Product Code: ICAL09_P137

Closed Loop Control of Laser Welding Processes Using Cellular Neural Network Cameras - Experimental Results
Authors:
Felix Abt, Forschungsgesellschaft Fuer Strahlwerkzeuge Fgsw; Stuttgart Germany
Andreas Blug, Fraunhofer Institute for Physical Measurement Techniques Ipm; Freiburg Germany
Leonardo Nicolosi, Iee Institut Fuer Grundlagen Der Elektrotechnik U. Elektronik; Dresden Germany
Friedrich Dausinger, Dausinger & Giesen Gmbh; Stuttgart Germany
Rudolf Weber, Institut Fuer Strahlwerkzeuge Ifsw; Stuttgart Germany
Ronald Tetzlaff, Iee Institut Fuer Grundlagen Der Elektrotechnik U. Elektronik; Dresden Germany
Daniel Carl, Fraunhofer Institute for Physical Measurement Techniques Ipm; Freiburg Germany
Heinrich Hoefler, Fraunhofer Institute for Physical Measurement Techniques Ipm; Freiburg Germany
Presented at ICALEO 2009

Today, image processing using coaxial camera setups is used to monitor the quality of laser mate-rial processes such as laser welding, cutting or ablation. This article shows the potentials of a sensing system for the next step: A closed loop control of a full penetration keyhole welding process. With Cellular Neural Networks (CNN) it is possible to integrate processor elements in the electronic circuitry of CMOS cameras resulting in a Single-Instruction-Multiple-Data (SIMD)-architecture on the camera chip itself. Such pixel parallel systems provide extremely fast real-time image processing. This allows it to employ algo-rithms for image processing which are widely independent of the exact process parameters, re-ducing the adaption effort for different applica-tions, compared to photo diode systems.
A closed loop control system was implemented into a commercially available laser welding ma-chine. This system uses a CNN based camera surveying the contour of the full penetration hole with a control frequency in the multi kilohertz range. As a result the system reaches and holds the full penetration state automatically. Latest improvements on this CNN-based control system include a direction independent algorithm. This system enables the development of more complex seam shapes with variable orientation, material thickness and welding speed.