• Journal of Ocean Engineering and Technology
• /
• v.35 no.4
• /
• pp.287-295
• /
• 2021

This paper describes a recurrent neural network (RNN) for the fault classification of a blade pitch system of a spar-type floating wind turbine. An artificial neural network (ANN) can effectively recognize multiple faults of a system and build a training model with training data for decision-making. The ANN comprises an encoder and a decoder. The encoder uses a gated recurrent unit, which is a recurrent neural network, for dimensionality reduction of the input data. The decoder uses a multilayer perceptron (MLP) for diagnosis decision-making. To create data, we use a wind turbine simulator that enables fully coupled nonlinear time-domain numerical simulations of offshore wind turbines considering six fault types including biases and fixed outputs in pitch sensors and excessive friction, slit lock, incorrect voltage, and short circuits in actuators. The input data are time-series data collected by two sensors and two control inputs under the condition that of one fault of the six types occurs. A gated recurrent unit (GRU) that is one of the RNNs classifies the suggested faults of the blade pitch system. The performance of fault classification based on the gate recurrent unit is evaluated by a test procedure, and the results indicate that the proposed scheme works effectively. The proposed ANN shows a 1.4% improvement in its performance compared to an MLP-based approach.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.163-172
• /
• 2022

Typical anti-jamming technologies based on array antennas, Space Time Adaptive Process (STAP) & Space Frequency Adaptive Process (SFAP), are very effective algorithms to perform nulling and beamforming. However, it does not perform equally well for all types of jamming signals. If the anti-jamming algorithm is not optimized for each signal type, anti-jamming performance deteriorates and the operation stability of the system become worse by unnecessary computation. Therefore, jamming classification technique is required to obtain optimal anti-jamming performance. Machine learning, which has recently been in the spotlight, can be considered to classify jamming signal. In general, performing supervised learning for classification requires a huge amount of data and new learning for unfamiliar signal. In the case of jamming signal classification, it is difficult to obtain large amount of data because outdoor jamming signal reception environment is difficult to configure and the signal type of attacker is unknown. Therefore, this paper proposes few-shot jamming signal classification technique using meta-learning and transfer-learning to train the model using a small amount of data. A training dataset is constructed by anti-jamming algorithm input data within the GNSS receiver when jamming signals are applied. For meta-learning, Model-Agnostic Meta-Learning (MAML) algorithm with a general Convolution Neural Networks (CNN) model is used, and the same CNN model is used for transfer-learning. They are trained through episodic training using training datasets on developed our Python-based simulator. The results show both algorithms can be trained with less data and immediately respond to new signal types. Also, the performances of two algorithms are compared to determine which algorithm is more suitable for classifying jamming signals.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.177-189
• /
• 2016

This study examined the effectiveness of maternity nursing simulations using a high-fidelity simulator for undergraduate nursing students. One-group pretest-posttest design was used. The simulation-based education program consisted of three sessions, including the clinical scenarios about prenatal, childbearing and postpartum care. The program provided for 3 weeks in November 2014. Data was collected before and after the simulation education using self-reported questionnaires, which included simulation effectiveness, problem solving ability, communication skills and self-confidence in maternity nursing. The data of 83 participants were analyzed using the IBM SPSS 20.0 program. After simulation education, the overall score of the simulation effectiveness was 17.4 out of 26.0. Communication skill (t=4.58, p=<.001) and self-confidence in maternity nursing (t=9.70, p=<.001) increased significantly in the posttest. On the other hand, there was no significant change in the problem solving ability. The simulation effectiveness correlated significantly with the problem solving ability (r=.494, p<.001), communication skill (r=.361, p<.001), and self-confidence in maternity nursing (r=.497, p<.001) after simulation-based education. These findings suggest that the high-fidelity simulation in maternity nursing education could be used not only to enhance the nursing competency, but also to deal with the limitations of the clinical practicum in the current situation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.1-6
• /
• 2014

In this study, we propose optimized RBFNNs based on night vision face recognition simulator with the aid of $(2D)^2$ PCA algorithm. It is difficult to obtain the night image for performing face recognition due to low brightness in case of image acquired through CCD camera at night. For this reason, a night vision camera is used to get images at night. Ada-Boost algorithm is also used for the detection of face images on both face and non-face image area. And the minimization of distortion phenomenon of the images is carried out by using the histogram equalization. These high-dimensional images are reduced to low-dimensional images by using $(2D)^2$ PCA algorithm. Face recognition is performed through polynomial-based RBFNNs classifier, and the essential design parameters of the classifiers are optimized by means of Differential Evolution(DE). The performance evaluation of the optimized RBFNNs based on $(2D)^2$ PCA is carried out with the aid of night vision face recognition system and IC&CI Lab data.

• The KIPS Transactions:PartC
• /
• v.10C no.4
• /
• pp.471-478
• /
• 2003

Traditionally,, analysis, simulation and measurement have all been used to evaluate the performance of network protocols and functional entities that support mobile wireless service. Simulation methods are useful for testing the complex systems which have the very complicate interactions between components. To develop a mobile call simulator which is used to examine, validate, and predict the performance of mobile wireless call procedures must have the teletraffic model, which is to describe the mobile communication environments. Mobile teletraffic model is consists of 2 sub-models, traffic source and network traffic model. In this paper, we analyzed the network traffic data which are gathered from selected Base Stations (BSs) to define the mobile teletraffic model. We defined 4 types of cell location-Residential, Commercial, Industrial, and Afforest zone. We selected some Base Stations (BSs) which are represented cell location types in Seoul city, and gathered real data from them And then, we present the call rate per hour, cail distribution pattern per day, busy hours, loose hours, the maximum number of call, and the minimum number of calls based on defined cell location types. Those parameters are very important to test the mobile communication system´s performance and reliability and are very useful for defining the mobile network traffic model or for working the existed mobile simulation programs as input parameters.

• Fire Science and Engineering
• /
• v.32 no.3
• /
• pp.51-59
• /
• 2018

Although a fire curtain plays an important role in preventing smoke from spreading to the auditorium in a theater fire, there has been insufficient research on fire curtains. In this study, to check the accuracy of numerical simulation, for previous experiments using a reduced scale model, a numerical simulation was carried out, and the results were compared with previous experimental data. The fire curtain effect was then predicted numerically. A Fire Dynamics Simulator (FDS) was used, and the natural exhaust vent sizes were set to ~10%, ~5%, and ~1% of the stage floor area. The smoke movement was visualized, and the mass flow rates and temperatures were measured and analyzed. In addition, the law of similarity was used to examine the influence of a fire curtain in a real scale theater fire. Without the fire curtain, the present numerical simulation results were in agreement with the previous experimental data within reasonable accuracy. Meanwhile, the fire curtain affects the mass flow rates through the natural exhaust vent and proscenium opening, as well as the start time of soot outflow to the auditorium. Overall, the present results can be used to develop a fire curtain system.

• Journal of Bio-Environment Control
• /
• v.28 no.1
• /
• pp.16-27
• /
• 2019

Using virtual reality technology, users can learn and experience many interactions in virtual space like the actual physical space. This study was conducted to develop air flow simulator that allows farmers and consultants to consult air flow through VR devices by creating a greenhouse or pigpen model. It can help educate farmers about the importance of ventilation effects for agricultural facilities. We proposed CFD visualization system by building a virtual reality environment and constructing database of CFD and structure of agricultural facilities. After consultants can set up situations according to environmental conditions, the users experience the visualized air flow of agricultural facility according to the ventilation effects. Also it can provide a quantified environmental distribution in the agricultural facility. Currently, the CFD data in agricultural facilities are established during winter and summer. In order to experience various environmental conditions in the developed system, The experts need to run CFD data under various environmental conditions and register them in the system requirements.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.518-529
• /
• 2022

In Task C of the DECOVALEX-2023 project, nine institutes from six nations are developing their numerical codes to simulate thermo-hydro-mechanical coupled behavior for the FE experiment performed at Mont Terri underground rock laboratory, Switzerland. Currently, Step 1 for comparing the simulation results to field data is the ongoing stage, and we used the OGS-FLAC simulator for a series of numerical simulations. As a result, temperature increase depending on the heating hysteresis was well simulated, and saturation variation in the bentonite depending on phase change was observed. However, due to the suction overestimation, relative humidity and temperature change in the bentonite and the pressure variation in the Opalinus clay showed a difference compared to the field data. From the observation, it is confirmed that the effect of the bentonite capillary pressure is dominant to the flow analysis in the disposal system. We further plan to draw improved results considering tunnel support material and accurate initial water pressure distribution. Additionally, the thermal, hydrological, and mechanical anisotropy of the Opalinus clay was well simulated. From the simulation results, we confirmed the applicability of the OGS-FLAC simulator in the disposal system analysis.

• Korean Journal of Optics and Photonics
• /
• v.11 no.6
• /
• pp.452-456
• /
• 2000

A measurement unit and signal processing algorithm have been developed for predicting arterial oxygen saturation noninvasively. The measurement set-up was composed of a probe including light source and photodetector, optical signal processing section, LED driving circuit, PC interface software for data acquisition and data processing software. Light from the LED's was irradiated onto the finger nail bed and transmitted light was measured at different wavelengths. An effective baseline correction method was developed and measured data were analyzed by using various data processing methods and prediction algOlithms. For performance evaluation, a pulse oximeter simulator (Bio- Tek Instrument Inc.) was used as reference. The best performance in terms of the correlation coefficient and the standard deviation was obtained under the following conditions; when the arterial signals were computed in terms of area rather than peak-valley difference, and when the algorithm calculating by $In(I_p/I_v)/I_{avr}$ value for pulsation waveform was used. In in vivo test, prediction was improved when the developed baseline correction method was used. In addition, wavelengths of 660 nm and 940 nm provided better linearity and precision than wavelengths of 660 nm and 805 nm. 05 nm.

• Journal of Korea Multimedia Society
• /
• v.11 no.2
• /
• pp.247-256
• /
• 2008

Recently, natural disasters like flooding damages have frequently occurred as to typhoons and local downpours affected by the climate changes. Many researches have actively been studied in analysing runoff models, the verification of their parameters, and the inflow on surfaces in order to lessen the damages. However, much time and effort needs in generating input files of the models in most current researches. Therefore, in this paper we develop a system for generating a simulation input data automatically. This system is connected to the EPA-SWMM based on the spatial data in the UIS systems and consists the simulation module for analysing urban flooding and the SWMM simulator module. Also, we construct a prototype using a range of regular inundation to generate a simulation input file. This system gives advantages showing inundation areas based on the map viewer as well as lessening errors of input data and simulation time.