328 溶融池裏面情報を用いた固定管の全周溶接制御システムの開発(OS 加工・検査のロボット化・知能化)

概要

論文の詳細を見る
In order to obtain sound welded joints in the welding of horizontal fixed pipes, it is important to control the back bead width in the first pass. However, it is difficult to obtain optimum back bead width, because the proper welding conditions change with welding position. Besides, because welding heat accumulates in the joint area of the pipe, the temperature rises with the progress of the time. Now, in this paper, a new method is developed to sensing of weld pool condition and control of penetration in fixed pipe welding from reverse side. As it is difficult to measure the back bead width directly, it is estimated by analyzing the shape and the dimensions of the molten pool images. Artificial Neural Network is used to estimate the relations among the parameters of the weld pool shape, welding conditions and the penetration of weld. The back bead width is controlled by optimizing the welding current estimated from the output of the Artificial Neural Network. As a result of welding control experiments, the effectiveness of this system for the penetration control of fixed pipes is demonstrated.
一般社団法人日本機械学会の論文
2001-11-02