关键词: 磁光图像, 跟踪, 卡尔曼滤波, 微间隙焊缝

Abstract: It is required that the laser beam focus spot be controlled to follow and track the weld joint accurately during butt joint laser welding. An approach for detecting and tracking the micro-gap (whose width is less than 0.1 mm) weld position based on Kalman filtering during butt joint laser welding is presented. A magneto-optical sensor is used to capture the micro-gap weld image sequence, and the weld position coordinate is extracted by analyzing the gray scale gradient feature of images. The state equation and measurement equation for weld position are established based on the eigenvector derived from the weld position and displacement variables. Considering that the system dynamic noise and measurement noise are Gauss white noises with zero mean random distribution, a Kalman filter algorithm is established, which could reduce the influence of system and process noises on the weld position measurement. The optimal state estimation of weld centre ordinates could be obtained through the optimal state estimation of weld position under the least squares condition. Laser welding experimental results show that the proposed method could accurately predict the micro-gap weld position during the butt joint laser welding.

Key words: Kalman filtering, magneto-optical image, micro-gap weld, tracking