Abstract

The solidification mode, random pore defects and deposition height were monitored during the laser metal deposition process by using a laser-induced plasma signal. The spectral lines of six elements that determine the solidification mode of austenite steel were extracted and set as features of the dataset. Two different solidification modes were successfully predicted through a support vector machine model. Random pore positions inside the deposition layer were identified by monitoring the statistical parameters of the plasma spectrum. Relationships between the pore position and the statistics features of the spectrum signal were developed. The spatial distributions of plasma temperature, electron density and signal intensity were characterized, and their connection with the deposition height was studied. The electron density and signal mean intensity were found to have linear relationships with the deposition height and can be used to detect abnormal height changes during the manufacturing process.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call