Design of a Database-Driven Quality Predictor for Painting Systems

Abstract

In painting processes, to prevent the occurrence of painting defects, the rotational speed of the bell cup should be adjusted online based on the painting quality. However, there is a considerable time-delay between the painting process and the evaluation of painting quality. This paper proposes a database-driven painting quality predictor, which has a mechanism to adaptively change the threshold to classify through learning to reduce the delay. A numerical simulation is performed to verify the effectiveness of the proposed method. As a result, the accuracy of the proposed method is superior to that of the conventional method.