Nobuo Shibata

Development of groove recognition algorithm with visual sensor. Practical development of visual sensor for welding robot (1st Report)

Summary To improve the automation or artificial intelligence of welding operations, it is necessary to develop high-performance sensors. Laser visual sensors are designed to recognise the configuration or detect the position of a weld by irradiating a slit light on to the welded joint, receiving the light with a CCD camera, and converting the two-dimensional information into three-dimensional information by image processing. The visual sensors for welding robots must be free from the influences of welding process disturbances, such as arc light, heat, spatter and fume. This paper describes optical component arrangements and image processing algorithms. The optical component of a sensor head helps avoid optical window contamination caused by spatter or fume. The image processor used can process image data quickly and accurately even if welding arc light illuminates the workpiece surface. The accuracy of weld position detection is within ±0.2 mm.

Development of torch position control and welding condition control technology for all‐position, multi‐layer GTA welding. Development of fully automatic GTA welding system for pipes (2nd Report)

Various welding operations involved in the construction of power generation plants, chemical plants, etc. requiring high standards of weld quality have routinely been performed by trained welders. Various occupational factors, such as what is known in Japan as 3K (kiken, kitsui, kitanai = dangerous, arduous, dirty) working as well as the shortage and advancing age of trained welders, have led to a growing demand for full automation of welding. To enable welding operations to be performed without the physical attendance or technical skills of human operatives, the authors have been previously engaged in the development of an all-position fully automatic GTA welding system providing advanced sensing functions and appropriate welding control functions of a nature and scope able to replace trained welders. Focused on stainless steel pipes, the proposed system offers a range of fully automatic welding and quality assurance functions from initial layer back welding, including tack welding, to final pass welding and appearance inspection of each welding pass. The first report describes the development of a wire height position control technology able to prevent electrode damage and poor weld bead quality due to wire deposition and wire contact. This report initially outlines the functions of the proposed fully automatic GTA welding system, then describes the laser slit sensor, the technology for measurement of the dimensions of the groove fitted with blocks (joint assembly attachments), the torch position tracking control technology in each welding pass and the technology for adaptive control of welding conditions. The results achieved by the system in multi-layer welding of pipes are finally evaluated.