期刊文献+

皮带撕裂的视觉检测 被引量:7

Visual Inspection of Belt Tearing
下载PDF
导出
摘要 为保证物料输送皮带的运行安全,构建了皮带撕裂视觉监控系统,并基于改进的BP神经网络方法实现了对皮带裂纹的视觉识别。首先,采用Canny算子对皮带裂纹进行边缘提取,并提出了对检测到的边缘进行四周外向扩展的方法,通过增加一个裂纹权重值,使检测到的裂纹边缘向外扩张,从而获得更鲁棒的边缘检测效果;然后,构建改进的BP神经网络预报模型,以皮带裂纹图像的面积及长宽比几何特征量作为网络输入量,采集皮带裂纹图像样本,实现BP网络预报模型的训练及预报结果输出。实验表明:提出的皮带撕裂检测方法是有效的。 In order to ensure the operating safety of conveyor belts, the paper established a belt tearing visual inspection system, in which the belt cracks were realized to be visually identified based on the improved BP neural network method. Firstly, the belt cracks was performed an edge extraction by adopting Canny operator. In addition, a method of extending the detected edge outwards was put forward, in which the crack edges would be extended outward by adding a weight value, so that a more robust edge detection result would be obtained. Furthermore, an improved BP neural network forecast model was established, of which the area and length-width ratio of the belt crack images were regarded as network inputs, in order to take samples of belt crack images and implement the training and forecast result outcomes of the BP network forecast model. The experimental result shows that the proposed belt tearing inspection method is effective.
作者 程月 尚学文 王福平 王福斌 CHENG Yue;SHANG Xue-wen;WANG Fu-ping;WANG Fu-bin(Department of Electrical Engineering,Tangshan Labor Technician College,Tangshan 063300,China;Tangshan Kunda Science and Technology Ltd.,Tangshan 063020,China;Third Company of Drilling and Exploration Group of Daqing Oilfield,Daqing 163412,China;College of Electrical Engineering,North China University of Science and Technology,Tangshan 063009,China)
出处 《机械工程与自动化》 2018年第3期132-134,137,共4页 Mechanical Engineering & Automation
基金 中科院自动化研究所项目资助(20140059)
关键词 皮带撕裂 Canny边缘提取 BP网络 视觉检测 belt tearing Canny edge extraction BP network visual identification
  • 相关文献

参考文献4

二级参考文献27

  • 1高江平,吴家惠,邓友生,王家澄.硫酸盐渍土膨胀规律的综合影响因素的试验研究[J].冰川冻土,1996,18(2):170-177. 被引量:27
  • 2Roosmalen V. Restoration of Archived Film and Video[D]. Delft, Holland: Delft University of Technology, 1999.
  • 3Kokaram A C. Motion Picture Restoration Digital Algorithms for Artifact Suppression in Degraded Motion Picture Film and Video[M]. Berlin, Germany: Springer-Verlag, 1998.
  • 4Joyeux L, Buisson O, Besserer B, et al. Detection and Removal of Line Scratches in Motion Picture Films[Cl//Proc. of the International Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 1999: 548-553.
  • 5Bruni V, Vitulano D, Kokaram A. Fast Removal of Line Scratches in Old Movies[C]//Proc. of the 17th International Conference on Pattern Recognition. Cambridge, UK: [s. n.], 2004: 827-830.
  • 6黄立度,席元伟,李俊超.硫酸盐渍土道路盐胀病害的基本特征及其防治[J].中国公路学报,1997,10(2):39-47. 被引量:55
  • 7HarkinS 著 叶世伟 史忠植译.神经网络原理[M].北京:机械工业出版社,2004.154-159.
  • 8沈掌泉.神经网络集成技术及其在土壤学中应用的研究.杭州:浙江大学,2006.
  • 9Zheng J, Suzuki K, Fujita M. Predicting driver’s lane-changing de-cisions using a neural network model. Simulation Modelling Practiceand Theory, 2014;42: 73-83.
  • 10Houenou A, Bonnifait P, Cherfaoui V,et al. Vehicle trajectory pre-diction based on motion model and maneuver recognition. IntelligentRobots and Systems ( IROS) , 2013 IEEE/RSJ International Confer-ence on. IEEE, 2013 : 4363-4369.

共引文献9

同被引文献78

引证文献7

二级引证文献32

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