• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.1 s.232
• /
• pp.88-95
• /
• 2005

This paper presents a design scheme of model reference adaptive control incorporating a Neural Network for a pneumatic servo system. The parameters of discrete-time model of plant are estimated by using the recursive least square method. Neural Network is utilized in order to compensate the nonlinear nature of plant such as compressibility of air and frictions present in cylinder. The experiment of a trajectory tracking control using the proposed control scheme has been performed and its effectiveness has been proved by comparing with the results of a model reference adaptive control.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.375-382
• /
• 2004

This paper presents control designs using neural networks (NN) for a XY positioning table. The proposed neuro-controller is composed of an outer PD tracking loop for stabilization of the fast flexible-mode dynamics and an NN inner loop used to compensate for the system nonlinearities. A tuning algorithm is given for the NN weights, so that the NN compensation scheme becomes adaptive, guaranteeing small tracking errors and bounded weight estimates. Formal nonlinear stability proofs are given to show that the tracking error is small. The proposed neuro-controller is implemented and tested on an IBM PC-based XY positioning table, and is applicable to many precision XY tables. The algorithm, simulation, and experimental results are described. The experimental results are shown to be superior to those of conventional control.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.2
• /
• pp.231-238
• /
• 1993

A rules of fuzzy control is to represent an expert‘s and engineer‘s ambiguous control knowledge of system with some lingustic rules. This rule is very difficult to represent perfectly because expert‘s knowledge is not precise and the rule is not perfect. We propose the fuzzy reasoning and learning to upgrade precision of imperfect rules successively after system running. In the proposed method, the precision of the backward part of a fuzzy rule is improved by back propagation learning method. Also, the method reasons the compatibility degree of the forward part of fuzzy rule by associative memory method. This method this is successfully applied to design auto-parking fuzzy controller in which expert‘s technology and knowledge are required in the limited area.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.510-518
• /
• 2014

In this study, in order to improve and optimize the performance of the turning mechanism for a fish robot in the fluid, we propose the tail joint trajectories using neural networks to mimic the CST(C-shape Sharp Turn) patterns of a real fish which is optimized in the natural environment. In order to mimic the CST patterns of a fish, we convert the sequential recording CST patterns into the coordinate data, and change the numerical coordinate data into a functions. We change the motion functions to the relative joint angles which is adapted to suit robot's shape and data. However, these relative joint trajectories obtained by the sequential recording of the carp have low-precision. It is difficult to apply to the control of a fish robot. Therefore, the relative joint trajectories are interpolated using neural networks with superior generalization ability and applied to the fish robot. we have found that the proposed method using neural networks is superior to ones using high-order polynomial equation through the computer simulations.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.173-183
• /
• 1998

In this paper, an auto-tuning method for fuzzy controller's membership functions based on the neural network is presented. The neural network emulator offers the path which reforms the fuzzy controller's membership functions and fuzzy rule, and the reformed fuzzy controller uses for speed control of induction motor. Thus, in the case of motor parameter variation, the proposed method is superior to a conventional method in the respect of operation time and system performance. 32bit micro-processor DSP(TMS320C31) is used to achieve the high speed calculation of the space voltage vector PWM and to build the self-learning fuzzy control algorithm. Through computer simulation and experimental results, it is confirmed that the proposed method can provide more improved control performance than that PI controller and conventional fuzzy controller.

• 전기의세계
• /
• v.40 no.4
• /
• pp.59-65
• /
• 1991

본 고에서는 퍼지 이론과 신경회로망 기법의 유사한 특성들을 살펴보고, 제어기 구성을 중심으로 한 응용 사례들을 소개하고자 한다. 그리고 앞으로 활발하게 연구가 이루어질 몇 분야들을 열거한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.628-631
• /
• 1992

The position control for DC motor under the unpredictable load variations is presented. Neural network controller trained to deal with this problem provide the estimates of system parameters. Pole placement is also performed in accordance with them. The proposed method is validated through computer simulation.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.255-256
• /
• 2008

미래의 로봇 산업은 기존 자동화 산업 뿐만 아니라 안내, 보안 등의 가정, 공공기관 또는 우주, 심해 등에서 인간을 대신할 대안으로 활용되어질 전망이다. 이는 기존의 단순반복에서 벗어나 자율이동, 자기학습 등이 가능하도록 개발되어야 한다. 본 논문에서는 로봇을 공공기관에서의 안내, 보안 또는 위험현장, 군사용으로 적용하기 위해 필요한 기술인 자율이동시스템을 개발하였다. 로봇이 자율이동하기 위해서는 자기위치추적, 장애물 탐지 및 회피 기술이 필요하다. 이를 위해 초음파센서를 이용해 로봇을 탐지 시스템을 구성하였으며 LM신경회로망 제어기를 사용하여 로봇의 이동을 제어하였다. 또한 시뮬레이션을 통해 장애물 회피능력과 이동성능 결과를 검증하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.395-400
• /
• 2000

In this paper, we propose a new neuro-fuzzy controller based on reinforcement learning. The proposed system is composed of neuro-fuzzy controller which decides the behaviors of an agent, and dynamic recurrent neural networks(DRNNs) which criticise the result of the behaviors. Neuro-fuzzy controller is learned by reinforcement learning. Also, DRNNs are evolved by genetic algorithms and make internal reinforcement signal based on external reinforcement signal from environments and internal states. This output(internal reinforcement signal) is used as a teaching signal of neuro-fuzzy controller and keeps the controller on learning. The proposed system will be applied to controller optimization and adaptation with unknown environment. In order to verifY the effectiveness of the proposed system, it is applied to collision avoidance of an autonomous mobile robot on computer simulation.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1124-1128
• /
• 2021

As regulations of emissions from ships become more stringent, electric propulsion systems have been increasingly used to solve this problem in vessels ranging from large merchant ships to small and medium-sized ships. Methods for improving the efficiency of the electric propulsion system include the improvement of power sources; the use of a system linked to environmentally friendly power sources, such as batteries, fuel cells, and solar power; and the development of hardware and control methodology for rectifiers, power conversion devices, and propulsion motors. The method using a phase-shifting transformer with diodes has been widely used for rectification. Power semiconductor devices with grid connection to an environmentally friendly power source using DC distribution, a variable speed power source, and the application of small and medium-sized electric propulsion systems have been developed. Accordingly, the demand for active front-end (AFE) rectifiers is increasing. In this study, a method using a neural network rather than a conventional proportional-integral controller was proposed to control the AFE rectifier. Tested controller data were used to design a neural network controller trained through MATLAB/Simulink. The neural network controller was applied to a rectification system designed using PSIM software. The results indicated the effectiveness of improving the waveform and power factor DC output stage according to the load variation. The proposed system can be applied as a rectification system for small and medium-sized environmentally friendly ships.