• Journal of the Korean Society for Heat Treatment
• /
• v.35 no.6
• /
• pp.327-336
• /
• 2022

In this study, a model for automatically recognizing several steel parts through a camera before charging materials was developed under the assumption that the temperature distribution in the pre-air atmosphere was known. For model development, datasets were collected in random environments and factories. In this study, the YOLO-v5 model, which is a YOLO model with strengths in real-time detection in the field of object detection, was used, and the disadvantages of taking a lot of time to collect images and learning models was solved through the transfer learning methods. The performance evaluation results of the derived model showed excellent performance of 0.927 based on mAP 0.5. The derived model will be applied to the model development study, which uses the model to accurately recognize the material and then match it with the temperature distribution in the atmosphere to determine whether the material layout is suitable before charging materials.

• Proceedings of the KIEE Conference
• /
• 2001.07c
• /
• pp.1738-1740
• /
• 2001

The occurrence of fires under transmission lines is responsible for a great number of power line outages. In this paper, the ac flashover voltages and the corona onset voltages of a model transmission line in the presence of flame were investigated. We found that the corona onset voltages and the flashover voltages were varied with the position of flames. Flashover voltages of vertical arranged electrodes with flame appeared to decrease 43[%] lower than those of same conditions with no flame.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.63-64
• /
• 2008

• Journal of the Korean Statistical Society
• /
• v.32 no.2
• /
• pp.103-119
• /
• 2003

Properties of stochastic regression imputation are discussed under the uniform within-cell response model. Variance estimator is proposed and its asymptotic properties are discussed. A limited simulation is also presented.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1487-1488
• /
• 2011

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.475-476
• /
• 2010

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.435-436
• /
• 2012

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.513-514
• /
• 2013

• Review of Korean Society for Internet Information
• /
• v.19 no.1
• /
• pp.23-29
• /
• 2018

• Journal of Korea Water Resources Association
• /
• v.47 no.10
• /
• pp.959-972
• /
• 2014

In this study, a space-time rainfall grid field generation model based on multifractal theory was verified using nine flood events in the upstream watershed of Chungju dam in South Korea. For this purpose, KMA radar rainfall data sets were analyzed for the space-time multifractal characteristics. Simulated rainfall fields that represent the multifractal characteristics of observed rainfall field were reproduced using the space-time rainfall grid field generation model with log-Poisson distribution and three-dimension wavelet function. Simulated rainfall fields were applied to the S-RAT model as input data and compared with both observed rainfall fields and low-resolution rainfall field runoff. Error analyses using RMSE, RRMSE, MAE, SS, NPE and PTE indicated that the peak discharge increases about 20.03% and the time to peak decreases about 0.81%.