• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.245-248
• /
• 2000

In this paper we improve the performance of autonomous mobile robot by induction of reinforcement learning concept. Generally, the system used in this paper is divided into two part. Namely, one is neural-fuzzy and the other is dynamic recurrent neural networks. Neural-fuzzy determines the next action of robot. Also, the neural-fuzzy is determined to optimal action internal reinforcement from dynamic recurrent neural network. Dynamic recurrent neural network evaluated to determine action of neural-fuzzy by external reinforcement signal from environment, Besides, dynamic recurrent neural network weight determined to internal reinforcement signal value is evolved by genetic algorithms. The architecture of propose system is applied to the computer simulations on controlling autonomous mobile robot.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.354-358
• /
• 2001

This paper presents a fuzzy neural network model which solves the underutilization problem. This fuzzy neural network has both stability and flexibility because it uses the control structure similar to AHT(Adaptive Resonance Theory)-l neural network. And this fuzzy nenral network does not need to initialize weights and is less sensitive to noise than ART-l neural network is. The learning rule of this fuzzy neural network is the modified and fuzzified version of Kohonen learning rule and is based on the fuzzification of leaky competitive leaming and the fuzzification of conditional probability. The similarity measure of vigilance test, which is performed after selecting a winner among output neurons, is the relative distance. This relative distance considers Euclidean distance and the relative location between a datum and the prototypes of clusters. To compare the performance of the proposed fuzzy neural network with that of Kohonen Self-Organizing Feature Map the IRIS data and Gaussian-distributed data are used.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.117-126
• /
• 2013

A ship is intended to reach a specified target point in the minimum-time when it travels with a constant speed through a region of strong currents and its heading angle is the control variable. This is called the Zermelo's navigation problem. Its approximate solution for the minimum-time control may be found using the calculus of variation. However, the accuracy of its approximate solution is not high since the solution is based on a table form of inverse relations for some complicated nonlinear equations. To enhance the accuracy, this paper employs the neural network to represent the inverse relation of the complicated nonlinear equations. The accurate minimum-time control is possible with the interpolation property of the neural network. Through the computer simulation study we have found that the proposed method is superior to the conventional ones.

• 전기의세계
• /
• v.38 no.2
• /
• pp.17-22
• /
• 1989

신경회로의 실로 광범위한 응용중에 시스템 제어가 차지하는 중요도는 산업 공정제어 시스템이라는 막대한 시장으로 보아 가장 크다고 본다. 그러나 이와 같은 신경회로제어가 실제로 보편화도기 위해서는 다음과 같은 연구가 선행되어야 한다. 1) 신경 회로의 경제적 구현 방식-Analog, Digital, Optical회로 2) 빠르고 효율적인 학습 알고리듬 3) 사용하기 쉬운 software 4) 신경회로의 응용분야 개발 신경회로는 이런 시스템을 가장 효과적으로 제어하는 방식일 것이다. 이로 볼때 앞으로 20년간 현존하는 산업제어시스템은 차차 신경 회로제어로 부분적 또는 전체적으로 대체되어야 한다. 물론 그에 앞서 기존의 시스템과 신경 회로방식을 어떻게 효율적, 경제적으로 결합하느냐하는 system engineering 연구가 선행되어야 함은 물론이다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.34-45
• /
• 1997

In this paper, we present hardware implemcntation of self-organizing feature map (SOFM) neural networkwith constant adaptation gain and binary reinforcement function on FPGA. Whereas a tnme-varyingadaptation gain is used in the conventional SOFM, the proposed SOFM has a time-invariant adaptationgain and adds a binary reinforcement function in order to compensate for the lowered abilityof SOFM due to the constant adaptation gain. Since the proposed algorithm has no multiplication operation.it is much easier to implement than the original SOFM. Since a unit neuron is composed of 1adde $r_tracter and 2 adders, its structure is simple, and thus the number of neurons fabricated onFPGA is expected to he large. In addition, a few control signal: ;:rp sufficient for controlling !he neurons.Experimental results show that each componeni ot thi inipiemented neural network operates correctlyand the whole system also works well.stem also works well.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.179-180
• /
• 2008

본 논문에서는 극배치(pole placement) 제어 시스템의 상태들에 의해서 훈련된 신경 회로망(Neural Network)을 기반으로 새로운 슬라이딩 평면의 설계 기법을 제안한다 훈련된 데이더를 가진 신경 회로망은 배치 제어의 성능을 가지며 새로운 슬라이딩 평면을 설계하는데 사용되어 진다. 그 결과 시스템의 파라미터 불확실성이 존재하더라도 제안된 슬라이딩 평면으로서 슬라이딩 모드 제어의 강인성이 신경회로망을 통한 극배치제어의 성능에 추가되는 것이 가능하다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2775-2784
• /
• 2013

A bead is intended to reach a specified target point in the minimum-time when it travels along a certain curve on a vertical plane with the gravity. This is called the brachistochrone problem. Its minimum-time control input may be found using the calculus of variation. However, the accuracy of its minimum-time control input is not high since the solution of the control input is based on a table form of inverse relations for some complicated nonlinear equations. To enhance the accuracy, this paper employs the neural network to represent the inverse relation of the complicated nonlinear equations. The accurate minimum-time control is possible with the interpolation property of the neural network. For various final target points, we have found that the proposed method is superior to the conventional ones through the computer simulations.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.6
• /
• pp.77-82
• /
• 2005

This paper is proposed fuzzy neural network(FNN) and artificial neural network(ANN) based on the vector controlled induction motor drive system. The hybrid combination of fuzzy control and neural network will produce a powerful representation flexibility and numerical processing capability. Also, this paper is proposed control and estimation of speed of induction motor using fuzzy and neural network. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The error between the desired state variable and the actual one is back-propagated to adjust the rotor speed, so that the actual state variable will coincide with the desired one. The back propagation mechanism is easy to derive and the estimated speed tracks precisely the actual motor speed. This paper is proposed the experimental results to verify the effectiveness of the new method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.05a
• /
• pp.96-101
• /
• 1998

많은 분야에서 널리 사용되고 있는 PID 제어기의 형태는 오차를 갖는 폐루프 시스템으로 구성되며, PID 제어기는 비례, 적분, 미분 제어기로 나누어진다. PID 제어기의 형태가 여러 가지로 제안되고 있지만 보다 중요한 것은 PID 제어기의 파라미터들을 어떻게 적절히 정하느냐 하는 파라미터 조정 문제이다. 실제로 산업 현장에 설치되어 있는 PID 제어기는 대부분 숙련된 기술자에 의해 수동 조작에 의한 시행 착오(trial and error) 법으로 동조되고 있다. 이 경우는 많은 노력과 시간이 소비되고, 외란(disturbance)이 첨가될 경우 적절히 동조된다는 보장도 없다. 본 논문에서는 이러한 문제를 해결하고자 신경회로망을 이용하여 PID 제어기의 파라미터를 동조하는 제어 방법을 제안하였다. 단일 뉴런으로 구성하여 구조가 간단하고, 학습에 의한 성능 개선이 가능하다. 오차 역전파(Error Back-Propagation) 알고리즘에 의하여 PID 파라미터가 되는 가중치를 자동 동조하는 방법이다. 제안한 방식의 유용성을 보이기 위해 DC 서보 모터와 비선형 시스템인 단일 관절 매니퓰레이터를 대상으로 시뮬레이션을 하였다.

• 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.