• Transactions of Materials Processing
• /
• v.17 no.8
• /
• pp.607-612
• /
• 2008

The groove rolling is a process that transforms the bloom or billet into a shape with circular section through a series of rolling. Inhibition of surface defect generation in groove rolling is a matter of great importance and therefore many research groups proposed a lot of models to find the location of surface defect initiation. In this study, we propose a model for maximum shear stress ratio over equivalent strain to catch the location of surface defect onset. This model is coupled with element removing method and applied to box groove rolling of POSCO No.3 Rod Mill. Results show that proposed model in this study can find the location of surface defect initiation during groove rolling when finite element analysis results is compared with experiments. The proposed criterion has been applied successfully to design roll grooves which inhibit the generation of surface defect.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• Journal of the Korean housing association
• /
• v.26 no.2
• /
• pp.67-79
• /
• 2015

As the Korean construction market in the apartment housing has changed to a housing consumer focused market, interest and importance on efficient use and management on existing buildings has increased rather than demand for new buildings. Interest of housing consumers on apartment house quality has increased in this market paradigm, and this spontaneously is connected to quality flaw related defect disputes and lawsuits that the importance of defect diagnosis has continuously increased. This defect diagnosis is directly connected to maintenance charges in defect dispute and lawsuit processes that rather objective and highly credible progress of duty is required. However, most defect diagnosis firms today that progress defect diagnosis are using different diagnosis methods and depend on the experience of experienced professionals that there is no standardized defect diagnosis process. Therefore, the purpose of this study is to provide common defect diagnosis process model for defect diagnosis firms utilizing the BPMN (Business Process Modeling Notation) modeling method. It is expected that this will contribute to professional and reliable task performances of concerned defect diagnosis workers. Furthermore, it is expected that design lawsuit damage will be substantially reduced by standardizing defect diagnosis processes.

• KIISE Transactions on Computing Practices
• /
• v.22 no.12
• /
• pp.681-686
• /
• 2016

Software defect prediction is an important factor in efficient project management and success. The severity of the defect usually determines the degree to which the project is affected. However, existing studies focus only on the presence or absence of a defect and not the severity of defect. In this study, we proposed an ensemble model using FCM based on defect severity. The severity of the defect of NASA data set's PC4 was reclassified. To select the input column that affected the severity of the defect, we extracted the important defect factor of the data set using Random Forest (RF). We evaluated the performance of the model by changing the parameters in the 10-fold cross-validation. The evaluation results were as follows. First, defect severities were reclassified from 58, 40, 80 to 30, 20, 128. Second, BRANCH_COUNT was an important input column for the degree of severity in terms of accuracy and node impurities. Third, smaller tree number led to more variables for good performance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.5 s.236
• /
• pp.734-742
• /
• 2005

The present study proposes the integrity evaluation model for a straight pipe with local wall thinning defect, which reflects the characteristics of training shape and loading condition in the Piping of nuclear power plant. For this purpose, a series of finite element analyses are performed under various defect geometries and loading conditions, and real pipe experiment data performed previously is employed. The model includes the effect of thinning length as well as thinning depth and width, and also it considers the combined loading effect between internal pressure and bending moment. The proposed model has been validated using the results of finite element analysis and pipe experiment data. The results indicate that the proposed model provides more reliable predictions of pipe failure than the current existing model, in terms of accuracy, consistency, and conservativeness of results.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.26-30
• /
• 2020

In this paper, we studied the problem if the experiment number occurring in order to identify defect in scaffold. We need to change each of the 5 print factor to predict defect when printing disk type scaffold using FDM 3d printer. So then the number of scaffold print will be more than 100,000 times. This experiment number is difficult to perform in the field. In order to solve this problem, we have produced a prediction model based on machine learning multiple linear regression using print conditions and defect scaffold data for print conditions. The prediction model produced was verified through experiments. The verification confirmed that the error was less than 0.5 %. We have confirmed that satisfied within the target margin of error 5 %.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.79-84
• /
• 2023

Image generation models have been applied in various fields to overcome data sparsity, time and cost issues. However, it has limitations in generating images from regular pattern images and detecting defects in such data. In this paper, we verified the feasibility of the image generation model to generate pattern images and applied it to data augmentation for defect detection of OLED panels. The data required to train an OLED defect detection model is difficult to obtain due to the high cost of OLED panels. Therefore, even if the data set is obtained, it is necessary to define and classify various defect types. This paper introduces an OLED panel defect data acquisition system that acquires a hypothetical data set and augments the data with an image generation model. In addition, the difficulty of generating pattern images in the diffusion model is identified and a possibility is proposed, and the limitations of data augmentation and defect detection data augmentation using the image generation model are improved.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.42 no.1
• /
• pp.20-30
• /
• 2016

Objectives: To validate a critical-size mandibular bone defect model in miniature pigs. Materials and Methods: Bilateral notch defects were produced in the mandible of dentally mature miniature pigs. The right mandibular defect remained untreated while the left defect received an autograft. Bone healing was evaluated by computed tomography (CT) at 4 and 16 weeks, and by micro-CT and non-decalcified histology at 16 weeks. Results: In both the untreated and autograft treated groups, mineralized tissue volume was reduced significantly at 4 weeks post-surgery, but was comparable to the pre-surgery levels after 16 weeks. After 16 weeks, CT analysis indicated that significantly greater bone was regenerated in the autograft treated defect than in the untreated defect (P=0.013). Regardless of the treatment, the cortical bone was superior to the defect remodeled over 16 weeks to compensate for the notch defect. Conclusion: The presence of considerable bone healing in both treated and untreated groups suggests that this model is inadequate as a critical-size defect. Despite healing and adaptation, the original bone geometry and quality of the pre-injured mandible was not obtained. On the other hand, this model is justified for evaluating accelerated healing and mitigating the bone remodeling response, which are both important considerations for dental implant restorations.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.63-68
• /
• 2022

In this study, we produced defect detection models using parallel convolution neural networks. If convolution neural networks are constructed parallel type, the model's detection accuracy will increase and detection time will decrease. We produced parallel-type defect detection models using 4 types of convolutional algorithms. The performance of models was evaluated using evaluation indicators. The model's performance is detection accuracy and detection time. We compared the performance of each parallel model. The detection accuracy of the model using AlexNet is 97 % and the detection time is 0.3 seconds. We confirmed that when AlexNet algorithm is constructed parallel type, the model has the highest performance.