• Journal of the Semiconductor & Display Technology
• /
• v.15 no.3
• /
• pp.6-11
• /
• 2016

Silicon wafer is one of main materials in solar cell. Micro-cracks in silicon wafer are one of reasons to decrease efficiency of energy transformation. They couldn't be observed by human eye. Also, their shape is not only various but also complicated. Accordingly, their shape classification is absolutely needed for manufacturing process quality and its feedback. The performance of typical classification techniques which is principal component analysis(PCA), neural network, fusion model to integrate PCA with neural network, and support vector machine(SVM), are evaluated using pattern features of micro-cracks. As a result, it has been confirmed that the SVM gives good results in micro-crack classification.

• International Journal of High-Rise Buildings
• /
• v.9 no.4
• /
• pp.351-360
• /
• 2020

Monitoring civil structures periodically is necessary for ensuring the fitness of the structures. Cracks on inner and outer surfaces of the building plays a vital role in indicating the health of the building. Conventionally, human visual inspection techniques were carried up to human reachable altitudes. Monitoring of high rise infrastructures cannot be done using this primitive method. Also, there is a necessity for more accurate prediction of cracks on building surfaces for ensuring the health and safety of the building. The proposed research focused on developing an efficient crack classification model using Transfer Learning enabled EfficientNet (TL-EN) architecture. Though many other pre-trained models were available for crack classification, they rely on more number of training parameters for better accuracy. The TL-EN model attained an accuracy of 0.99 with less number of parameters on large dataset. A bench marked METU dataset with 40000 images were used to test and validate the proposed model. The surfaces of high rise buildings were investigated using vision enabled Unmanned Arial Vehicles (UAV). These UAV is fabricated with TL-EN model schema for capturing and analyzing the real time streaming video of building surfaces.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.9
• /
• pp.715-721
• /
• 2016

In this paper, the classification rate of micro-cracks in silicon wafers was improved using a SVM. In case I, we investigated how feature data of micro-cracks and SVM parameters affect a classification rate. As a result, weighting vector and bias did not affect the classification rate, which was improved in case of high cost and sigmoid kernel function. Case II was performed using a more high quality image than that in case I. It was identified that learning data and input data had a large effect on the classification rate. Finally, images from cases I and II and another illumination system were used in case III. In spite of different condition images, good classification rates was achieved. Critical points for micro-crack classification improvement are SVM parameters, kernel function, clustered feature data, and experimental conditions. In the future, excellent results could be obtained through SVM parameter tuning and clustered feature data.

• Smart Structures and Systems
• /
• v.30 no.4
• /
• pp.385-395
• /
• 2022

Detecting cracks on a concrete structure is crucial for structural maintenance, a crack being an indicator of possible damage. Conventional crack detection methods which include visual inspection and non-destructive equipment, are typically limited to a small region and require time-consuming processes. Recently, to reduce the human intervention in the inspections, various researchers have sought computer vision-based crack analyses: One class is filter-based methods, which effectively transforms the image to detect crack edges. The other class is using deep-learning algorithms. For example, convolutional neural networks have shown high precision in identifying cracks in an image. However, when the objective is to classify not only the existence of crack but also the types of cracks, only a few studies have been reported, limiting their practical use. Thus, the presented study develops an image processing procedure that detects cracks and classifies crack types; whether the image contains a crazing-type, single crack, or multiple cracks. The properties and steps in the algorithm have been developed using field-obtained images. Subsequently, the algorithm is validated from additional 227 images obtained from an open database. For test datasets, the proposed algorithm showed accuracy of 92.8% in average. In summary, the developed algorithm can precisely classify crazing-type images, while some single crack images may misclassify into multiple cracks, yielding conservative results. As a result, the successful results of the presented study show potentials of using vision-based technologies for providing crack information with reduced human intervention.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.5
• /
• pp.9-16
• /
• 2019

Recent economic trends are worsening and becoming longer, and Korean shipbuilding is focused on high value added and high technology, especially for LNG carriers and large container ships. Both ship types increased in size in the 2010s but have requirements such as high strength, toughness at low temperatures and continuous weldability for preventing brittle fractures at service temperatures. In particular, as container ships become larger, the International Classification Society (IACS) has established a provision (IACS UR S33) that mandates the use of BCA (Brittle Crack Arrest) certified vessels for large container vessels contracted after 2014 to ensure safety. Therefore, studies on BCA 47Y.P are currently being undertaken, but BCA 40Y.P has not been actively studied yet. We will test BCA 40Y.P to verify why it can be applied to a large container ship and measure fatigue cracking.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.4
• /
• pp.2752-2759
• /
• 1996

This paper presents crack growth analysis approach on the basis of neural networks, a branch of cognitive science to high temperature low cycle fatigue that shows strong nonlinearity in material behavior. As the number of data patterns on crack growth increase, pattern classification occurs well and two point representation scheme with gradient of crack growth curve simulates crack growth rate better than one point representation scheme. Optimal number of learning data exists and excessive number of learning data increases estimated mean error with remarkable learning time J-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).

• Proceedings of the KWS Conference
• /
• 2010.05a
• /
• pp.61-61
• /
• 2010

The purpose of this study is to prevent the unstable fracture at the FCA butt weldment of hatch coaming deck in the ultra large containership during service life. In order to do it, the behavior of the embedded crack at the weldment under design loading conditions was evaluated in accordance with BS7910. Here, the level of primary stress induced by ship motion was evaluated by the design code of classification society and FEA. The level of residual stress as secondary stress was calculated in consideration of the restraint degree of weldment and welding heat input by using the predictive equation proposed by authors in the previous study. The fatigue crack growth rate at the weldment was evaluated using CT specimen in accordance with ASTM E647. According to the results, although the allowable defect for embedded crack specified in the classification society exists at the weldment, the occurrence possibility of unstable fracture at the weldment could not be negligible, regardless of CTOD value given in this study. So, in this study, the effect of initial defect size, welding heat input, restraint degree and CTOD on the fracture mechanical characteristics of embedded crack at the weldment was evaluated by the comprehensive fracture assessment. Based on the results, the design criteria including allowable defect, residual stress level and CTOD value was established to prevent the unstable fracture at the FCA butt weldment of hatch coaming deck in an ultra large containership during service life of 20years.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.13 no.2
• /
• pp.11-19
• /
• 1993

It is very essential to get the accurate classification of defects in primary pressure vessel weld for the safety of nuclear power plant. The signal analysis using the digital signal processing and pattern recognition is performed to classify UT defects extracting feature vector from ultrasonic signals. The minimum distance classifier and the maximum likelihood classifier based on statistics were applied in this experiment to discriminate ultrasonics data obtained form both the training specimens (slit, hole) and the testing specimens(crack, slag). The classification rate was measured using pattern classifier. Results of this study show the promise in solving the many flaw classification problems that exist today.

• Tunnel and Underground Space
• /
• v.17 no.2 s.67
• /
• pp.102-108
• /
• 2007

Generally, the method used most widely for rock mass classification is considering the rock strength and development of joint frequency. However, if rock bed has micro-crack and long joint, this method is not rational. Therefore, the difficulties of excavation in the rock bed with complicated geological condition are decided by combining joint frequency. indoor tests (uniaxiall compressive strength, point load test, indoor elastic wave velocity, etc.) and field seismic refraction survey, and the rock mass classification should be implemented by considering their interrelationship.