Heuristics for managing trainable binary inspection systems

Abstract

Binary inspection systems such as those based on ideal templates, neural networks, fuzzy logic, and genetic algorithms are trained by presenting them with exemplars of acceptable work. The system inspects new work by comparing it to the exemplars. The operator may not always agree with the judgment of the system and may decide to retrain it during production. This article explores the quality risks of using and of modifying trainable systems. Risk reduction heuristics used in software development are explored and adapted for use with trainable inspection systems. The use of these heuristics is illustrated in a series of scenarios.

KEYWORDS:

• process monitoring
• artificial neural networks
• measurement system analysis
• genetic algorithms
• process variability
• binary inspection systems
• trainable inspection systems

About the author

T. Bress is a Managing Engineer in the Mechanical Engineering practice of Exponent, a nation-wide science and engineering consulting firm. He is a Certified Six Sigma Black Belt, Certified Quality Engineer and Certified Reliability Engineer with the American Society for Quality and is also a Certified Manufacturing Engineer with SME. He is also a National Instruments Certified LabVIEW Architect and is the author of the book Effective LabVIEW Programming. He has a B.S. and M.S. in Mechanical Engineering from MIT and a Ph.D. in Mechanical Engineering from the University of Michigan. Dr. Bress consults on a wide range of mechanical engineering topics and specializes in issues related to design and manufacturing.