• Nuclear Engineering and Technology
• /
• v.42 no.2
• /
• pp.219-230
• /
• 2010

In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor's operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal component-based auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.872-898
• /
• 2007

Pantograph sliding plate abrasion auto-detect system, one of the electric rail car auto-detecting devices, is a system that decides how much abrasion and when to replace without an inspector physically looking at the abrasion on the wet plate using machine vision, a cutting-edge technology. This paper covers the cause of deteriorating reliability that affects pantograph wet plate edge detection due to noise added to the video when it rains. In order to remove such noise, problems should be checked through Smoothing, Averaging mask and Median filter using filtering technique and stable edge detection without being affected by noise should be induced in video measurement used in machine vision technology.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.16 no.4
• /
• pp.151-158
• /
• 2008

Gasoline Homogeneous Charge Compression Ignition (HCCI) combustion is a new combustion concept. Unlike the conventional internal combustion engine, the premixed fuel mixture with high residual gas rate is auto-ignited and burned without flame propagation. There are several operating factors which affect HCCI combustion such as start of combustion (SOC), residual gas fraction, engine rpm, etc. Among these factors SOC is a critical factor in the combustion because it affects exhaust gas emissions, engine power, fuel economy and combustion characteristics. Therefore SOC of gasoline HCCI should be controlled precisely, and SOC detection should be preceded SOC control. This paper presents a control oriented SOC detection method using 50 percent normalized difference pressure. Normalized difference pressure is defined as the normalized value of difference pressure and difference pressure is difference between the in-cylinder firing pressure and the motoring pressure. These methods were verified through the HCCI combustion experiments. The SOC detection method using difference pressure provides a fast and precise SOC detection.

• Communications for Statistical Applications and Methods
• /
• v.30 no.4
• /
• pp.369-388
• /
• 2023

In this paper, we develop the two-step procedure that detects and estimates the position of structural changes for multivariate nonstationary time series, either on mean parameters or second-order structures. We first investigate the presence of mean structural change by monitoring data through the aggregated cumulative sum (CUSUM) type statistic, a sequential procedure identifying the likely position of the change point on its trend. If no mean change point is detected, the proposed method proceeds to scan the second-order structural change by modeling the multivariate nonstationary time series with a multivariate locally stationary Wavelet process, allowing the time-localized auto-correlation and cross-dependence. Under this framework, the estimated dynamic spectral matrices derived from the local wavelet periodogram capture the time-evolving scale-specific auto- and cross-dependence features of data. We then monitor the change point from the lower-dimensional approximated space of the spectral matrices over time by applying the dynamic principal component analysis. Different from existing methods requiring prior information on the type of changes between mean and covariance structures as an input for the implementation, the proposed algorithm provides the output indicating the type of change and the estimated location of its occurrence. The performance of the proposed method is demonstrated in simulations and the analysis of two real finance datasets.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.8
• /
• pp.1179-1185
• /
• 2012

This paper presents a new approach for the detection of seismic events using accumulated changes on time-frequency domain and variable threshold. To detect seismic P-wave arrivals with rapidness and accuracy, it is that the changes on the time and the frequency domains are simultaneously used. Their changes are parameters appropriated to reflect characteristics of earthquakes over moderate magnitude(${\geq}$ magnitude 4.0) and microearthquakes. In addition, adaptively controlled threshold values can prevent false P-wave detections due to low SNR. We tested our method on real earthquakes those have various magnitudes. The proposed algorithm gives a good detection performance and it is also comparable to STA/LTA algorithm in computational complexity. Computer simulation results shows that the proposed algorithm is superior to the conventional popular algorithm (STA/LTA) in the seismic P-wave detection.

• Structural Monitoring and Maintenance
• /
• v.6 no.3
• /
• pp.237-254
• /
• 2019

This paper presents an improved time series based damage detection approach with experimental verifications for detection, localization, and quantification of damage in shear-type structures under varying mass effects using output-only vibration data. The proposed method can be very effective for automated monitoring of buildings to develop proactive maintenance strategies. In this method, Auto-Regressive Moving Average models with eXogenous inputs (ARMAX) are built to represent the dynamic relationship of different sensor clusters. The damage features are extracted based on the relative difference of the ARMAX model coefficients to identify the existence, location and severity of damage of stiffness and mass separately. The results from a laboratory-scale shear type structure show that different damage scenarios are revealed successfully using the approach. At the end of this paper, the methodology limitations are also discussed, especially when simultaneous occurrence of mass and stiffness damage at multiple locations.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.588-590
• /
• 2006

Recently, many on-line approaches to instrument channel surveillance (drift monitoring and fault detection) have been reported worldwide. On-line monitoring (OLM) method evaluates instrument channel performance by assessing its consistency with other plant indications through parametric or non-parametric models. The heart of an OLM system is the model giving an estimate of the true process parameter value against individual measurements. This model gives process parameter estimate calculated as a function of other plant measurements which can be used to identify small sensor drifts that would require the sensor to be manually calibrated or replaced. This paper describes an improvement of auto-associative kernel regression by introducing a correlation coefficient weighting on kernel distances. The prediction performance of the developed method is compared with conventional auto-associative kernel regression.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.73-76
• /
• 2007

Photodynamic diagnosis(PDD) is a method to diagnose the possibility of cancer, both by the principle that if a photosensitizer is injected into an organic tissue, it is accumulated in the tissue of a malignant tumor selectively after a specific period, and by a comparison of the intensity of the fluorescence of normal tissue with abnormal tissue after investigating the excitation light of a tissue with accumulated photosensitizer. Since the selection of the wavelength band of excitation light has an interrelation with fluorescence generation according to the selection of a photosencitizer, it plays an important role in POD. This study aims at designing and evaluating light source devices that can stably generate light with various kinds of wavelengths In order to make possible PDD using a photosensitizer and diagnosis using auto-fluorescence. The light source device was a Xenon lamp and filter wheel, composed of an optical output control through Iris and filters with several wavelength bands It also makes the inducement of auto-fluorescence possible because it is designed to generate a wavelength band of 380-400. The transmission part of the light source was, developed to enhance the efficiency of light transmission. To evaluate this light source device, the characteristics of the light output and wavelength band were verified. To validate the capability of this device as PDD the detection of auto-fluorescence using mouse was performed.

• Journal of the Korea Society for Simulation
• /
• v.19 no.3
• /
• pp.1-6
• /
• 2010

Simulation analysis may be the essential means to either evaluate performance of systems or optimize system parameters for new design. Including many variations for design and implementation, MANET (Mobile Ad-hoc NETwork) is one target area of such an analysis. Since every node, however, included in the network has mobility, one MANET could be overlapped or merged with another one which use a different transport protocol. In order to communicate among nodes in this case, the new merged network should configure paths and addresses in advance. Configuring paths and addresses generates much overheads which ultimately cause delay in communicating data. Performance analysis is required to improve the data transport performance by minimizing overheads. This paper proposes a sound address auto-configuration method which is based on an on-demand manner and then presents modeling and performance analysis of the method. NS-2 simulation results verify that the proposed method can not only alleviate overheads, which are inevitably generated for address auto-configuration processes, and but also decentralize them in time.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.