This paper introduces an intelligent system for monitoring and recognition of process disturbances during short-short-Cirutiong gas-metal arc welding. It is based on the measured and statisticlly processed dataof welding electrical parameters. A 12-dimensional array of process features is designed to describevarious welding conditions and is employed as input vector of the intelligent system. Three methods, Such as fuzzy c-means, neural netowrk and fuzzy Kohonen clustering network areused to conduct process monitoring and automatic recognition. The correct recoginition rates of these three methods are compared.

This paper is concerned with numerical studies of the anode region of a high-intensity argon arc. The anode region is divided into three subzones: the anode boundary layer, the presheath and the sheath. The governing equations of the dominating processes with the boundary conditions taken from the solutions of LTE plasmas are solved by applying the Runge

在分析TIG焊接弧光谱的基础上，设计出复合滤光镜头，与普通CCD摄像机组成视觉传感器，从试件正面观测熔池图像。焊接过程中根据电流大小通过软件调整采集图像亮度，得到了比较清晰的TIG焊接熔池图像。利用自行开发的图像处理算法。检测出了熔池正面的形状参数。该算法处理一幅图像像用时不超过70ms，满足实时检测的需要。

It is of great significance to determine the sheath potential of gas tungsten arcs because it has a marked e ect on the heat flux at the anode. In this paper one of the parameters a, i.e., the percentage of the electrons entering the lattice of anode, is introduced for determining the sheath potential. The results indicate that the sheath potential is strongly dependent on the parameter a which is used to make a di erence between an anode conducting electricity and a cool wall isolated. For determining the sheath potential, a formula is established, which takes account of the electron temperature, the electron flux and the ion flux at the free-fall edge as well as the parameter α.

The common commercial charge coupled device (CCD) camera is combined with a composite light filter to form a vision sensing system of low cost. It can capture the whole image of a weld pool clearly during constant-current gas tungsten arc welding (GTAW). Based on the imageprocessing algorithm, the edges of the weld pool under di erent welding conditions can be extracted. Calibration is made to obtain the weld pool geometry in real size. The measured results are useful for developing a welding process control system and verifying the mathematical models of weld pool behaviours.