Application of Artificial Neural Net in Defect Image Recognizing of Cutting Chip
Aiming at the problem of image recognition in the process of defected chip generation of automatic machining, fuzzy category methods of RBF net and eight neighborhood Euler numbers are researched in this paper. They are based on fuzzy theory and neural net. The gradient steepest descent of optimization theory is used and aberration is minimized by step between required output and actual output. By modifying studying algorithm, recognized capacity is increased. This method is tested in Matlab platform. It can be concluded that fraction of chip image under sophisticated surrounding may be recognized accurately through this net.
Zhejun Yuan, Xipeng Xu, Dunwen Zuo, Julong Yuan and Yingxue Yao
Y. L. Zhao et al., "Application of Artificial Neural Net in Defect Image Recognizing of Cutting Chip", Key Engineering Materials, Vols. 315-316, pp. 496-500, 2006