Vision-based Sensing Of Weld Pool Geometry In MAG Welding Of Short-Circuiting Transfer

With the development of welding process automation, a higher demand is expected on the on-line quality monitoring. Since the weld pool contains explicit and abundant information about the welding quality, the geometry of the weld pool has a great effect on the formation and quality of the welded joint. Detecting the weld pool geometrical parameters from topside of work piece with visual sensor is of great theoretical and practical significance in verifying the numerical simulation results of welding thermal process, realizing the on-line quality monitoring and controlling weld penetration.According to the MAG welding of short-circuiting transfer process in which arc light, spatter, smoke dust and other interference exist, a visual-based sensing system is designed. Through the analysis of the arc spectrum, a composite light-filter is determined to eliminate the disturbance of the arc light. A proper sampling time is selected. A short-circuit detection and CCD camera ex-trigger circuit is developed based on the welding voltage waveform. The exposure time is fixed at the moment of short circuit, which solves the problems caused by the surrounding luminance and spatter interference. Grabbed from the front position with small angle and the rear position with large angle, uninterrupted, clear and undistorted images of weld pool are obtained using the ordinary industrial CCD camera.Based on the analysis of the weld pool images, a series of image processing algorithms are developed to extract the whole weld pool edge, including the 7×7 square median filtering, edge-enhanced algorithm and dynamic searching algorithm. According to the calibration result of the pinhole camera, the geometrical parameters of weld pool are acquired.The weld pool geometrical parameters including the length, the width and the breadth length ratio are acquired under different welding current, welding speed and contact tube-to-workpiece. The regularity with the welding parameters, the weld pool geometry and weld penetration changing respectively is analyzed.Combined with the weld pool images captured from the side direction, the reason that causes error in the weld pool length obtained from the topside sensing is analyzed. The original measurement is modified based on the weld pool gradient. A new method that the topside sensing is combined with the results acquired from the side detection is adopted...