• Tribology and Lubricants
• /
• v.24 no.6
• /
• pp.332-337
• /
• 2008

This paper presents the surface defect analysis based on the experimental investigation of scribed glasses. The scribing process by a diamond wheel cutter is widely used as a reliable and inexpensive method for sizing of glass sheets. The wheel cutter generates a small median crack on the glass surface, which is then propagated through the glass thickness for complete separation. The surface contour patterns in which are formed during a scribing process are strongly related to wheel cutter parameters such as wheel tip surface finish, tip angle and wheel diameter, and cutting process parameters such as scribing pressure, speed and tooling technique. The scribed surface of a glass sheet provides normal Wallner lines, which represent regular median cracks and crack propagation in glass thickness, and abnormal surface roughness patterns. In this experimental study, normal and abnormal surface topographic patterns are classified based on the surface defect profiles of scribed glass sheets. A normal surface of a scribed glass sheet shows regular Wallner lines with deep median cracks. But some specimens of scribed glass sheets show that abnormal surface profiles of glass sheets in two pieces are represented by a chipping, irregular surface cracks in depth, edge cracks, and combined crack defects. These surface crack patterns are strongly related to easy breakage of the scribed glass imposed by external forces. Thus the scribed glass with abnormal crack patterns should be removed during a quality control process based on the surface defect classification method as demonstrated in this study.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.2
• /
• pp.65-70
• /
• 2003

In this study, researchers developed the estimative algorithm for artificial defect in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages : Crack, Delamination and Normal. According to the results, we were confirmed that estimative algerian was provided the recognition rates of 75.7% (for Crack) and 83.4% (for Delamination) and 87.2 % (for Normal).

• Transactions of Materials Processing
• /
• v.27 no.2
• /
• pp.100-106
• /
• 2018

In the continuous casting process, the incidence of transverse surface cracks on the piece may occur by multiple and diverse variables. It is noted that mathematical models may predict only the occurance of the transverse surface cracks, but can require a lot of time (more than three days) to produce a result with this process. This study applied neural networks to predict whether the cracks on the piece surface occurs or does not occur. The computation time was shortened to three minutes, making it applicable to an on-line program, which predicts the non-cracks or cracks of the piece surface in the actual continuous casting process. In addition, the operating conditions to prevent the occurrence of the transverse surface cracks, using decision boundaries were also suggested.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.331-332
• /
• 2023

With the aging of buildings, the number and importance of regular inspections of buildings are increasing. The current safety inspection goes through a procedure in which a skilled technician visits an old building, visually checks it, takes a photo, and finally organizes and judges it at the office. For this, field personnel and analysis and review personnel are required. Since the inspection procedure includes taking pictures, a huge amount of data has been accumulated from the time digital photos were used to the present. When a model that can check cracks outside a building is developed using these data, manpower and time required can be greatly reduced. Therefore, this study aims to create a model for classifying cracks that occur outside the building through the artificial intelligence method. The created model can be used as a basic model for determining cracks only by external photography in the future, and furthermore, it can be used as basic data for calculating the size and width of cracks.

• Journal of applied mathematics & informatics
• /
• v.8 no.1
• /
• pp.59-69
• /
• 2001

The paper deals with the interaction between three Griffith cracks propagating under antiplane shear stress at the interface of two dissimilar infinite elastic half-spaces. The Fourier transform technique is used to reduce the elastodynamic problem to the solution of a set of integral equations which has been solved by using the finite Hilbert transform technique and Cooke’s result. The analytical expressions for the stress intensity factors at the crack tips are obtained. Numerical values of the interaction efect have been computed for and results show that interaction effects are either shielding or amplification depending on the location of each crack with respect to other and crack tip spacing. AMS Mathematics Subject Classification : 73M25.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.1 s.173
• /
• pp.52-61
• /
• 2000

The role of quantitative nondestructive evaluation of defects is becoming more important to assure the reliability and the safety of structure, which can eventually be used for residual life evaluation of structure on the basis of fracture mechanics approach. Although ultrasonic technique is one of the most widely used techniques for application of practical field test among the various nondestructive evaluation technique, there are still some problems to be solved in effective extraction and classification of ultrasonic signal from their noisy ultrasonic waveforms. Therefore, crack size determination through a neural network based on the back-propagation algorithm using back-scattered ultrasonic signals is established in this study. For this purpose, aluminum plate containing vertical or inclined surface breaking crack with different crack length was used to receive the back-scattered ultrasonic signals by pulse echo method. Some features extracted from these signals and sizes of cracks were used to train neural network and the neural network's output of the crack size are compared with the true answer.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.5
• /
• pp.463-470
• /
• 2015

Solar cell is typical representative of renewable green energy. Silicon wafer contributes about 66 percent to its cost structure. In its manufacturing, micro-cracks are often occurred due to manufacturing process such as wire sawing, grinding and cleaning. Their detection and classification are important to process feedback information. In this paper, a classification method of micro-cracks is proposed, based on the fusion of principal component analysis(PCA) and neural network. The proposed method shows that it gives higher results than single application of two methods, in terms of shape and size classification of micro-cracks.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.12
• /
• pp.145-154
• /
• 2018

The damage investigation and inspection methods performed in concrete facilities such as bridges, tunnels, retaining walls and so on, are usually visually examined by the inspector using the surveying tool in the field. These methods highly depend on the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, the new image processing techniques are necessary in order to automatically detect the cracks and objectively analyze the characteristics of cracks. In this study, deep learning and image processing technique were developed to detect cracks and analyze characteristics in images for concrete facilities. Two-stage image processing pipeline was proposed to obtain crack segmentation and its characteristics. The performance of the method was tested using various crack images with a label and the results showed over 90% of accuracy on crack classification and segmentation. Finally, the crack characteristics (length and thickness) of the crack image pictured from the field were analyzed, and the performance of the developed technique was verified by comparing the actual measured values and errors.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• International journal of steel structures
• /
• v.18 no.5
• /
• pp.1589-1597
• /
• 2018

Fatigue tests and numerical analysis were carried out to evaluate the fatigue performance at the U-rib to deck welded joint in steel box girder. Twenty specimens were tested corresponding to different penetration rates (80 and 100%) under fatigue bending load, and the fatigue strength was investigated based on hot spot stress (HSS) method. The detailed stress distribution at U-rib to deck welded joint was analyzed by the finite element method, as well as the stress intensity factor of weld root. The test results show that the specimens with fully penetration rate have longer crack propagation life due to the welding geometry, resulting in higher fatigue failure strength. The classification of FAT-90 is reasonable for evaluating fatigue strength by HSS method. The penetration rate has effect on crack propagation angle near the surface, and the 1-mm stress below weld toe and root approves to be more suitable for fatigue stress assessment, because of its high sensitivity to weld geometry than HSS.