Seam Tracking Technology for Hyperbaric Underwater Welding

Automatic weld seam tracking technology to be used in hyperbaric underwater damaged pipeline repair welding is much more important, because of poor bevel preparation and severe working condition. A weld seam tracking system based on digital signal processing（DSP） passive light weld image processing technology has been established. A convenient charge coupled device（CCD） camera system was used in the high pressure environment with the help of an aperture and focus altering mechanism to guarantee overall image visibility in the scope of pressure below 0.7 MPa. The system can be used in the hyperbaric environment to pick up the real welding image of both the welding arc and the welding pool. The newly developed DSP technology was adopted to achieve the goal of system real time characteristics. An effective weld groove edge recognition technique including narrow interesting window opening, middle value wave filtering, Sobel operator weld edge detecting and edge searching in a defined narrow area was proposed to remove the guide error and system accuracy was ensured. The results of tracking simulation and real tracking application with arc striking have proved the validity and the accuracy of the mentioned system and the image processing method.

Novel welding image processing method based on fractal theory

Computer vision has come into used in the fields of welding process control and automation. In order to improve precision and rapidity of welding image processing, a novel method based on fractal theory has been put forward in this paper. Compared with traditional methods, the image is preliminarily processed in the macroscopic regions then thoroughly analyzed in the microscopic regions in the new method. With which, an image is divided up to some regions according to the different fractal characters of image edge, and the fuzzy regions including image edges are detected out, then image edges are identified with Sobel operator and curved by LSM (Lease Square Method). Since the data to be processed have been decreased and the noise of image has been reduced, it has been testified through experiments that edges of weld seam or weld pool could be recognized correctly and quickly.

Laser-based manufacturing concepts for efficient production of tailor welded sheet metals

Laser welding is an established manufacturing technology for a large variety of automotive applications due to its attractive properties such as low heat input, high precision and fast welding speed. Especially when welding high strength steels, which are dominantly used in today＇s car body construction, the low heat input by laser welding bears significant advantages with regard to the properties of the weld seam. The exploitation of the full application potential of laser welding in mass production requires an appropriate manufacturing concept and corresponding auxiliary technologies. The present paper demonstrates the integration of laser welding into the surrounding manu- facturing concepts by a modular setup with different levels of automation. This approach offers flexible solutions for individual needs thereby optimizing investment cost, labor cost and productivity. Recently available laser sources enable exceptionally high welding speed on thin gauged sheet metals but require efficient material handling con- cepts to utilize the full speed potential. Industrial concepts are presented offering efficient material handling and high process robustness for mass production welding.