• Journal of Welding and Joining
• /
• v.13 no.4
• /
• pp.132-146
• /
• 1995

Flaw classification(determination of the flaw type) and flaw sizing (prediction of the flaw shape, orientation and sizing parameters) are very important issues in ultrasonic nondestructive evaluation of weldments. In this work, new techniques for both classification and sizing of flaws in weldments are described together with extensive review of previous works on both topics. In the area of flaw classification, a methodology is developed which can solve classification problems using probabilistic neural networks, and in the area of flaw sizing, a time-of-flight equivalent(TOFE) sizing method is presented.

• Journal of the Korean Society of Safety
• /
• v.12 no.2
• /
• pp.3-16
• /
• 1997

In modern high performance engineering applications, the structural integrity of materials and structures are quite often evaluated using fracture mechanics. This evaluation in turn requires information on the flaw geometry (location, type, shape, size, and orientation). The ultrasonic nondestructive evaluation (NDE) method is one technique that is commonly used to provide such information. Flaw classification (determination of the flaw type ) and flaw sizing (prediction of the flaw shape, orientation and sizing parameters) are very important issues for quantitative ultrasonic NDE. In this paper new approaches to both classification and sizing of flaws are described together with extensive review of previous works on both topics. In the area of flaw classification, a methodology is developed which can solve classification problems using probabilistic neural networks, and in the area of flaw sizing, a time-of-flight equivalent (TOFE) sizing method is presented. The techniques proposed here are in a form that can be used directly in many practical applications to quantitative estimates of the flaw's significance.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.393-396
• /
• 1995

In this syudy, the researches classifying the artificial and natural flaws in welding parts are performed using the smart pattern recognition technology. For this purpose the smart signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing,feature extraction , feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear disciminant function classifier, the empirical Bayesian classifier. Also, the smart pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack,lack of penetration,lack of fusion,porosity,and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately learned the neural network classifier is better than ststistical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 1996.11a
• /
• pp.167-176
• /
• 1996

Flaw classification and sizing are very essential issues in quantitative ultrasonic nondestructive evaluation of various materials and structures including weldments. For performing of these tasks in an automated fashion, we are developing an intelligent ultrasonic evaluation system with a multi-axis portable scanner which can do consistent and efficient acquisition and processing of ultrasonic flaw signals. Here we present our efforts to develop of this intelligent system including design of the portable scanner, acquisition and processing of ultrasonic flaw signals, display of pseudo 3-D image of flaws, and classification and sizing of flaws in weldments.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.1
• /
• pp.119-127
• /
• 2000

In this study the classified researches the artificial and natural flaws in welding parts are performed using the pattern recognition technology. For this purpose the signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing feature extraction feature selection and classifi-er selection is teated by bulk,. Specially it is composed with and discussed using the statistical classifier such as the linear discriminant function the empirical Bayesian classifier. Also the pattern recognition technology is applied to classifica-tion problem of natural flaw(i.e multiple classification problem-crack lack of penetration lack of fusion porosity and slag inclusion the planar and volumetric flaw classification problem), According to this result it is possible to acquire the recognition rate of 83% above even through it is different a little according to domain extracting the feature and the classifier.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.19 no.5
• /
• pp.378-391
• /
• 1999

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.6
• /
• pp.658-662
• /
• 2001

The classification of surface flaw types was performed on the basis of angular dependence of backscattered ultrasound. The copper line adhered on the surface, cower line filled in groove, pure groove and the normal edge were adopted as various surface flaw patterns of glass specimen. A backward longitudinal profile was formed probably by the longitudinal wane scattering at and near 1st critical angle. The wave trains at the peak angles of the backward radiation profiles showed different shapes according to the superposition ratio of scattered and leaky waves. The asymmetry of the backward radiation profile arose due to the scattering effect of flaw. The additive resonance effect of copper line appeared in the left side of the profile. The peak angles of both the longitudinal and radiation profiles were shifted toward small angle by the scattering effect.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.20 no.2
• /
• pp.102-109
• /
• 2000

This paper describes two different theories used to model the scattering of ultrasound by a volumetric flaw and a crack-like flaw. The elastodynamic Kirchhoff approximation (EKA) and the geometrical theory of diffraction (GTD) are applied respectively to a cylindrical cavity and a semi-infinite crack. These methods are known as high frequency approximations. The 2-D elastodynamic scattering problems of a plane wave incident on these model defects are considered and the scattered fields are expressed in terms of the reflection and diffraction coefficients. The ratio of the scattered far field amplitude to the incident wave amplitude is computed as a function of the angular location and compared with the boundary element solutions.

• Nuclear Engineering and Technology
• /
• v.51 no.7
• /
• pp.1784-1790
• /
• 2019

Accurate and consistent characterization of defects in steam generator tubes (SGT) in nuclear power plants is one of the key issues in the field of nondestructive testing since the large number of signals to be analyzed in a time-limited in-service inspection causes a serious problem in practice. This paper presents an effective approach to this difficult task of automated classification of motorized rotating pancake coil (MRPC) eddy current flaw acquired from tube specimens with deliberated defects using deep neural networks (DNN). This approach consists of five steps, namely, the data acquisition using the MRPC probe in the tube, the signal preprocessing to make data more suitable for training DNN, the data augmentation for boosting a training performance, the training of DNN, and finally demonstration of the trained DNN for discriminating the axial and circumferential defects. The high performance obtained in this study shows that DNN is useful for classification of defects in tubes from the MRPC eddy current signals even though the number of signals is very large.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.304-309
• /
• 2003

In this study, natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.