• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.51 no.3
• /
• pp.99-106
• /
• 2002

This study presents an approach to model the Electric Railway System with the common grounding based on the 8-port network model and to analyse traction power feeding system focused on the amplification of harmonic current. The entire system can be easily modeled by the combination of 8-port representation of each component in parallel and/or series. Through the research, 8-port network model which can be effectively applied to harmonic analysis is derived.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.2
• /
• pp.114-118
• /
• 2005

Recently, in order to guarantee the quality of the final product from the production line, several equipments able to examine the polymer ingredients' quality are being used. Rheotruder is one of the equipments manufactured to measure the viscosity of the ingredient that is an important factor for the quality of final product. However, Rheotruder has nonlinear characteristics such as time delay which make systematic analysis difficult. In this paper, in order to enhance the performance of Rheotruder, a new scheme is introduced. It incorporates TDNN (Time Delay Neural Network) bank and Elman network to get a right decision on whether the tested ingredient is good or not. Furthermore, the proposed scheme is verified through real test execution.

• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.157-162
• /
• 1990

In this study, a peripheral auditory model is used as a frequency feature extractor and a recurrent network which has recurrent links on input nodes is constructed in order to show the reliability of the recurrent network as a recognizer by executing recognition tests for 4 Korean place names and syllables. In the case of using the general learning rule, it is found that the weights are diverged for a long sequence because of the characteristics of the node function in the hidden and output layers. So, a refined weight compensation method is proposed and, using this method, it is possible to improve the system operation and to use long data. The recognition results are considerably good, even if time worping and endpoint detection are omitted and learning patterns and test patterns are made of average length of data. The recurrent network used in this study reflects well time information of temporal speech signal.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2212-2215
• /
• 2002

This dissertation suggests and implements a middle level network which is called PICNET-NP (Plant Implementation and Control Network for Nuclear Power Plant). PICNET-NP is based partly on IEEE 802.4 token-passing bus access method and partly on IEEE 802.3 physical layer. For this purpose a new interface a physical layer service translator, is introduced. A control network using this method is implemented and applied to a distributed real-time system. To verify the performance of proposed protocol experimental were carried out, and the following results are obtained. 1) proper initialization of the protocol. 2) normal receiving and transmission of data. 3) proper switching of transmission media in case of a fault condition on the one of transmission media. The proposed protocol exhibits the excellent performance in the experimental system. From the test results in the experimental system, the proposed protocol, PICNET-NP, can be used for the upgrading of a nuclear power plant and the distributed control system in the next generation of nuclear power plant.

• Journal of Power System Engineering
• /
• v.11 no.1
• /
• pp.28-32
• /
• 2007

This research proposed that development of wireless condition monitoring system using WLAN network. It offers the prospect of improved performance that removed a current a coaxial cable and reduced overall cost of condition monitoring. Recently, there is an interesting concern for wireless system as an infrastructure technology construct ubiquitous computing environment in the future. High performance computing board makes minimization with integrate of a various functions which support wireless LAN network. Instead of wired coaxial cable using measurement system in industry, wireless LAN network assists industry automation and engineer's convenience. Developed system adapted wireless LAN network on shipboard with engine room and deck house, it also executes wireless measurement test on 8500TEU containership.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.2
• /
• pp.212-212
• /
• 1999

This paper proposed a high impedance fault detection method using a neural network on distribution lines. The v-I characteristic curve was obtained by high impedance fault data tested in various soil conditions. High impedance fault was simulated using EMTP. The pattern of High Impedance Fault on high density pebbles was taken as the learning model, and the neural network was valuated on various soil conditions. The average values after analyzing fault current by FFT of evenr·odd harmonics and fundamental rms were used for the neural network input. Test results were verified the validity of the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.1 no.1
• /
• pp.83-94
• /
• 1996

The test statistic in ANOVA tests has a single or doubly noncentral F distribution and the noncentral F distribution is applied to the calculation of the power functions of tests of general linear hypotheses. In this paper. the evaluation of the cumulative function of the single noncentral F distribution is applied to the neural network theory. The neural network consists of the multi-layer perceptron structure and learning process has the algorithm of the backpropagation. Numerical comparisons are made between the results obtained by neural network theory and the Patnaik's values.

• Journal of Welding and Joining
• /
• v.32 no.2
• /
• pp.43-47
• /
• 2014

Famous artificial neural network (ANN) is applied to predict proper process window of arc welding. Target weldment is variously combined lap joint fillet welding of automotive steel plates. ANN's system variable such as number of hidden layers, perceptrons and transfer function are carefully selected through case by case test. Input variables are welding condition and steel plate combination, for example, welding machine type, shield gas composition, current, speed and strength, thickness of base material. The number of each input variable referred in welding experiment is counted and provided to make it possible to presume the qualitative precision and limit of prediction. One of experimental process windows is excluded for predictability estimation and the rest are applied for neural network training. As expected from basic ANN theory, experimental condition composed of frequently referred input variables showed relatively more precise prediction while rarely referred set showed poorer result. As conclusion, application of ANN to arc welding process window derivation showed comparatively practical feasibility while it still needs more training for higher precision.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.451-458
• /
• 2002

This paper presents the prediction of deep excavation-induced ground surface movements using artificial neural network, which is of prime importance in the perspective of damage assessment of adjacent buildings. A finite element model, which can realistically replicate deep-excavation-induced ground movements was employed and validated against available large-scale model test results. The validated model was then used to perform a parametric study on deep excavations with emphasis on ground movements. Using the result of the finite element analysis, Artificial Neural Network(ANN) system is formed, which can be used in the prediction of deep exacavation-induced ground surface displacements. The developed ANN system can be effecting used for a first-order prediction of ground movements associated with deep-excavation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.3
• /
• pp.66-73
• /
• 2008

This paper presents a position sensorless control system of SRM over wide speed range. Due to the doubly salient structure of the SRM, the phase inductance varies along with the rotor position. Most of the sensorless control techniques are based on the fact that the magnetic status of the SRM is a function of the angular rotor position. The rotor position estimation of the SRM is somewhat difficult because of its highly nonlinear magnetizing characteristics. In order to estimate more accurate rotor position over wide speed range, Neural Network is used for this highly nonlinear function approximation. Magnetizing data patterns of the prototype 1-hp SRM are obtained from locked rotor test, and used for the Neural Network training data set. Through measurement of the flux-linkage and phase currents, rotor position is able to estimate from current-flux-rotor position lookup table which is constructed from trained Neural Network. Experimental results for a 1-hp SRM over 16:1 speed range are presented for the verification of the proposed sensorless control algorithm.