회전 역진자의 위치제어를 위한 적응 퍼지-신경망 제어기의 설계

탁한호,추연규 진주산업대학교 농업기술연구소 2000 農業技術硏究所報 Vol.13 No.-

In this paper, an position control method using adaptive fuzzy-neural controller(AFNC) is proposed for modeling of nonlinear complex systems. The proposed adaptive fuzzy-neural controller implements system structure and parameter identification using the intelligent schemes together with optimization theory, linguistic fuzzy implication rules, and neural networks from input and output data of processes. Inference type for this adaptive fuzzy-neural controller is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of adaptive fuzzy-neural controller are tuned automatically using improved modified complex method and modified leaning algorithm. For the purpose of its application to nonlinear processes, data for rotating inverted pendulum system ar used for the purpose of evaluating the performance of the proposed adaptive fuzzy-neural controller. The results show that the proposed method can produce the intelligence model with higher accuracy than other works achieved previously.

RLS 추정기법을 이용한 직류 서어보 전동기의 위치제어 ( RLS estimator based on position control of DC servo motor )

탁한호,최부기,이형기 한국통신학회 1991 한국통신학회 학술대회논문집 Vol.- No.-

적응 퍼지 제어기를 이용한 유연성 빔의 위치제어

탁한호,이병로,김병철,전중창,황석순,정민우 진주산업대학교 산업과학기술연구소 2003 산업과학기술연구소보 Vol.- No.10

In this paper, applications of adaptive fuzzy controller to position control of flexible beam are considered. When a flexible beam is rotated by a motor through the fixed end, transverse vibration may occur. The architecture and learning underlying adaptive networks based fuzzy inference system (ANFIS) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge and stipulated input-output data pairs. Therefor, a dynamic model for a flexible beam is derived, and then a comparative analysis was made with before learning and after learning adaptive fuzzy controller through an simulation. The results are presented to illustrate the advantages and improved performance of the proposed position control cver the after learning adaptive fuzzy controller.

RBF를 이용한 적응궤환 신형화 제어기의 설계

탁한호,추연규,정민우,이인용 진주산업대학교 농업기술연구소 1999 農業技術硏究所報 Vol.12 No.-

본 논문은 비선형 시스템인 도립진자 시스템의 효율적인 위치제어를 위해 새로운 제어기법인 RBF 신경회로망 제어이론을 적용하였다. 전체적인 제어시스템의 구성은 플랜트를 제어하기 위해 선형 제어기와 비선형 제어기를 설계하였고, 여기서 설계한 비선형 제어기는 PD 제어기와 신경회로망 제어기를 사용하여 병렬로 구성하였다. 또한 이들의 제어기법에 대한 특성 비교를 위하여 시뮬레이션을 행하였다. 시뮬레이션 결과에서는 신경회로망 제어기가 PD 제어기보다 원하는 위치를 오차가 적으면서 더 빠른 속도로 수렴함을 알 수 있었다. 결과적으로 이 논문에서 설계한 RBF 신경회로망을 이용한 신경회로망 적응 궤환 선형화 제어기가 도립진자 시스템의 제어에 효과적이라는 것을 알았다. The paper demonstrates that RBF(Radial Basis Function) neural networks can be used effective for the identification of inverted pendulum system. The content of this paper concerns RBF neural networks model, where not all inputs to and outputs from the networks are measurable. Computer simulation results reveal that the identification scheme suggested are practically feasible.

Hierarchical behavior control of mobile robot based on space & time sensor fusion(STSF)

탁한호 한국지능시스템학회 2006 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.6 No.4

Navigation in environments that are densely cluttered with obstacles is still a challenge for Autonomous Ground Vehicles (AGVs), especially when the configuration of obstacles is not known a priori. Reactive local navigation schemes that tightly couple the robot actions to the sensor information have proved to be effective in these environments, and because of the environmental uncertainties, STSF(Space and Time Sensor Fusion)-based fuzzy behavior systems have been proposed. Realization of autonomous behavior in mobile robots, using STSF control based on spatial data fusion, requires formulation of rules which are collectively responsible for necessary levels of intelligence. This collection of rules can be conveniently decomposed and efficiently implemented as a hierarchy of fuzzy-behaviors. This paper describes how this can be done using a behavior-based architecture. The approach is motivated by ethological models which suggest hierarchical organizations of behavior. Experimental results show that the proposed method can smoothly and effectively guide a robot through cluttered environments such as dense forests.

Control of the Mobile Robot Navigation Using a New Time Sensor Fusion

탁한호,김창근,김명규 한국지능시스템학회 2004 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.4 No.1

This paper proposes a sensor-fusion technique where the data sets for the previous moments are properly transformed and fused into the current data sets to enable accurate measurement, such as, distance to an obstacle and location of the service robot itself. In the conventional fusion schemes, the measurement is dependent on the current data sets. As the results, more of sensors are required to measure a certain physical parameter or to improve the accuracy of the measurement. However, in this approach, instead of adding more sensors to the system, the temporal sequence of the data sets are stored and utilized for the measurement improvement. Theoretical basis is illustrated by examples and the effectiveness is proved through the simulations. Finally, the new space and time sensor fusion(STSF) scheme is applied to the control of a mobile robot in an unstructured environment as well as structured environment.

PID 제어기의 퍼지 이득 조정

탁한호,추연규,김현덕 진주산업대학교 1999 산업과학기술연구소보 Vol.- No.6

The purpose of this paper is to find PID parameters. The model of controller is designed by Matlab-Simulink program and each parameter of PID is estimated automatically by the Fuzzy controller. The simulation is carried out on FGS(Fuzzy Gain Scheduling), and then this is compared and analyzed with the simple PID controller.

신경망을 이용한 회전 역진자 시스템의 제어

탁한호,이주원,신춘식 진주산업대학교 1997 論文集 Vol.36 No.-

Today, the complexity and nonlinearity in system have increased. For example, an inverted pendulum of nonlinear system is widely used as a substitute of nonlinear control system. But it is difficult to establish mathemathical equation and model control system. This paper aims to propose a method to control desired position and desired pole angle of the rotary inverted pendulum using multilayer neural networks. In the begining of learning, we controller the system using PD controller to avoid unstability of system. After learning of neural networks we controlled the system using neural networks. In this paper we compare the result of PD controller with result of neural networks, and point out some good points of neural networks for nonlinear system control.

상호작용 비선형성이 있는 다중 리더와 단일 추종자를 위한 일치 기반의 협력 제어

탁한호,임영훈,Tack, Han-Ho,Lim, Young-Hun 한국정보통신학회 2021 한국정보통신학회논문지 Vol.25 No.11

본 논문에서는 상호작용을 갖는 다중 리더들과 단일 추종자를 위한 협력 제어 문제를 고려한다. 리더들은 제어 가능하고, 추종자는 모든 리더들과 상호작용을 갖고 상호작용에 의하여 제어된다. 따라서 리더들을 제어함으로써 일치를 달성하는 협력 제어문제를 연구한다. 리더들과 추종자는 각 일차 적분기와 이차 적분기로 모델링되고 상호작용에 비선형성이 존재한다고 가정한다. 리더들은 추종자 사이의 상호작용만을 측정할 수 있고 이웃한 리더들과 측정된 정보를 교환할 수 있다. 따라서 본 논문에서는 측정된 상호작용에 대한 정보와 속도 일치를 위한 가상의 속도 변수에 대한 정보교환을 이용하여 일치 기반의 협력 제어 알고리즘을 제안한다. 라살레 불변의 법칙을 기반으로 에이전트들의 공통 상태로의 수렴을 해석한다. 마지막으로 이론적 결과들을 검증하기 위하여 수치적 예제를 제공한다. This paper considers the cooperative control problem for multiple leaders and a single follower with interactions. The leaders are controllable, and the follower has interactions with all leaders and is controlled by the interactions. Then, we study the cooperative control problem that achieves the consensus by controlling the leaders. The leaders and the follower are modeled by the single-integrator and the double-integrator, respectively, and it is assumed that the interactions have the nonlinearities. The leaders can estimate the interaction between the follower and exchange the estimated information with neighbors. Then, this paper proposes the consensus-based cooperative control algorithm using the information exchange of the estimated interactions and the virtual velocity variables to achieve the velocity consensus. We analyze the convergence of the agents to the common state based on the Lasalle's Invaraince Principle. Finally, we provide the numerical example to validate the theoretical results.

보상형 퍼지 제어기 설계에 관한 연구

탁한호,추연규 진주산업대학교 2000 산업과학기술연구소보 Vol.- No.7

FLC(Fuzzy Logic Controller) is stronger to the disturbance than a classical controller and its overshoot of the intialized value is excellent. In case an unknown process or the mathematical modeling of a complicated system is impossible, a fit control quantity can be acquired by the fuzzy inference, But FLC is not able to adjust the rule-base with respect to any sudden changes of the control environment. There are many ways to overcome the problems, but we will propose CFLC(Compensated Fuzzy Logic Controller) which combines PID controller with FLC. In this paper, the output characteristics of CFLC will be compared and analyzed with those PID controller.