An in-process machine vision detecting system in continuous machining

  • Authors:

  • Qiaoling Yuan;Shiming Ji;Yi Xie;Li Zhang;Wei Fan;Mingsheng Jin

  • Affiliations:

  • The MOE Key Laboratory of Mechanical and Automation, Zhejiang University of Technology, Hangzhou, P. R. China;The MOE Key Laboratory of Mechanical and Automation, Zhejiang University of Technology, Hangzhou, P. R. China;Institute of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou, P. R. China;The MOE Key Laboratory of Mechanical and Automation, Zhejiang University of Technology, Hangzhou, P. R. China;The MOE Key Laboratory of Mechanical and Automation, Zhejiang University of Technology, Hangzhou, P. R. China;The MOE Key Laboratory of Mechanical and Automation, Zhejiang University of Technology, Hangzhou, P. R. China

  • Venue:
  • IMCAS'06 Proceedings of the 5th WSEAS international conference on Instrumentation, measurement, circuits and systems
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In continuous machining, batches of wasters have been manufactured if the machine worked wrong before the inspection. It is necessary to develop in-process detecting techniques for products' quality control. So a high-speed machine vision system for auto detecting defects in continuous machining is designed in this paper. The perimeter of product's edge and Euler number of the image are measured as detecting parameters. The customized wavelet transform for edge detection is proposed in this paper. The above image's characteristics are chosen as input vectors of this machine vision system, and 50 various images of each defect type are chosen as training samples, the recursion least square law is used to train this system. This system is successfully used to detect various defects of the products on line and the detection rate achieves more than 95%. The advantages of this system may be seen as lower cost, less bulky, greater resolution, and flexibility.