No abstract

Purpose -The control of weld penetration in gas tungsten arc welding (GTAW) is required for a "teach and playback" robot to overcome the gap variation in the welding process. This paper aims to investigate this subject. Design/methodology/approach -This paper presents a robotic system based on the real-time vision measurement. The primary objective has been to demonstrate the feasibility of using vision-based image processing to measure the seam gap in real-time and adjust welding current and wire-feed rate to realize the penetration control during the robot-welding process. Findings -The paper finds that vision-based measurement of the seam gap can be used in the welding robot, in real-time, to control weld penetration. It helps the "teach and playback" robot to adjust the welding procedures according to the gap variation.Research limitations/implications -The system requires that the seam edges can be accurately identified using a correlation method. Practical implications -The system is applicable to storage tank welding of a rocket. Originality/value -The control algorithm based on the knowledge base has been set up for continuous GTAW. A novel visual image analysis method has been developed in the study for a welding robot.

The application of recognition for the weld seam and its initial position in a complicated environment based on the image pattern match technology has been discussed. According to adopting the two-step pattern match method, the recognition speed and accuracy have been improved, and the error points have been wiped off during the global pattern match stage by using the area analysis method. The initial position can be accurately recognized by using the method that dynamically adjusts the search area during the local pattern match stage in the area that is near the end of the weld. The results of the experiments prove that this method not only has the characters that include anti-jamming, fast running speed and high recognition, but also has a preferably practical value.

No abstract

The arc welding process is so complex that the classical modeling method cannot obtain the model effectively. However, the model of the arc welding process is necessary for the intelligent control of the process. Therefore, the modeling has been the interest of many researchers. Recently, more and more researchers are attempting to obtain the model of the process by means of intelligent methods, such as the neural network method, the fuzzy set method, and so on. All these methods concentrate on simulating the intelligent behavior of human beings, namely using human experience. Many applications of these methods have proved their effectiveness under certain conditions. However, their limits are obvious and further research is needed. This paper proposes a method of rough set based knowledge modeling for the aluminum alloy pulsed gas tungsten arc welding (GTAW) process. Owing to the ability of dealing with knowledge (experience) of the rough set theory, the method can obtain the knowledge model of the aluminum alloy pulsed GTAW process. The model obtained is easily understood and revised. Experiment results indicate that the method is effective. The method can be regarded as the basis of the intelligent control of the welding process.