Learning methods for online-process diagnosis

Patrick Feucht, Johann Marius Zöllner, Karsten Berns, Torsten Zirzlaff, Oskar Leisin

Abstract: Because of the very high workpiece costs in manufacturing processes, production errors should be detected online in order to avoid a series of defective workpieces. This article describes a qualitative evaluation method for time series that is applied to the diagnosis of a procedure for spraying car body parts. The determination of the parameters for the procedure is gained through learning data, which simplifies the industrial use enormously. A prototype that is already employed in production confirms the expected functionality of the procedure.