• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.23-33
• /
• 1994

In this paper, we propose a probabilistic model appropriate for the bearing estimator which uses cross-correlation method following a close investigation on real underwater acoustic bearing data. The well-known JPDA(Joint Probabilistic Data Association) filter is tuned to the underwater acoustic bearing estimation based on the result that the reliability of the bearing measurement is related to the amplitude of the cross-correlation peak. The proposed probabilistic model is shown to be adequate by presenting the results of the improved tracking performance of the modified filter for various real bearing data as well as artificially generated ones.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.419-422
• /
• 2005

In this note, the Takagi-Sugeno (T-S) fuzzy-model-based state estimator using standard Kalman filter theory is investigated. In that case, the dynamic system model is represented the T-S fuzzy model with the fuzzy state estimation. The steady state solutions can be found for proposed modeling method and dynamic system for maneuvering targets can be approximated as locally linear system. And then, modeled filter is corrected by the fuzzy gain which is a fuzzy system using the relation between the filter residual and its variation. This paper studies the T-S fuzzy model-based state estimator which the dynamic system can be approximated as linear system.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.7 no.6
• /
• pp.517-523
• /
• 2002

A sensorless control of a PM synchronous motor with the compensation of the motor parameter variation is presented. The rotor position is estimated by using the d-axis and q-axis current errors between the real system and motor model of the position estimator. The stator resistance is measured at low speeds when the motor changes its rotating direction and the variation of the stator resistance and back emf constant caused by the temperature variation is compensated. The gains in the position estimator are also adapted according to the motor speeds.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.7
• /
• pp.609-615
• /
• 2007

We propose an optimized adaptive PID control scheme. This paper is focused on the development of model reduction as well as a new adoptive control structure (viz. a recursive least square estimation (RLSE) method-based structure) that is constructed with smith-predictor structure and a real time estimator. The estimator adjust parameters of a reduced model in real time. It leads to robust and superb control performance for the noise or variation of parameters of process. Experimental study reveals that the proposed control structure exhibits more superb output performance in comparison to some previous methods.

• Journal of IKEEE
• /
• v.7 no.1 s.12
• /
• pp.107-118
• /
• 2003

In this paper, dynamic control model is formulated by considering the geometrical structure of the deaerator storage tank in nuclear power plant and input-output flow rate at steady state, and we describe fault detection and diagnosis (FDD) scheme based on the adaptive estimator. The performance and effectiveness of the proposed FDD scheme are evaluated by applying real operating data obtained from the YOUNGKWANG 3 & 4 FSAR.

• Journal of Advanced Marine Engineering and Technology
• /
• v.24 no.6
• /
• pp.102-109
• /
• 2000

In this industrial induction motor speed and torque controlled drive system, the closed loop control usually requires the measurement of speed or position of amotor. However a sensorless drive of an induction motor has several advantages ; low cost and mechanical simplicity. Thus this paper investigates a field oriented control method without speed and flux sensors. The proposed control strategy is based on the Model Reference Adaptive System(MRAS) using a new flux estimator which replaces integrators with two lag circuits as the reference model. This algorithm may overcome several shortages of conventional MRAS such as integrator problems, small EMF at low speed. The simulation and experimental results indicate good speed responses.

• Proceedings of the KIPE Conference
• /
• 1998.07a
• /
• pp.245-248
• /
• 1998

This paper proposes a sensorless velocity estimator using the reduced-order state equation of induction motor based on Kalman Filter. The electrical transients in the stator voltage equations of induction motor are neglected in the reduced-order model. The advantage of using the reduced-order model is to reduce the required number of numerical integrations for filtering the rotor speed. As changing the operating points and the parameters of the induction motor in simulation studies, the behavior of the sensorless velocity estimator as predicted by the reduced-order state equation of induction machine is compared with the behavior predicted by the complete state equation of induction machine.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.449-455
• /
• 2011

In this paper, a time-delay problem of a tele-operated control system is investigated and compensated by neural network. The smith predictor requires an exact system model to deal with a time-delay in the system. To compensate for modeling errors in the configuration of the Smith predictor, a neural network approach is presented. Based on forming the Smith predictor structure, the radial basis function(RBF) neural network estimator is used. Simulation and experimental studies are conducted to show the functionality of the proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.2
• /
• pp.125-130
• /
• 2001

This paper presents an indirect field-oriented (IFO) induction motor position servo drives which uses the model following adaptive controller with the artificial neural network(ANN)-based rotor resistance estimator. The model reference adaptive system(MRAS)-based 2-layer ANN estimates the rotor resistance on-line and a linear model-following position controller is designed by using the estimated the rotor resistance value. At the end, a fuzzy logic system(FLS) is added to make the position controller robust to the external disturbances and the parameter variations. The simulation results show the effectiveness of the proposed method.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.501-506
• /
• 2020

질의 난이도 분석 문제는 자연어 질의문을 답변할 때 어려움의 정도를 측정하는 문제이다. 질의 난이도 분석 문제는 문서 독해, 의학 시험, 비디오 질의 등과 같은 다양한 데이터셋에서 연구되어 왔다. 본 논문에서는 질의문과 질의문에 응답하기 위한 정보들 간의 관계를 파악하는 것으로 질의 난이도 분석 문제를 접근하여 이를 BERT와 Dual Multi-head Attention을 사용하여 모델링 하였다. 본 논문에서 제안하는 모델의 우수성을 증명하기 위하여 최근 자연언어이해 부분에서 높은 성능을 보여주는 기 학습 언어 모델과 이전 연구의 질의 난이도 분석 모델과의 성능을 비교하였고, 제안 모델은 대표적인 비디오 질의 응답 데이터셋인 DramaQA의 Memory Complexity에서 99.76%, Logical Complexity에서는 89.47%의 정확도로 가장 높은 질의 난이도 분석 성능을 보여주었다.