Real time control of curved laser welding processes by cellular neural networks (CNN): first results

[摘要] In the last decades the laser beam welding (LBW) has outclassed older weldingtechniques in the industrial scenario. Despite the improvement in weldingtechnology, sophisticated methods of fault detection are not commonly used incommercially available equipments yet. A recent analysis of process imageshave revealed the possibility to build up a real time closed loop controlsystem. By the use of image based quality features, a feedback signal can beprovided to maintain the process in the desired state. The development of thepresented visual control system has been focused on the adjustment of thelaser power according to the detection of the so called full penetrationhole. Due to the high dynamics of the laser welding, a fast real time imageprocessing with controlling rates in the multi kilo Hertz range is necessaryto have a robust feedback control. In this paper an algorithm for the realtime control of welding processes is described. It has been implemented onthe Eye-RIS v1.2, a visual system which mounts a cellular structure. Byapplying this algorithm in real time applications, controlling rates of about7 kHz can be reached. In the following some real time control results arealso described.

[学科分类] 电子、光学、磁材料