• Nuclear Engineering and Technology
• /
• v.54 no.6
• /
• pp.2107-2119
• /
• 2022

Accurate remaining useful life (RUL) prediction for critical components of nuclear power equipment is an important way to realize aging management of nuclear power equipment. The electric gate valve is one of the most safety-critical and widely distributed mechanical equipment in nuclear power installations. However, the electric gate valve's extended service in nuclear installations causes aging and degradation induced by crack propagation and leakages. Hence, it is necessary to develop a robust RUL prediction method to evaluate its operating state. Although the particle filter(PF) algorithm and its variants can deal with this nonlinear problem effectively, they suffer from severe particle degeneracy and depletion, which leads to its sub-optimal performance. In this study, we combined the whale algorithm with regularized particle filtering(RPF) to rationalize the particle distribution before resampling, so as to solve the problem of particle degradation, and for valve RUL prediction. The valve's crack propagation is studied using the RPF approach, which takes the Paris Law as a condition function. The crack growth is observed and updated using the root-mean-square (RMS) signal collected from the acoustic emission sensor. At the same time, the proposed method is compared with other optimization algorithms, such as particle swarm optimization algorithm, and verified by the realistic valve aging experimental data. The conclusion shows that the proposed method can effectively predict and analyze the typical valve degradation patterns.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.10 no.2
• /
• pp.25-30
• /
• 1992

Most algorithms in computer vision and digital photogrammetry assume that digital stereo pairs are registered in epipolar geometry. But, an aerial stereo pair is not likely to be in epiplar geometry since the attitude of the camera at the instant of exposure is different at every exposure station. In this paper, stereo digital imagery is obtained from aerial stereo pair by scanner. Then procesure to resample the digital imagery to epipolar geometry using exterior orientation elements after absolute orientation is described. As a result, a stereo imagery in epipolar geometry is produced from stereo digital imagery. Epipolar imagery in this paper is applied to the image matching method by digital image correlation technique. Then, a digital elevation model is produced from the result of image matching. The digital elevation model in this paper is compared to the other digital elevation model produced by analytical plotter. As a result, an economical method to generate digital elevation model is presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.534-539
• /
• 2010

In genomic studies, thousands of features are collected on relatively few samples. One of the goals of these studies is to build classifiers to predict the outcome of future observations. There are three inherent steps to build classifiers: a significant gene selection, model selection and prediction assessment. In the paper, with a focus on prediction assessment, we normalize microarray data with quantile-normalization methods that adjust quartile of all slide equally and then design a system comparing several methods to estimate 'true' prediction error of a prediction model in the presence of feature selection and compare and analyze a prediction error of them. LOOCV generally performs very well with small MSE and bias, the split sample method and 2-fold CV perform with small sample size very pooly. For computationally burdensome analyses, 10-fold CV may be preferable to LOOCV.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.200-209
• /
• 2019

When forecasting future values, a model estimated after minimizing training errors can yield test errors higher than the training errors. This result is the over-fitting problem caused by an increase in model complexity when the model is focused only on a given dataset. Some regularization and resampling methods have been introduced to reduce test errors by alleviating this problem but have been designed for use with only a given dataset. In this paper, we propose a new optimization approach to reduce test errors by transforming a test error minimization problem into a training error minimization problem. To carry out this transformation, we needed additional data for the given dataset, termed pseudo data. To make proper use of pseudo data, we used three types of missing data imputation techniques. As an optimization tool, we chose the least squares method and combined it with an extra pseudo data instance. Furthermore, we present the numerical results supporting our proposed approach, which resulted in less test errors than the ordinary least squares method.

• Journal of Korean Society of Forest Science
• /
• v.100 no.3
• /
• pp.392-396
• /
• 2011

The purpose of this study was to develop the basic wood density (Abbreviated BWD) for Pinus densiflora and to evaluate the applicability of bootstrap simulation method. The data sets were divided into two groups based on eco-types in Korea, one from Gangwon type and the other from Jungbu type. The estimated BWDs derived from bootstrap simulation, which is one of the non-parametric statistics, were 0.418 ($g/cm^3$) in the Pinus densiflora in Gangwon while 0.464 ($g/cm^3$) in the Pinus densiflora in Jungbu. To evaluate the bootstrap simulation, the mean BWD, standard error and 95% confidence interval of probability density were estimated. The number of replication were 100, 500, 1,000, and 5,000 times that showed constant 95% confidence interval, while tended to decrease in terms of standard errors. The results of this study could be very useful to apply basic wood density values to calculate reliable carbon stocks for Pinus densiflora in Korea.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.885-896
• /
• 2022

Motor failure in manufacturing plays an important role in future A/S and reliability. Motor failure is detected by measuring sound, current, and vibration. For the data used in this paper, the sound of the car's side mirror motor gear box was used. Motor sound consists of three classes. Sound data is input to the network model through a conversion process through MelSpectrogram. In this paper, various methods were applied, such as data augmentation to improve the performance of classifying fault motors and various methods according to class imbalance were applied resampling, reweighting adjustment, change of loss function and representation learning and classification into two stages. In addition, the curriculum learning method and self-space learning method were compared through a total of five network models such as Bidirectional LSTM Attention, Convolutional Recurrent Neural Network, Multi-Head Attention, Bidirectional Temporal Convolution Network, and Convolution Neural Network, and the optimal configuration was found for motor sound classification.

• Journal of Korea Water Resources Association
• /
• v.42 no.10
• /
• pp.857-866
• /
• 2009

In this study, basic data is consisted annual maximum rainfall at 56 stations that has the rainfall records more than 30years in Korea. The 14 probability distributions which has been widely used in hydrologic frequency analysis are applied to the basic data. The method of moments, method of maximum likelihood and probability weighted moments method are used to estimate the parameters. And 4-tests (chi-square test, Kolmogorov-Smirnov test, Cramer von Mises test, probability plot correlation coefficient (PPCC) test) are used to determine the goodness of fit of probability distributions. This study emphasizes the necessity for considering the variability of the estimate of T-year event in hydrologic frequency analysis and proposes a framework for evaluating probability distribution models. The variability (or estimation error) of T-year event is used as a criterion for model evaluation as well as three goodness of fit criteria (SLSC, MLL, and AIC) in the framework. The Jackknife method plays a important role in estimating the variability. For the annual maxima of rainfall at 56 stations, the Gumble distribution is regarded as the best one among probability distribution models with two or three parameters.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.3
• /
• pp.127-134
• /
• 2018

Electric transmission towers are facilities to transport electrical power from a plant to an electrical substation. The towers are connected using power lines that are installed with a proper sag by loosening the cable to lower the tension and to secure the sufficient clearance from the ground or nearby objects. The power line sag may extend over the tolerance due to the weather such as strong winds, temperature changes, and a heavy snowfall. Therefore the periodical mapping of the power lines is required but the poor accessibility to the power lines limit the work because most power lines are placed at the mountain area. In addition, the manual mapping of the power lines is also time-consuming either using the terrestrial surveying or the aerial surveying. Therefore we utilized multiple overlapping images acquired from a low-cost drone to automatically reconstruct the power lines in the object space. Two overlapping images are selected for epipolar image resampling, followed by the line extraction for the resampled images and the redundant images. The extracted lines from the epipolar images are matched together and reconstructed for the power lines primitive that are noisy because of the multiple line matches. They are filtered using the extracted line information from the redundant images for final power lines points. The experiment result showed that the proposed method successfully generated parabolic curves of power lines by interpolating the power lines points though the line extraction and reconstruction were not complete in some part due to the lack of the image contrast.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.220-223
• /
• 2004

Automatic image registration is an essential element of remote sensing because remote sensing system generates enormous amount of data, which are multiple observations of the same features at different times and by different sensor. The general process of automatic image registration includes three steps: 1) The extraction of features to be used in the matching process, 2) the feature matching strategy and accurate matching process, 3) the resampling of the data based on the correspondence computed from matched feature. For step 2) and 3), we have developed an algorithms for automated registration of satellite images with RANSAC(Random Sample Consensus) in success. However, for step 1), There still remains human operation to generate GCP Chips, which is time consuming, laborious and expensive process. The main idea of this research is that we are able to automatically generate GCP chips with comer detection algorithms without GPS survey and human interventions if we have systematic corrected satellite image within adaptable positional accuracy. In this research, we use SUSAN(Smallest Univalue Segment Assimilating Nucleus) algorithm in order to detect the comer. SUSAN algorithm is known as the best robust algorithms for comer detection in the field of compute vision. However, there are so many comers in high-resolution images so that we need to reduce the comer points from SUSAN algorithms to overcome redundancy. In experiment, we automatically generate GCP chips from IKONOS images with geo level using SUSAN algorithms. Then we extract reference coordinate from IKONOS images and DEM data and filter the comer points using texture analysis. At last, we apply automatically collected GCP chips by proposed method and the GCP by operator to in-house automatic precision correction algorithms. The compared result will be presented to show the GCP quality.

• Journal of the Optical Society of Korea
• /
• v.15 no.3
• /
• pp.293-299
• /
• 2011

In this study, we demonstrated Fourier-domain/swept-source optical coherence tomography (FD/SS-OCT) at a center wavelength of 800 nm for in vivo human retinal imaging. A wavelength-swept source was constructed with a semiconductor optical amplifier, a fiber Fabry-Perot tunable filter, isolators, and a fiber coupler in a ring cavity. Our swept source produced a laser output with a tuning range of 42 nm (779 to 821 nm) and an average power of 3.9 mW. The wavelength-swept speed in this configuration with bidirectionality is 2,000 axial scans per second. In addition, we suggested a modified zero-crossing method to achieve equal sample spacing in the wavenumber (k) domain and to increase the image depth range. FD/SS-OCT has a sensitivity of ~89.7 dB and an axial resolution of 10.4 ${\mu}m$ in air. When a retinal image with 2,000 A-lines/frame is obtained, an acquisition speed of 2.0 fps is achieved.