Welds have been inspected by radiography for years, but this technology has major drawbacks: low detection rates for critical planar defects (i.e. cracks and lack of fusion), subjective interpretation, no vertical sizing capability, significant safety hazards, licensing issues, plant closures, and generally slow inspection rates. For decades, the main alternative was manual ultrasonics, which i...

Automated and intelligent classification of defects can improve productivity, quality, safety various welded components used in industries. This study presents a transfer learning approach for accurate tungsten inert gas (TIG) welding while joining stainless steel parts. In this approach, eight pre-trained deep models (VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV...

In this paper, a method for the detection and classification of defects in weld radiographs is presented. The method has been applied for detecting and discriminating discontinuities in the weld images that may correspond to false alarms or defects such as worm holes, porosity, linear slag inclusion, gas pores, lack of fusion or crack. A set of 43 descriptors corresponding to texture measuremen...

Both laser-arc hybrid welding and narrow gap welding have potential for the fabrication of thick sections, but their combination has been seldom studied. In this research, 40 mm thick mild steel was welded by narrow gap laser-arc hybrid welding. A weld with smooth layer transition, free of visible defects, was obtained by nine passes at a 6 mm width narrow gap. The lower part of the weld has th...

Received Sep 9, 2017 Revised Dec 20, 2017 Accepted Jan 7, 2018 Welding is a fabrication of joining materials into one component. Defects are unavoidable during the welding process, and hence the inspection of welds is a most important task in many industries. In this work, a Computer Aided Detection (CAD) system is designed to detect weld defects based on image processing techniques. It is a no...

This paper presents an approach that is based on the combined use of Dempster-Shafer (DS) theory and fuzzy sets for improving automatic detection of weld defects. It consists in modelling detection uncertainty in feature space through using the mass function weighted by membership degrees, and fusing the features of objects using DS combination rule. The method is demonstrated on the typical in...

Method: A continuous non-contact scanning method is used in the rectangular slot defect in the different regions of the weld by using a new magnetization system that is vertical to the travelling direction. The characteristics of the weld and the defect are transformed into accurate two-dimensional grayscale graphics through grayscale linear transformation. This is done through the combination ...

Welding is an area in which technological developments out match the developments in its science base, which is primarily driven by the phenomenal industrial demand for welded structure. Reliability, Reproducibility and Viability requirements are forcing Technologists to look at weld defects such as distortion, hot cracking, in a systematic and logical approach than on adhoc basis. Distortion i...

A novel microwelding procedure to join Si-to-glass using ps-laser pulses with high repetition rates is presented. The procedure provides weld joint with mechanical strength as high as 85 MPa and 45 MPa in sample pairs of Si/aluminosilicate (Si/SW-Y) and Si/borosilicate (Si/Borofloat 33), respectively, which are higher than anodic bonding, at high spatial resolution (< 20 µm) and very high throu...

In this paper we present a new approach to detecting weld defects from digitalised films based on texture features. Texture is one of the most important features used in recognising patterns in an image. However, these features are not yet commonly exploited in the analysis of X-ray images in NDT. The paper describes two groups of widely used texture features: 1) features based on the cooccurre...