Abstract
Quality improvement systems, as opposed to quality control systems, generally require feedback information on the nature and extent of defects being encountered so as to take appropriate remedial actions. This paper discusses the use of neural networks to classify surface defects on automotive valve stem seals. The neural networks are to be incorporated in an automated visual inspection machine forming part of an overall quality improvement system. Three types of neural networks are considered: the adaptive logic network, the backpropagation multi-layer perceptron (BMLP) and the Kohonen feature map. The BMLP has the best classification accuracy (90%). When different BMLP modules are combined, each to classify a range of defect sizes, the accuracy increases due to “synergy” between the individual modules.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Machine Tools and Manufacture
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
