Development of a weld quality monitoring system in CO2 laser welding by using photodiodes

Abstract

On a laser weld production line, a slight alteration of the welding condition produces many defects. The defects are monitored in real time in order to prevent continuous occurrence of defects, to reduce the loss of material, and to guarantee good quality. The measurement system consists of three photodiodes to detect the plasma and spatter signals in CO2 laser welding. For high speed CO2 laser welding, such as laser tailored welded blanks, an on-line weld quality monitoring system was developed by using fuzzy multifeature pattern recognition. Weld qualities are classified as optimal heat input, little low heat input, low heat input, and focus misalignment. Then the result of the final weld quality is estimated good or bad.