• Nuclear Engineering and Technology
• /
• v.40 no.1
• /
• pp.69-76
• /
• 2008

Most pressurized water reactors use Venturi flow meters to measure the feedwater flow rate. However, fouling phenomena, which allow corrosion products to accumulate and increase the differential pressure across the Venturi flow meter, can result in an overestimation of the flow rate. In this study, a soft-sensing model based on fuzzy support vector regression was developed to enable accurate on-line prediction of the feedwater flow rate. The available data was divided into two groups by fuzzy c means clustering in order to reduce the training time. The data for training the soft-sensing model was selected from each data group with the aid of a subtractive clustering scheme because informative data increases the learning effect. The proposed soft-sensing model was confirmed with the real plant data of Yonggwang Nuclear Power Plant Unit 3. The root mean square error and relative maximum error of the model were quite small. Hence, this model can be used to validate and monitor existing hardware feedwater flow meters.

• Journal of Power Electronics
• /
• v.8 no.4
• /
• pp.345-353
• /
• 2008

In this paper, a novel loss minimization of an induction generator in wind energy generation systems is presented. The proposed algorithm is based on the flux level reduction, for which the generator d-axis current reference is estimated using support vector regression (SVR). Wind speed is employed as an input of the SVR and the samples of the generator d-axis current reference are used as output to train the SVR algorithm off-line. Data samples for wind speed and d-axis current are collected for the training process, which plots a relation of input and output. The predicted off-line function and the instantaneous wind speed are then used to determine the d-axis current reference. It is shown that the effect of loss minimization is more significant at low wind speed and the loss reduction is about to 40% at 4[m/s] wind speed. The validity of the proposed scheme has been verified by experimental results.

• Journal of Advanced Navigation Technology
• /
• v.20 no.6
• /
• pp.604-611
• /
• 2016

Drone, which refers to unmanned aerial vehicles (UAV), industries are improving rapidly and exceeding existing level of remote controlled aircraft models. Also, they are applying automation and cloud network technology. Recently, the ability of drones can bring serious threats to public safety such as explosives and unmanned aircraft carrying hazardous materials. On the purpose of reducing these kinds of threats, it is necessary to detect these illegal drones, using acoustic feature extraction and classifying technology. In this paper, we introduce sound feature vector extraction method by harmonic feature extraction method (HLA). Feature vector extraction method based on HLA make it possible to distinguish drone sound, extracting features of sound data. In order to assess the performance of distinguishing sounds which exists in outdoor environment, we analyzed various sounds of things and real drones, and classified sounds of drone and others as simulation of each sound source.

• 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.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.7
• /
• pp.261-271
• /
• 1986

This paper describes a method for the state estimation considering current measurement component and detection of the bad data. The state values are estimated by weighted least square method in which measurement vector included bus injection current and line current. The bad data are detected using standardized variable of normal distribution and identified using sensitivity coefficients. When the bad data were occured by the bad measurement values. The results of the application to the model power system reveal the effectiveness of the presented algorithms.

• Journal of Broadcast Engineering
• /
• v.2 no.1
• /
• pp.36-44
• /
• 1997

We propose 3D perspective display using elevation matrix data with 2D information overlay. This algorithm is based on ID scan-line method and we used color index of the newly developed raster map, VRRG(Vector Restored Raster Graphics). The proposed method allows the fast generation of perspective view of 3D data with 2D overlay and the fast selective display of the features of 2D overlay.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.527-530
• /
• 1996

The Kalman filter has been used as a self-localization method for the mobile robot. To satisfy the assumptions inherent in the Kalman filter, we should calibrate the sensors of the robot before use of them. However, it is generally hard to find exact sensor parameters, and the parameters may change during the robot task as the environment varies. Thus we need to perform on-line sensor calibration, by which we can obtain more credible location of the mobile robot. In this paper, we present an on-line sensor calibration scheme which estimates the unknown sensor bias and the current position of the robot. To this end, first we find out the calibration errors of the sensor from redundant sensory data using the parity vector and recursive minimum variance estimation. Then we calculate the current position of the robot by weighted least square estimation without internal encoder data. The performance of the proposed method is evaluated through computer simulation.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.234-237
• /
• 2007

Road networks are important geospatial databases for various GIS (Geographic Information System) applications. Road digital maps may contain geometric spatial errors due to human and scanning errors, but manually updating roads information is time consuming. In this paper, we developed a new road features updating methodology using from multispectral high-resolution satellite image and pre-existing vector map. The approach is based on initial seed point generation using line segment matching and a modified double snake algorithm. Firstly, we conducted line segment matching between the road vector data and the edges of image obtained by Canny operator. Then, the translated road data was used to initialize the seed points of the double snake model in order to refine the updating of road features. The double snake algorithm is composed of two open snake models which are evolving jointly to keep a parallel between them. In the proposed algorithm, a new energy term was added which behaved as a constraint. It forced the snake nodes not to be out of potential road pixels in multispectral image. The experiment was accomplished using a QuickBird pan-sharpened multispectral image and 1:5,000 digital road maps of Daejeon. We showed the feasibility of the approach by presenting results in this urban area.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.26 no.3
• /
• pp.323-330
• /
• 2016

This paper describes real-time unbalance moment compensation method for line of sight(LOS) stabilization control systems. The factors of system inertia, frictions and unbalance moment affect the control accuracy of drive systems that are equipped to on the move(OTM) platforms requiring LOS stabilization function. In case of the unbalance moment among those factors is continuously changed as variation of relative angle between gravity vector and drive torque vector. Then, consideration of the effect in real-time is very complicate. Therefore, its effect should be designed to be minimized, however, designing it almost zero is impossible in real condition. In other words, it is hard to achieve target performance overcoming stability issue of highly unbalanced systems. To solve these problems, this paper proposes calculation method of unbalance moment by using measured sensor data for LOS stabilization control and its use for control compensation. Also, kinematical converting process and control structure for compensation are explained. The effectiveness of the proposed method as variation of unbalance moment is verified under simulation circumstance modeled by assuming LOS control system with 2-axis gimbal structure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.962-969
• /
• 2006

To address the importance of the process fault detection for productivity, support vector machines (SVMs) is employed to assist the decision to determine process faults in real-time. The reactive ion etching (RIE) tool data acquired from a production line consist of 59 variables, and each of them consists of 10 data points per second. Principal component analysis (PCA) is first performed to accommodate for real-time data processing by reducing the dimensionality or the data. SVMs for eleven steps or etching m are established with data acquired from baseline runs, and they are further verified with the data from controlled (acceptable) and perturbed (unacceptable) runs. Then, each SVM is further utilized for the fault detection purpose utilizing control limits which is well understood in statistical process control chart. Utilizing SVMs, fault detection of reactive ion etching process is demonstrated with zero false alarm rate of the controlled runs on a run to run basis.