Automatic detection of welding defects using radiography with a neural approach

Yahia, Noureddine Ben; Belhadj, T.; Brag, S.; Zghal, Ali

doi:10.1016/j.proeng.2011.04.112

Cited by 13 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method of welding defect classification could be including feature extraction [1][2][3][4][5][6][7][8], thermal image analysis and ultrasonic inspection [9][10][11], and image histogram [12][13][14][15][16].…”

Section: Classification Of Welding Defectsmentioning

confidence: 99%

Classification of Welding Defects Using Gray Level Histogram Techniques via Neural Network. (Dept. M. ( Production ) )

Khalifa

Abouelatta

Gadelmawla

et al. 2020

Bulletin of the Faculty of Engineering. Mansoura University

View full text Add to dashboard Cite

Technological development accompanied the need to get a high-quality welding. The important industries such as oil and auto industries and other important industries need to rely on reliable welding operations; collapse as a result of this welding may mean a great loss in lives and money. This paper aimed to produce an automatic system to detect, recognize and classify welding cases (defects and no defects) in radiography images was described depending upon image histogram technique. Two main steps to do that, In the first step, image processing techniques, including converting color images to gray scale, filtering image, and resizing were implemented to help in the image array of weld images and the detection of weld defects. The second step, a proposed program was build in-house depending upon Matlab to classify and recognize automatically six types of weld defects met in practice, it is Porosity -Undercut -Lac of fusion -Crack -Slag -Cavity, plus the non-defect type. It was clear from the results that it can rely on this method significantly, reaching rates as well as the appointment of defects and no defects to about 94.3%.

show abstract

Section: Classification Of Welding Defectsmentioning

confidence: 99%

Classification of Welding Defects Using Gray Level Histogram Techniques via Neural Network. (Dept. M. ( Production ) )

Khalifa

Abouelatta

Gadelmawla

et al. 2020

Bulletin of the Faculty of Engineering. Mansoura University

View full text Add to dashboard Cite

show abstract

“…Subsequently, they perform the extraction of the weld bead, as well as the extraction and classification of defects. Most traditional approaches include different models of neural networks ( [10], [12], [20], [60]), neural network combined with binary logic ( [13]), surface thresholding method ( [61]), neuro-fuzzy (ANFIS) ( [19]), support vector machine (SVM) ( [22]), as well as approaches with more than one model like fuzzy, KNN and neural networks ( [9]); minimum distance, KNN and fuzzy KNN ( [14]); SVM, neural networks and KNN ( [18]). There are few studies reported in the literature based on the DWDI exposure technique, and they are presented below.…”

Section: Related Approachesmentioning

confidence: 99%

A Deep Artificial Immune System to Detect Weld Defects in DWDI Radiographic Images of Petroleum Pipes

2019

View full text Add to dashboard Cite

In recent years, research focused on (semi)automatic radiographic inspection methods has gained more attention. The present work proposes a method for detecting defects in radiographic images of welded joints of oil pipes. Real condition images obtained by the double wall double image (DWDI) technique usually present a lower quality when compared with images traditionally considered in many studies reported in the literature. First, the proposed approach detects discontinuities in DWDI radiographic images of welded joints, and then, based on a hybrid paradigm encompassing artificial immune systems (AIS) and deep learning (DL), it classifies each discontinuity as 'defect' and 'non-defect'. The proposed method performs two phases in the AIS module: early classification (based on negative selection) and evolving classification (based on clonal selection). In both phases, the pattern recognition task is performed using a set of features extracted from each discontinuity through a detector genetically encoded into immune cells. As an attempt to improve the classification performance, DL models (AlexNet and autoencoders) are incorporated aiming to increase the number of extracted features. Experiments performed on a set of 727 discontinuities show that the proposed approach achieves an Fscore of 70.7%, outperforming each of its modules running by themselves: AlexNet with Fscore = 64.86% and AIS with Fscore = 66%. Considering the challenges imposed by real conditions on image acquisition-and the low rates of false negatives-, results demonstrate that the proposed approach can be used to assist in inspection works when dealing with DWDI images. INDEX TERMS Artificial immune systems, deep learning, radiographic images, discontinuities classification, defect detection.

show abstract

“…M is mean, s is standard deviation in window and R shows the maximum possible standard deviation of grey level [10]. This step inherently classifies one or two types of defects from others.…”

Section: Cmentioning

confidence: 99%

“…SBS (sequential backward selection) has been used to avoid computationally intractable exhaustive feature selection. Yahia et al proposed another welding defect detection method using radiographic images with neural approach [10]. This method essentially works on edge detection method based on MPC (multi-layer perceptron).…”

mentioning

confidence: 99%

Welding Defect Detection and Classification Using Geometric Features

Hassan

Awan²,

Jalil

2012

2012 10th International Conference on Frontiers of Information Technology

View full text Add to dashboard Cite

In this paper we present a welding defect detection system using radiographic images. Main goal is to craft a dependable system because a human evaluator is not a stable evaluator besides other humanoid constraints. We present a novel technique for the detection and classification of weld defects by means of geometric features. Firstly noise reduction is done as radiographic images contain noise due to several effects. After this we tend to localize defects with maximum interclass variance and minimum intra class variance. Further we move towards extracting features describing the shape of localized objects in segmented images. Using these shape descriptors (geometric features) we classify the defects by Artificial Neural Network.

show abstract

Automatic detection of welding defects using radiography with a neural approach

Cited by 13 publications

References 5 publications

Classification of Welding Defects Using Gray Level Histogram Techniques via Neural Network. (Dept. M. ( Production ) )

Classification of Welding Defects Using Gray Level Histogram Techniques via Neural Network. (Dept. M. ( Production ) )

A Deep Artificial Immune System to Detect Weld Defects in DWDI Radiographic Images of Petroleum Pipes

Welding Defect Detection and Classification Using Geometric Features

Contact Info

Product

Resources

About