• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.10
• /
• pp.1492-1499
• /
• 2004

In this paper, defect formation in ring rolling is revealed by computer simulation of ring rolling processes. The rigid-plastic finite element method is employed for this study. An analysis model having relatively fine mesh system near the roll gap is used for reducing the computational time and a scheme of minimizing the volume change is applied. The formation of the central cavity formation defect in ring rolling of a taper roller bearing outer race and the polygonal shape defect in ring rolling of a ball bearing outer race has been simulated. It has been seen that the results are qualitatively good with actual phenomena.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.249-255
• /
• 2022

This study proposed an analysis framework for real-time prediction of CNC processing defects using machine learning-based models that are recently attracting attention as processing defect prediction methods, and applied it to CNC machines. Analysis shows that the XGBoost, CatBoost, and LightGBM models have the same best accuracy, precision, recall, F1 score, and AUC, of which the LightGBM model took the shortest execution time. This short run time has practical advantages such as reducing actual system deployment costs, reducing the probability of CNC machine damage due to rapid prediction of defects, and increasing overall CNC machine utilization, confirming that the LightGBM model is the most effective machine learning model for CNC machines with only basic sensors installed. In addition, it was confirmed that classification performance was maximized when an ensemble model consisting of LightGBM, ExtraTrees, k-Nearest Neighbors, and logistic regression models was applied in situations where there are no restrictions on execution time and computing power.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.5
• /
• pp.459-467
• /
• 2011

The work of constructing apartment housing involves various fields of industry that are linked to each other, and is based on a design document prepared by multiple technicians and architects. Consequently, design errors, material flaws or faulty construction works can cause defects, which sometimes overlap with each other. Construction companies should repair any defects found in a completed building within a specified period of time, and to do this, should establish a business plan by efficiently predicting the cost of defect repair. As it is very difficult for companies to accurately predict the occurrence of defects, historical performance data is used as a base. For domestic apartment housing units, data on the cost of defect repair is insufficient, so there are hardly any methods that can be used to make precise predictions. Therefore, the intent of this study is to develop a model that can predict the cost of defect repair by supply type and area, based on historical performance data with ten years worth of post-completion.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.77-90
• /
• 2018

Software Defect Prediction (SDP) is a field of study that identifies defective modules. With insufficient local data, a company can exploit Cross-Project Defect Prediction (CPDP), a way to build a classifier using dataset collected from other companies. Most machine learning algorithms for SDP have used more than one parameter that significantly affects prediction performance depending on different values. The objective of this study is to propose a parameter selection technique to enhance the performance of CPDP. Using a Harmony Search algorithm (HS), our approach tunes parameters of cost-sensitive boosting, a method to tackle class imbalance causing the difficulty of prediction. According to distributional characteristics, parameter ranges and constraint rules between parameters are defined and applied to HS. The proposed approach is compared with three CPDP methods and a Within-Project Defect Prediction (WPDP) method over fifteen target projects. The experimental results indicate that the proposed model outperforms the other CPDP methods in the context of class imbalance. Unlike the previous researches showing high probability of false alarm or low probability of detection, our approach provides acceptable high PD and low PF while providing high overall performance. It also provides similar performance compared with WPDP.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.310-315
• /
• 2003

This paper presents the effect of boundary condition of failure pressure model for buried pipelines on failure prediction by using a failure probability model. The first order Taylor series expansion of the limit state function is used in order to estimate the probability of failure associated with various corrosion defects for long exposure periods in years. A failure pressure model based on a failure function composed of failure pressure and operation pressure is adopted for the assessment of pipeline failure. The effects of random variables such as defect depth, pipe diameter, defect length, fluid pressure, corrosion rate, material yield stress, material ultimate tensile strength and pipe thickness on the failure probability of the buried pipelines are systematically studied by using a failure probability model for the corrosion pipeline.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.1-6
• /
• 2013

For predicting defect-prone module in software, SVM classifier showed good performance in a previous research. But there are disadvantages that SVM parameter should be chosen differently for every kernel, and algorithm should be performed iteratively for predict results of changed parameter. Therefore, we find these parameters using Genetic Algorithm and compare with result of classification by Backpropagation Algorithm. As a result, the performance of GA-SVM model is better.

• Journal of Korean Vacuum Science & Technology
• /
• v.3 no.1
• /
• pp.1-9
• /
• 1999

This paper presents a newly enhanced damage model in Monte Carlo (MC) simulation for the accurate prediction of 3-Dimensional (3D) as-implanted impurity and point defect profiles induced by ion implantation in (100) crystal silicon. An empirical electronic energy loss model for B, BF2, As, P and Si self implant over the wide energy range has been proposed for the ULSI device technology and development. Our model shows very good agreement with the SIMS data over the wide energy range. In the damage accumulation, we considered the self-annealing effects by introducing our proposed non-linear recomvination probability function of each point defect for the computational efficiency. For the damage profiles, we compared the published RBS/channeling data with our results of phosphorus implants. Our damage model shows very reasonable agreement with the experiments for phosphorus implants.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.1
• /
• pp.10-17
• /
• 2014

A 3D model based on the finite element method (FEM) was built to simulate the infrared thermography (IRT) inspection process. Thermal contrast is an important parameter in IRT and was proven to be a function of defect parameters. Parametric studies were conducted on internal defects with different depths, thicknesses, and orientations. Thermal contrast evolution profiles with respect to the time of the defect and host material were obtained through numerical simulation. The thermal contrast decreased with defect depth and slightly increased with defect thickness. Different orientations of thin defects were detected with IRT, but doing so for thick defects was difficult. These thermal contrast variations with the defect depth, thickness, and orientation can help in optimizing the experimental process and interpretation of data from IRT.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.958-967
• /
• 2023

This work studies the defect features in a dilute FeMnNi alloy by an Object Kinetic Monte Carlo (OKMC) model based on the "grey-alloy" method. The dose rate effect is studied at 573 K in a wide range of dose rates from 10^-8 to 10^-4 displacement per atom (dpa)/s and demonstrates that the density of defect clusters rises while the average size of defect clusters decreases with increasing dose rate. However, the dose-rate effect decreases with increasing irradiation dose. The model considered two realistic mechanisms for producing <100>-type self-interstitial atom (SIA) loops and gave reasonable production ratios compared with experimental results. Our simulation shows that the proportion of <100>-type SIA loops could change obviously with the dose rate, influencing hardening prediction for various dose rates irradiation. We also investigated ways to compensate for the dose rate effect. The simulation results verified that about a 100 K temperature shift at a high dose rate of 1×10^-4 dpa/s could produce similar irradiation microstructures to a lower dose rate of 1×10^-7 dpa/s irradiation, including matrix defects and deduced solute migration events. The work brings new insight into the OKMC modeling and the dose rate effect of the Fe-based alloys.