Higher-Order Statistics for Automatic Weld Defect Detection

Saber, Sara; Selim, Gamal M.

doi:10.4236/jsea.2013.65031

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it primarily enables the detection of cracks developing in a plane perpendicular to the path of the beam [89]. Figure 6 illustrates the principles of gamma radiography [90].…”

Section: X-ray Radiographymentioning

confidence: 99%

Review of Nondestructive Testing Methods for Aerospace Composite Materials

Shetu

2024

J. Comput. Mech. Manag

View full text Add to dashboard Cite

Composite structures and materials have seen significant advancements in cost-effectiveness, product eﬀiciency, and specific properties, leading to their extensive use in the aerospace industry. Reliable nondestructive testing (NDT) of composites is crucial for reducing maintenance costs and addressing safety concerns. This review provides a comprehensive analysis of various NDT methods, including Ultrasonic Testing, Acoustic Emission, Eddy Current Testing, Shearographic Testing, Infra-Red Thermography, and X-Ray Radiography. Each method’s principles, instruments, and applications for defect detection and damage evaluation in composite materials are thoroughly examined. The paper highlights the strengths and limitations of these NDT techniques, emphasizing their roles in ensuring the structural integrity of aerospace composites. Ultrasonic Testing and Infra-Red Thermography are identified as flexible and cost-effective solutions, widely applied in both academic research and industrial sectors. Despite the challenges in providing a complete diagnostic of structural integrity, each NDT method offers unique advantages. Future research in NDT for composites will focus on integrating advanced data processing techniques, such as machine learning and deep learning, and developing smart inspection systems with high precision and rapid data processing capabilities.

show abstract

“…However, it primarily enables the detection of cracks developing in a plane perpendicular to the path of the beam [89]. Figure 6 illustrates the principles of gamma radiography [90].…”

Section: X-ray Radiographymentioning

confidence: 99%

Review of Nondestructive Testing Methods for Aerospace Composite Materials

Shetu

2024

J. Comput. Mech. Manag

View full text Add to dashboard Cite

show abstract

“…A defect detection method based on multistage processing of the image, with the subsequent classification using a neural network was proposed in work. 12 At the initial stage, the image was pre-processed by reducing the noise component using the Wiener filter, improving the contrast of the image using an adaptive histogram enhancing (AHE). 13 A discrete wavelet transform was employed to reduce the area for further processing.…”

Section: Related Workmentioning

confidence: 99%

Automatic detection of welding defects using the convolutional neural network

Sizyakin

Voronin

Gapon

et al. 2019

Automated Visual Inspection and Machine Vision III

View full text Add to dashboard Cite

Quality control of welded joints is an important step before commissioning of various types of metal structures. The main obstacles to the commissioning of such facilities are the areas where the welded joint deviates from acceptable defective standards. The defects of welded joints include non-welded, foreign inclusions, cracks, pores, etc. The article describes an approach to the detection of the main types of defects of welded joints using a combination of convolutional neural networks and support vector machine methods. Convolutional neural networks are used for primary classification. The support vector machine is used to accurately define defect boundaries. As a preprocessing in our work, we use the methods of morphological filtration. A series of experiments confirms the high efficiency of the proposed method in comparison with pure CNN method for detecting defects.

show abstract

“…The efficiency in terms of computation complexity was improved by this methodology. Sara saber et al [3] proposed an algorithm for automatic detection of weld defects in radiographic images. First the mage was enhanced using adaptive histogram equalization and followed by filtering action using mean and wiener filters.…”

Section: Related Workmentioning

confidence: 99%

DWT Based Automated Weld Pool Detection and Defect Characterisation from Weld Radiographs

Sudheera

Nandhitha

Mohanachandran

et al. 2014

AMR

View full text Add to dashboard Cite

Industrial Radiography is the most widely accepted NDT technique for weld quality in industries. As it is an indirect method, defect type and nature must be obtained by analyzing the radiographs. Manual interpretation of radiographs is subjective in nature. So the paradigm shifted to automated weld defect detection system. Though considerable research is done in automated weld defect detection, an accurate domain specific technique has not yet been evolved due to noise, artifacts in radiographs, low contrast between the defect region and the background and difficulty in isolating the defect. The proposed work aims at developing an automated weld defect detection system that enhances the contrast between the object and the background and isolates the weld defect. In this work, real time weld radiographs are acquired and contrast enhancement is performed with DWT. Slag and Porosity are isolated and dimensionally characterized.

show abstract

Higher-Order Statistics for Automatic Weld Defect Detection

Cited by 5 publications

References 21 publications

Review of Nondestructive Testing Methods for Aerospace Composite Materials

Review of Nondestructive Testing Methods for Aerospace Composite Materials

Automatic detection of welding defects using the convolutional neural network

DWT Based Automated Weld Pool Detection and Defect Characterisation from Weld Radiographs

Contact Info

Product

Resources

About