Description

In this project three main topics were included which are described briefly below:

1. A flexible AI algorithm for image analysis was optimized for the use case of tool wear detection with regards to image size, network size and image augmentation.
2. The optimization in topic 1. were utilized in a new use case: AI-based detection of melt pool area on microscopic cross-section images of seams in laser beam welding. A brief result is shown in Figure 1.
3. Furthermore, the indirect estimation of the hard-to-determine keyhole depth in laser beam welding using the measured surface roughness of the seams was investigated. In the first approach, no useful correlation for indirect quality assessment could be found. A data sample is shown in Figure 2.