Discrimination of steel types by sparks: applying neural network

Very many product inspection processes depend on human senses, visual mostly. Generally, such inspections are called Kannou Kensa in Japanese, which means sensory inspections. Neuro-fuzzy control is coming to function increasingly like human senses, and these techniques have come to be used for automating or mechanizing the sensory inspections. This paper discloses an experimental model for discriminating steel types resorting to image processing technique and neural network based on the method of spark test for steels (JIS G 0556) in the simplified test for identifying the material out of different material tests executed in iron and steel fields.<>