results of the image segmentation of tool wear for the different stages in a turning process,and the tool wear can be effectively judged.
机构地区 西北工业大学
出处 《中国机械工程》 EI CAS CSCD 北大核心 2008年第5期547-550,共4页 China Mechanical Engineering
基金 陕西省教育厅专项科研计划资助项目(07JK335) 陕西省自然科学基础研究计划资助项目(2006E123)
关键词 脉冲耦合神经网络(PCNN) 刀具磨损 图像分割 状态检测 pulse- couple neutral network (PCNN) tool wear image segmentation state detection
  • 相关文献

参考文献17

  • 1Abu--Zahra N H, Yu Gang. Analytical Model for Tool Wear Monitoring in Turning Operations Using Ultrasound Waves[J]. International Journal of Machine Tools & Manufacture, 2000,40 : 1619-1635.
  • 2Sortino M. Application of Statistical Filtering for Optical Detection of Tool Wear [J].International Journal of Machine Tools & Manufacture,2003,43 :493-497.
  • 3Mannan M A,Kassim A A,Ma Jing. Application of Image and Sound Analysis Techniques to Monitor the Condition of Cutting Tools[J]. Pattern Recognition Letters, 2000,21 :969-979.
  • 4Kassim A A,Mannan M A,Ma Jing. Machine Tool Condition Monitoring Using Workpiece Surface Texture Analysis[J]. Machine Vision, 2000,11 (4) : 257-263.
  • 5Kassim A A,Zhu Mian, Mannan M A. Connectivity Oriented Fast Hough Transform for Tool Wear Monitoring[J]. Pattern Recognition, 2004,37 : 1925- 1933.
  • 6Kerr D, Pengilley J, Garwood R. Assessment and Visualization of Machine Tool Wear Using Comput er Vision[J]. The International Journal of Advanced Manufacture, 2006,28(4): 781-791.
  • 7Wang W H, Hong G S, Wong Y S. Flank Wear Measurement by a Threshold Independent Method with Sub--pixel Accuracy[J]. International Journal of Machine Tools & Manufacture, 2006, 46: 199- 207.
  • 8Gu Xiaodong,Guo Shide, Yu Daoheng. A New Approach for Automated Image Segmentation Based on Unit--linking PCNN[C]//The Proceedings of the First International Conference on Machine Learning and Cybernetics. Beiiing: IEEE, 2002 : 175-178.
  • 9Kuntimad G, Ranganath H S. Perfect Image Seg mentation Using Pulse Coupled Neural Networks [J]. IEEE Transactions on Neural Networks, 1999, 10(3) : 591-598.
  • 10顾晓东,余道衡.PCNN的原理及其应用[J].电路与系统学报,2001,6(3):45-50. 被引量:42

二级参考文献32

  • 1吴成柯,刘靖,徐正伟,周凌云.图像分割的遗传算法方法[J].西安电子科技大学学报,1996,23(1):34-41. 被引量:17
  • 2Gu Xiaodong,The 8th International Conference on Neural Information Processing,ICONIP,2001年
  • 3De Liang L Wang,IEEE Trans Neural Networks,2000年,12卷,1期,181页
  • 4Liu X,IEEE Trans Neural Networks,1999年,10卷,3期,564页
  • 5Stewart R D,Fermin I,et al.Region growing with pulse-coupled neural networks:an alternative to seeded region growing[J].IEEE Trans.on Neural Networks,2002,13(6):1557-1562.
  • 6Shareef N,Wang D L,et al.Segmentation of medical images using LEGION[J].IEEE Trans.on Medical Imaging,1999,18(1):74-91.
  • 7Kuntimad G,Ranganath H S.Perfect image segmentation using pulse coupled neural networks[J].IEEE Trans.on Neural Networks,1999,10(3):591-598.
  • 8Eckhorn R,ReitBoeck H J,et al.Feature linking via synchronization among distributed assemblies:simulation of results form cat visual cortex[J].Neural Computation,1990,2(3):293-307.
  • 9Ranganath H S,Kuntimad G,et al.Pulse coupled neural networks for image processing[A].Proceedings of IEEE Southeastcon'95,Visualize the Future[C].New York:IEEE,1995.37-43.
  • 10Ranganath H S,Kuntimad G.Image segmentation using pulse coupled neural networks[A].Proceedings of IEEE International Conference on Neural Networks[C],Orlando FL:IEEE,1994.1285-1290.

共引文献115

同被引文献113

引证文献8

二级引证文献43

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部