Intelligent visual inspection of valve-stem seals

• Publisher: Elsevier Science
• Year: 1995
• Tongue: English
• Weight: 490 KB
• Volume: 1995
• Category: Article
• ISSN: 1350-4789
• DOI: 10.1016/s1350-4789(00)80036-7

✦ Synopsis

Intelligent inspection valve-stem visual of seals During the moulding of valve-stem seals, different fault types can occur. This article describes how one company, Seal Technology Systems, in Cardiff, Wales, applied rules and neural networks in an automated visual inspection system for the rejection of faulty seals, and more importantly, to provide information about the faults that could be used by an on-line quality improvement system. An attentional mechanism was used which detects discontinuities on the sealing lip contour, and neural networks employed to classify surface defects by their geometrical outline features. This article describes the types of faults discriminated by the system, the optical and mechanical hardware employed, the different algorithms used and their practical validation.