Article

Vision based neurofuzzy logic control of weld pool geometry

Science and Technology of Welding & Joining (Impact Factor: 1.27). 09/2002; 7(5):321-325. DOI: 10.1179/136217102225006813

ABSTRACT The geometry of the weld pool contains accurate, instantaneous information about welding quality. Thus, weld pool sensing and control plays a significant role in automated arc welding. Previous studies have focused on inferring penetration through models and controlling penetration by various methods, such as adaptive control, model based fuzzy logic, etc. In the present work, a weld pool imaging system employing a LaserStrobe (tradename) high shutter speed camera is used to obtain contrasting images and eliminate arcing interference. Two image processing tools based on edge detection and connectivity analysis extract online information about the weld pool length and width. A neurofuzzy control system elicited from both human experience and experimental results has been developed to control the welding current and welding speed in real time based on changes in weld pool dimensions. Closed loop control of welding speed is used to achieve desirable weld pool geometry.

1 Bookmark
 · 
74 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: The present paper presents a method for weld location extraction in radiographic images. Images are processed line by line by applying fuzzy reasoning based on local pixel characteristics. For each pixel, values of spatial contrast and spatial variance are computed for evaluating the edge fuzzy membership value. The method proposed uses the machine learning approach for knowledge acquisition, which automatically generates fuzzy rules by learning from examples. Using this method, all welds are successfully extracted from 101 radiographic images taken from aluminium alloy welding parts.
    Science and Technology of Welding & Joining 12/2006; 12(1):63-66. · 1.27 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a vision system based on the use of a CMOS camera. The vision system has demonstrated its potential for applications of weld pool monitoring. It has been demonstrated in this study that the arc light can be successfully eliminated and that a substantial amount of information can be obtained in real time e.g. metal transfer in TIG welding and weld pool geometry, position and development. The system's design and components are detailed in this study including camera technology and selection, and a range of illumination techniques. A study on the welding spectra has helped greatly in the selection of an optimum spectral window where arc radiations are low. A combination of optical filtering, short pulse laser illumination and fast-shuttering imaging techniques along with precise synchronisation and very accurate triggering methods has enabled high quality images of the weld area irrespective of the brightness of the intense arc light. A number of illumination sources including pulsed and continuous wave (CW) lasers, laser diodes and LED illumination are used.
    Electronic Design, 2008. ICED 2008. International Conference on; 01/2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: A computer vision technique based on the real-time measurement and control of the upper surface or ‘topface’ weld pool size is discussed. The primary objective is to demonstrate the feasibility of using vision-based image processing to provide measurements and subsequent control of a weld's geometrical properties during the weld formation or molten phase. A novel reference feature – a correlation-based image analysis algorithm – has been developed, which may be configured to operate with a number of different welding processes. Upper surface weld pools with regulation via a simple classical feedback control algorithm have then been demonstrated to show how this approach may be used to improve weld uniformity and repeatability.
    Welding International 01/2011;