Vision inspection system for the identification and classification of defects in MIG welding joints

Abstract

The variety of vision inspection systems for welding defects in the present manufacturing scenario is needed for overcoming certain limitations such as the problem of inaccuracy in the images, non-uniformed illumination, noise and deficient contrast, and confusion in defects if they occur in the same spot at the surface and subsurface. Hence, it is imperative to design a new vision inspection system which will enable to overcome the aforementioned problems in welding. A sophisticated new vision inspection system using machine vision has been developed for this study to identify and classify the surface defects of butt joint as per standard EN25817 in metal inert gas (MIG) welding. In this proposed vision system, images of welding surfaces are captured through a CCD camera. Four frames of sequence of images are obtained using four zones of LEDs using the front light illumination system in this method. From these images, the regions of interest are segmented and the average gray levels of the characteristic features of these images are calculated. The same process can be extended further to four zones (four quadrants) of four types of welded joints. Finally, welded joints can be classified into one of the four predefined ones based on the back-propagation neural network. The proposed system demonstrates an overall accuracy of 95% from the 80 real samples tested.

New directions for inline inspection of automobile laser welds using non-destructive testing

“…Unlike laser triangulation, the method does not provide a 3 dimensional weld profile, relying on an approach close to a visual inspection. The main disadvantages are the lack of precision, low inspection speed and especially the necessary hardware high cost [5,7].…”

Multisensor Inspection of Laser-Brazed Joints in the Automotive Industry

“…Therefore, EC signals relate only to the weld bead and base materials. In image-based inspection systems like simple visual inspection [4], image processing [5], laser vision [35], or near-infrared signals [36], any dust or dirt over the bead may be identified as false positive. These approaches also miss the ability of assessing conductivity variations potentially revealing One of the main advantages of the EC technique for this specific application relies on its lack of response to the presence of non-conductive materials.…”

“…In addition, these techniques' The four-point technique can be a great advantage when lack of fusion defects are present. Lack of fusion defects are located at the interface between the filler material and the sheet metal and not always open to the surface, becoming hardly detected by surfacescanning techniques such as visual inspection [4,5,35,36]. In addition, these techniques' output consists of multi-dimensional data for each measured point that must be stored The four-point technique can be a great advantage when lack of fusion defects are present.…”

“…Image processing of welded joint surfaces was used for defects' detection and classification. As no depth information can be retrieved, it is impossible to recover the joint profile, and therefore, results are close to those of visual inspection with the benefits of automation [5]. Buried defects lack of detection and low speed of inspection are again the main drawbacks of this option.…”

Detection and classification of surface defects of gun barrels using computer vision and machine learning

“…There are quite a number of features available to choose from depending on the application. Features based on texture description were found to give better results [7][8][9]. Automatic feature selection methods were not used widely.…”