Web process inspection using neural classification of scattering light

Web process inspection requires rapid examination of vast amounts of data. The two resulting issues, the sensory system and the computer processing required to detect faults in the sheet material accurately, were examined. It was found that scattered coherent light from the surface of the material being processed could be directly conditioned by a photodetector so as to produce a small set of features which are then examined by a neural network trained to find unsatisfactory surface conditions. A surface inspection system using measurement of the angular distribution over a 25°C cone angle of the scattering was constructed, calibrated, and evaluated for inspection of coated sheet and steel samples. Features, created by a simulated segmented photodetector, were inputs to a neural network which used classification based upon T. Kohonen´s (1989) learning vector quantization (LVQ2). The system was evaluated with CrO₂ coated steel samples. Classification by fault or no-fault categorized 133 samples corrected out of 135, while there were seven errors in one attempt at classification by the various common types of surface fault out of the same number of test samples and nine in another