• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.219-226
• /
• 1994

Sinusoidal current tracking inverters have substantial advantages in high performance acdrive systems and various control strategies for the inverter have been proposed by several researchers. This paper develops a sinusoidal current tracking inverter with neural networks. The neural network are trained to follow a set of reference current waveforms by erro back propagation algorithm and the trained neural networks are applied to the current control. We compare neural networks method with conventional current control methods (fixed band and sinusiidal band hystersis methods) and simulation results are presented.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.433-439
• /
• 1998

In this paper, we present an approach to the structure identification based on the input space partition methods and to the parameter identification by hybrid learning method in neuro-fuzzy system. The structure identification can automatically estimate the number of membership function and fuzzy rule using grid partition, tree partition, scatter partition from numerical input-output data. And then the parameter identification is carried out by the hybrid learning scheme using back-propagation and least squares estimate. Finally, we sill show its usefulness for neuro-fuzzy modeling to truck backer-upper control.

• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.681-688
• /
• 2020

The telegrapher's theory was used to develop a new formulation for the neutron noise equation. Telegrapher's equation is supposed to demonstrate a more realistic approximation for neutron transport phenomena, especially in comparison to the diffusion theory. The physics behind such equation implies that the signal propagation speed is finite, instead of the infinite as in the case of ordinary diffusion. This paper presents the theory and results of the development of a new method for calculation of the neutron noise using the telegrapher's equation as its basis. In order to investigate the differences and strengths of the new method against the diffusion based neutron noise, a comparison was done between the behaviors of two methods. The neutron noise based on SN transport considered as a precision measuring point. The Green's function technique was used to calculate the neutron noise based on telegrapher's and diffusion methods as well as the transport. The amplitude and phase of Green's function associated with the properties of the medium and frequency of the noise source were obtained and their behavior was compared to the results of the transport. It was observed, the differences in some cases might be considerable. The effective speed of propagation for the noise perturbations were evaluated accordingly, resulting in considerable deviations in some cases.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.198-207
• /
• 2010

Many methods and techniques have been developed to obtain the accurate design parameters in soft soils. In particular, several researchers suggest the techniques to get the void ratio for understanding the soil behavior. The objective of this paper verifies the accuracy of the proposed analytical solution for determining the void ratio based on the elastic wave velocities. The paper covers the theories of Wood, Biot, Gassmann and Foti proposed chronological order. The total theory represents the wave propagation in fully saturated medium. To verify the proposed analytical solution, the laboratory and field tests are carried out. After measuring the elastic wave, the void ratios are assessed using proposed equation. The volume based void ratios are also obtained for comparing with the estimated value by several equations. The values estimated by volume, Gassmann and Biot are show good similarity. However, the void ratios based on Wood and Foti methods have a slightly different trend. This study suggests that the theories of Biot and Gassmann may be a useful equation for assessing the void ratio using elastic wave velocities in the field.

• Journal of IKEEE
• /
• v.10 no.1 s.18
• /
• pp.69-74
• /
• 2006

In this paper, we present symbol detection methods for decision feedback equalizers (DFE) in trellis coded modulation systems. The proposed symbol detectors improve symbol error rate (SER) by exploiting the coding structure of trellis coded modulation (TCM). For example, for 8-PAM signals the achieved SER with the proposed detection scheme is improved to $2{\times}10^{-5}$ from $2.5{\times}10^{-2}$ of the conventional symbol-by-symbol detector under AWGN channel at 20dB SNR. This SER improvements mitigate error propagation of DFE.and produces significant over-all SER improvement for under multipath channels (for example, from 0.26 to 0.01 and 0.005 under a severe multipath channel 20dB SNR as shown in the simulation result of this paper).

• Nuclear Engineering and Technology
• /
• v.52 no.2
• /
• pp.287-295
• /
• 2020

Group method of data handling (GMDH) is considered one of the earliest deep learning methods. Deep learning gained additional interest in today's applications due to its capability to handle complex and high dimensional problems. In this study, multi-layer GMDH networks are used to perform uncertainty quantification (UQ) and sensitivity analysis (SA) of nuclear reactor simulations. GMDH is utilized as a surrogate/metamodel to replace high fidelity computer models with cheap-to-evaluate surrogate models, which facilitate UQ and SA tasks (e.g. variance decomposition, uncertainty propagation, etc.). GMDH performance is validated through two UQ applications in reactor simulations: (1) low dimensional input space (two-phase flow in a reactor channel), and (2) high dimensional space (8-group homogenized cross-sections). In both applications, GMDH networks show very good performance with small mean absolute and squared errors as well as high accuracy in capturing the target variance. GMDH is utilized afterward to perform UQ tasks such as variance decomposition through Sobol indices, and GMDH-based uncertainty propagation with large number of samples. GMDH performance is also compared to other surrogates including Gaussian processes and polynomial chaos expansions. The comparison shows that GMDH has competitive performance with the other methods for the low dimensional problem, and reliable performance for the high dimensional problem.

• Journal of Satellite, Information and Communications
• /
• v.8 no.1
• /
• pp.77-82
• /
• 2013

The object tracking method using particle filtering has been proved successful since it is based on the Monte Carlo simulation to estimate the posterior distribution of the state vector that is nonlinear and non-Gaussian in the real-world situation. In this paper, we present two nobel methods that can improve the performance of the object tracking algorithm based on the particle filtering. First one is the feedback method that replace the low-weighted tracking sample by the estimated state vector in the previous frame. The second one is an tracking box correction method to find an confidence interval of back projection probability on the estimated candidate object area. An sample propagation equation is also presented, which is obtained by experiments. We designed well-organized test data set which reflects various challenging circumstances, and, by using it, experimental results proved that the proposed methods improves the traditional particle filter based object tracking method.

• Journal of Advanced Marine Engineering and Technology
• /
• v.26 no.6
• /
• pp.695-704
• /
• 2002

Generally, induction motor controller requires rotor speed sensor for commutation and current control, but it increases cost and size of the motor. So in these days, various researches including speed sensorless vector control have been reported and some of them have been put to practical use. In this paper a new speed estimation method using neural networks is proposed. The optimal neural network structure was tracked down by trial and error, and it was found that the 8-16-1 neural network has given correct results for the instantaneous rotor speed. Supervised learning methods, through which the neural network is trained to learn the input/output pattern presented, are typically used. The back-propagation technique is used to adjust the neural network weights during training. The rotor speed is calculated by weights and eight inputs to the neural network. Also, the proposed method has advantages such as the independency on machine parameters, the insensitivity to the load condition, and the stability in the low speed operation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.8
• /
• pp.1833-1841
• /
• 1997

Rectangular dielectric waveguides, the most fundamental and indispensible elements in integrated optics, have been investigated by many researchers with various approaching methods including from the relatively approximate techniques to the numerical method. In this paper, the optimum equivalent waveguide model is adopted which is determined by a perturbation feedback process for analyzing the propagation constant by means of computer simulation, we have ascertained that the propagation constant from perturbation feedback method gives the best approximate value because it coincide with more exact value than obtained by other approximating methods. The technique also provides analytical expression for the modal field profile that should be useful in the design of various integrated optical devices.

• Journal of the Korean Society of Safety
• /
• v.19 no.1
• /
• pp.23-30
• /
• 2004

Modern production systems are very complex by request of automation, and failure modes that occur in thisautomatic system are very various and complex. The efficient fault diagnosis for these complex systems is essential for productivity loss prevention and cost saving. Traditional fault diagnostic system which perforns sequential fault diagnosis can cause catastrophic failure during diagnosis when fault propagation is very fast. This paper describes the Real-time Intelligent Multiple Fault Diagnosis System (RIMFDS). RIMFDS assesses current machine condition by using sensor signals. This system deals with multiple fault diagnosis, comprising of two main parts. One is a personal computer for remote signal generation and transmission and the other is a host system for multiple fault diagnosis. The signal generator generates various faulty signals and image information and sends them to the host. The host has various modules and agents for efficient multiple fault diagnosis. A SUN workstation is used as a host for multiple fault modules and agents for efficient multiple fault diagnosis. A SUN workstation is used as a host for multiple fault diagnosis and graphic representation of the results. RIMFDS diagnoses multiple faults with fast fault propagation and complex physical phenomenon. The new system based on multiprocessing diagnoses by using Hierarchical Artificial Neural Network (HANN).