Real-time Prediction of Quality Characteristics Based on Inline Process Data Using Machine Learning

Laser beam welding significantly outperforms conventional joining techniques in terms of flexibility and productivity. The process benefits in particular from the highly focused energy and thus from a well-defined heat input. The high intensities of brilliant laser radiation, however, induce very dynamic effects and complex processes within the interaction zone. The high process dynamics require a consequent and reliable quality assurance to ensure the required weld quality. A novel sensor concept for laser material processing based on Optical Coherence Tomography (OCT) was used to measure the capillary depth of the keyhole during deep penetration welding. The OCT signal was preprocessed, analyzed by means of statistical methods and compared with analyses of the quality of the weld seams. A Machine Learning approach could be utilized to reveal correlations between the weld depth signal and typical weld seam characteristics, underlining the high level of information contained in the OCT signal about characteristic process phenomena that affect the weld seam quality. In order to obtain useful information from the process data, the process of Knowledge Discovery in Databases (KDD) was considered holistically. For this purpose, all steps, including data acquisition, data preprocessing, data mining and data interpretation, were considered. Taking into account effects that influence the measurement and characteristic process phenomena in laser beam welding, a procedure was developed with which valid predictions can be drawn about the weld seam properties even with a small amount of training data.     «

Laser beam welding significantly outperforms conventional joining techniques in terms of flexibility and productivity. The process benefits in particular from the highly focused energy and thus from a well-defined heat input. The high intensities of brilliant laser radiation, however, induce very dynamic effects and complex processes within the interaction zone. The high process dynamics require a consequent and reliable quality assurance to ensure the required weld quality. A novel sen...     »