A visual model of welding robot based on CNN deep learning

被引：0
作者：
Li H. [1 ]
Han X. [1 ]
Fang Z. [2 ]
机构：
[1] Intelligent Manufacturing Department, Wuyi University, Jiangmen
[2] Institute of Automation, Chinese Academy of Sciences, Beijing
来源：
Hanjie Xuebao/Transactions of the China Welding Institution | 2019年 / 40卷 / 02期
关键词：
Convolutional neural network; Deep learning; Visual model; Welding robot; Welding target;
D O I：
10.12073/j.hjxb.2019400060
中图分类号：
学科分类号：
摘要：
In order to accurately recognize the weld target in complex environment, a visual model of welding robot based on deep learning was established. The model adoped a convolutional neural network (CNN) combining local connection and full connection. The local connection was composed of 3 convolution layers (C) and 3 subsampling layers (S) with C-S alternating mode for feature extraction of welding target. The full connection layer was composed of input layer, hidden layer and output layer as a classifier for weld target recognition. More than 1 000 image samples of welding targets were sampled for CNN network training, and the influence of different CNN structure parameters on the model was analyzed. The test results show that the visual model was robust to the translation, rotation and scaling of welding targets, and could be applied to the visual navigation of welding robots. © 2019, Editorial Board of Transactions of the China Welding Institution, Magazine Agency Welding. All right reserved.
引用
收藏
页码：154 / 160
页数：6
相关论文
共 11 条
  • [1] Chen X., Chen S., Recognition and positioning of start welding position for arc welding robot, Transactions of the China Welding Institution, 30, 4, pp. 17-20, (2009)
  • [2] Ye Y., Zhang H., Pan J., Et al., System of underwater welding robot for large-scale structure, Transactions of the China Welding Institution, 36, 11, pp. 41-44, (2015)
  • [3] Yang X., Xu Y., Huang S., Et al., A recognition algorithm for feature points of V groove welds based on structured light, Journal of Shanghai Jiaotong University, 50, 10, pp. 1573-1577, (2016)
  • [4] Guo L., Zhang H., Identification tracking welding system for right angle fillet seam in narrow space, Transactions of the China Welding Institution, 38, 11, pp. 21-26, (2017)
  • [5] Cong H., Guo F., Lu F., Et al., Research on weld seam recognition technology based on CCD image processing, Electronic Measurement Technology, 35, 3, pp. 73-76, (2012)
  • [6] Hinton G.E., Osindero S., Teh Y.W., A fast learning algorithm for deep belief nets, Neural Computation, 18, 7, pp. 1527-1554, (2006)
  • [7] Hinton G.E., Salakhutdinov R.R., Reducing the dimensionality of data with neural networks, Science, 313, 5786, pp. 504-507, (2006)
  • [8] Lecun Y., Bengio Y., Hinton G.E., Deep learning, Nature, 521, 7553, pp. 436-444, (2015)
  • [9] Simonyan K., Zisserman A., Very deep convolutional networks for large-scale image recognition, Proc. Of International Conference on Learning Representations (ICLR), pp. 1-14, (2015)
  • [10] Yim J., Ju J., Jung H., Image classification using convolutional neural networks with multi-stage feature, Proc. of 3rd International Conference on Robot Intelligence Technology and Applications, pp. 587-593, (2015)
12