Power control during remote laser welding using a convolutional neural network

Alex Božič (Author), Matjaž Kos (Author), Matija Jezeršek (Author)

Abstract

The increase in complex workpieces with changing geometries demands advanced control algorithms in order to achieve stable welding regimes. Usually, many experiments are required to identify and confirm the correct welding parameters. We present a method for controlling laser power in a remote laser welding system with a convolutional neural network (CNN) via a PID controller, based on optical triangulation feedback. AISI 304 metal sheets with a cumulative thickness of 1.5 mm were used. A total accuracy of 94% was achieved for CNN models on the test datasets. The rise time of the controller to achieve full penetration was less than 1.0 s from the start of welding. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was used to further understand the decision making of the model. It was determined that the CNN focuses mainly on the area of the interaction zone and can act accordingly if this interaction zone changes in size. Based on additional testing, we proposed improvements to increase overall controller performance and response time by implementing a feed-forward approach at the beginning of welding.

Keywords

konvolucijske nevronske mreže;lasersko daljinsko varjenje;nadzor moči laserja;triangulacijska povratna zanka;convolutional neural network;remote laser welding;laser-power control;triangulation feedback;

Data

Language:	English
Year of publishing:	2020
Typology:	1.01 - Original Scientific Article
Organization:	UL FS - Faculty of Mechanical Engineering
UDC:	621.791.725:004.032.26(045)
COBISS:	39691267
ISSN:	1424-8220
Views:	279
Downloads:	114
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary keywords:	konvolucijske nevronske mreže;lasersko daljinsko varjenje;nadzor moči laserja;triangulacijska povratna zanka;
Type (COBISS):	Article
Pages:	f. 1-15
Volume:	ǂVol. ǂ20
Issue:	ǂiss. ǂ22
Chronology:	Nov. 2020
DOI:	10.3390/s20226658
ID:	12972445