• Title/Summary/Keyword: 상태 귀환

Search Result 32, Processing Time 0.028 seconds

Neuro-Fuzzy Controller Based on Reinforcement Learning (강화 학습에 기반한 뉴로-퍼지 제어기)

  • 박영철;심귀보
    • 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.

  • PDF

Blind Equalization of Digital Television Broadcasting Signals in Dynamic Multipath Channels (다이내믹 다중경로 채널에서의 디지털 텔레비전 방송 신호에 대한 블라인드 등화)

  • 오길남
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.41 no.5
    • /
    • pp.269-274
    • /
    • 2004
  • In this paper, proposed is the dual-mode algorithm of blind decision feedback equalizer (DFE) for digital terrestrial television signals. According to channel impairments, the proposed dual-mode algorithm for blind DFE operates in decision-directed mode or in blind mode of operation. The error signals being used in tap update of the equalizer are generated in the best mode of operations, so that the confidence of equalizer tap coefficient update is more accurate. As a result, it is possible to track the channel characteristics variations by automatic switching over between two modes of operations. For 8-level vestigial sideband modulated digital television signals, the mean square errors and symbol error rates of the proposed algorithm are compared with those of conventional methods. And the usability of the proposed scheme is assessed by computer simulations under various static and dynamic multipath channel environments.

A Feed-forward Microsecond Level Real-time SOP Finding System (순방향 마이크로초 단위의 실시간 편광상태 검출 시스템)

  • Jung, Hyun-Soo;Shin, Seo-Yong
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.33 no.1C
    • /
    • pp.94-101
    • /
    • 2008
  • In this paper, we introduce a real-time state-of-polarization(SOP) finding system. The system divides the optical wave into linear horizontal- and vertical-SOP components and measures two different beat-signals, which are produced by superposition with reference optical source, in time domain. From these measured beat signals we can get SOP information of the signal instantly. Since the proposed scheme is a feed-forward measurement system, comparing with conventional systems which require an optical feedback loop, the measurement time becomes reduced tremendously. We also introduced a novel calibration method for compensating birefringence-related errors which may occur during the measurement. We prove the operation and performance of the proposed system through computer simulation and actual experiments.

An Experimental Study on an Optimal Controller for the Overhead Crane Using the Genetic Algorithm (유전자 알고리즘을 이용한 천정크레인의 최적제어기에 실험적 연구)

  • Choi, Hyeung-Sik;Kim, Kil-Tae
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.16 no.1 s.94
    • /
    • pp.34-41
    • /
    • 1999
  • This paper presents a HGA-based(hybrid genetic algorithm) optimal control strategy to control of the swing motion and the transfer of the overhead crane. The objective is to achieve the regulation of the fast swing motion or fast position control. The controller is based on the state feedback. The HGA-based optimal algorithm is applied to find optimal gains of the controller. Computer simulation and experiments were performed to demonstrate the effectiveness of the proposed control scheme.

  • PDF

Output Feedback LQ control of a Space Robot in Discrete-Time (우주로봇의 이산시간 출력 귀환 LQ 제어)

  • 임승철
    • Journal of KSNVE
    • /
    • v.6 no.5
    • /
    • pp.567-574
    • /
    • 1996
  • This paper concerns an articulated space robot with flexible links. The equations of its motion are derived by means of the Lagrangian mechanics. Assuming that magnitude of elastic motions are relatively small, the perturbation approach is taken to separate the original equations of motion into linear and nonlinear equations. Th effect the desired payload motion, open loop control inputs are first determined based on the nonlinear equations. One the other hand, in order to reduce the positional errors during the maneuver, vibration suppression is actively done with a feedforward control for disturbance cancellation to some extent. Additionally, for performance robustness against residual disturbance, an LQ control modified to have a prescribed degree of stability is applied based on the linear equations. Measurement equations are formulated to be used for the maximum likelihood estimator to reconstruct states from the original robot equations of motion. Finally, numerical simulations show effectiveness of the proposed control design scheme.

  • PDF

A Study on Characteristics of Heat Transfer for a Rotating Heat Pipe with a Trigonal Cross Section (삼각 단면을 갖는 회전 열파이프의 열전달 특성에 관한 연구)

  • 이진성;김철주;김윤제;최영준;홍성은
    • Proceedings of the Korea Society for Energy Engineering kosee Conference
    • /
    • 1997.10a
    • /
    • pp.114-121
    • /
    • 1997
  • 회전 열파이프의 열전달 성능은 액막 두께 및 증발부로 귀환되는 응축 액막 유동율에 의해 결정된다. 그 동안 응축액 유동율을 촉진시키기 위하여 용기 내벽에 groove, 테이퍼 및 나선형 코일을 삽입하여 유동율을 높이는 방법들이 연구되었다. 본 연구도 회전 열파이프의 내부 관벽 구조에 관한 것으로써 삼각 단면을 갖는 회전 열파이프의 열전달 특성을 파악하고자 하였다. 삼각 단면을 갖는 회전 열파이프는 고속 회전 영역에서 모서리 부분으로 액막이 집중되어 관 내벽에 형성되는 액막 두께를 줄일 수 있으나 증발부에서 국부적인 과열이 발생되어 불안정한 작동 상태를 나타내었다. 따라서 본 연구에서는 개선방안으로 증발부에 부분적으로 원형관을 접합하였으며, 그 결과 dry-out의 억제와 함께 삼각 유동 단면에 의한 액막 두께 감소 효과를 볼 수 있었다. 회전체 발열부 냉각에 적용시키기 위해서는 앞으로 최적의 기하학적 형상에 따른 충전율 및 액막에서의 열전달에 대한 정량적인 해석 연구가 필요할 것으로 생각된다.

  • PDF

A Study on the Design of the Optimal Nonlinear Controller for Single State Feedback (단일상태 귀환 제어계의 최적 비선형제어기 설계에 관한 연구)

  • No, Yong-Gyun;Jo, Gyeom-Rae;Lee, Jin-Geol
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.6 no.1
    • /
    • pp.85-92
    • /
    • 1989
  • For feedback control of a linear dynamic system the optimum linear state regulator (OLSR) can be implemented only if all states are available for feedback. This work demonstrates that when only the output state is available for feedback, a nonlinear controllers can give improved performance over that obtained by a proportional controller. This paper found the optimal control law by dynamic programming and principles of optimalityl. This, performances of both proportional and nonlinear controllers are compared with performance of optimum linear state regulator.

  • PDF

Experiences of Information Encountering on the Use of Electronic Scholarly Resources (과제 수행 시 전자학술정보 사용에 있어서의 정보 조우 경험 행태)

  • Lee, You-Jin
    • Proceedings of the Korean Society for Information Management Conference
    • /
    • 2018.08a
    • /
    • pp.69-72
    • /
    • 2018
  • 엄청난 양의 정보와 정보기술들이 만연한 정보환경이 도래함에 따라 사람들은 의식적으로 정보를 탐색하는 과정에서 원래 찾으려 했던 주제는 아니지만 유용하고, 흥미로운 정보를 발견하는 경험을 보다 자주 접할 수 있게 되었다. 이에 우연한 정보의 획득(OAI)에 대한 연구의 필요성이 제기되고 있다. 그러나 현재 국내의 문헌정보학 분야에 있어 이에 대한 연구는 미비한 상태이다. 이에 본 연구에서는 대학생과 대학원생의 과제 수행 시 전자학술정보를 사용하는 데에 있어 발생하는 정보 조우(IE) 경험에 대해 알아보고자 하였다. 이를 위해 먼저 선행연구 분석을 통해 과제 수행을 목적으로 가장 비중 있게 활용되고 있는 정보원이 전자학술정보임을 파악하고, 과제 수행 시 전자학술정보를 활용해 본 적이 있는 대학생과 대학원생을 대상으로 설문조사를 실시하였다. 그 결과, 설문에 참여한 응답자들은 Erdelez(2004)가 제시한 정보 조우의 기능적 모형에서 주목(noticing)과 검토(examining), 귀환(returning) 과정에 대한 경험을 비중 있게 인지하고 있는 것으로 나타났다. 반면 중단(stopping)의 경우, 상대적으로 긍정적인 답변의 비율이 낮았으며, 획득(capturing)에 대한 물음에서는 차이를 보였다.

  • PDF

Performance Analysis of Space-Time Coded Spatial Multiplexing Systems with Rate Allocation and Power Control (전송률 할당 및 전력 제어를 갖는 시공간 블록 부호화한 공간 다중화 시스템의 성능 분석)

  • Na, Seung-Gun;Hwang, Hyeon-Chyeol;Kim, Seok-Ho;Choi, Sun-Ho;Kwak, Kyung-Sup
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.30 no.7A
    • /
    • pp.568-577
    • /
    • 2005
  • In this paper, we propose the transmission scheme for the space-time block coded spatial multiplexing systems that have adaptive rate and power allocation per each transmit antenna through the use of feedback information related to channel state. Simulation results show that the adaptive power and rate transmission scheme gain more than 4.5 dB over conventional equal-power and rate transmission scheme.

Load Sharing Control by Following Average Torque Current in Continuous Casting (연속 주조 공정에서 평균 토크전류 추종에 의한 인발력 분배 제어)

  • Chun, Chang-Keun;Kim, Cheul-U
    • Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
    • /
    • v.18 no.3
    • /
    • pp.74-80
    • /
    • 2004
  • If the withdrawal force of strand driven roll which is controlled with predetermined speed isn't distributed regularly in continuous casting process, mold level is changed cyclically and slab quality is not good. In this paper, both casting speed control and load sharing control algorithm of strand driven roll according to ratio which is set up by operator at same time is proposed. The proposed algorithm is to share the withdrawal force by following torque current of each driven roll as average torque current by changing speed reference of each driven roll motor. The load sharing control with anti-wind up for improvement transient state is adopted and the proposed algorithm is implemented in POSCO pilot caster.