Laser processing quality monitoring by combining acoustic emission and machine learning: a high-speed X-ray imaging approach

摘要

In situ and real-time monitoring of laser processes are very challenging due to complex dynamics of the laser-matter interactions. Acoustic emission (AE) technique is often used as non-destructive monitoring of many kinds of processes. However, acoustic emission is not industrialized for laser processing for two reasons. First, the signals are too sensitive to the environmental noises. Second, a correlation of the acoustic emission signal with the real events is very difficult to realize despite being of utmost importance. To overcome these difficulties, we combined fast hard X-ray imaging with acoustic sensors and state-of-the-art machine learning.