• 제목/요약/키워드: Direct learning control

검색결과 106건 처리시간 0.044초

Fuzzy-CMAC 신경회로망 기반 적응제어 (Adaptive Control Based on Fuzzy-CMAC Neural Networks)

  • 최종수;김형석;김성중;권오신
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1996년도 하계학술대회 논문집 B
    • /
    • pp.1186-1188
    • /
    • 1996
  • Neural networks and fuzzy systems have attracted the attention of many researehers recently. In general, neural networks are used to obtain information about systems from input/output observation and learning procedure. On the other hand, fuzzy systems use fuzzy rules to identify or control systems. In this paper we present a generalized FCMAC(Fuzzified Cerebellar Model Articulation Controller) networks, by integrating fuzzy systems with the CMAC(Cerebellar Model Articulation Controller) networks. We propose a direct adaptive controller design based on FCMAC(fuzzified CMAC) networks. Simulation results reveal that the proposed adaptive controller is practically feasible in nonlinear plant control.

  • PDF

신경회로망을 이용한 리니어 펄스 모터의 정밀 제어 (Precise Control of a Linear Pulse Motor Using Neural Network)

  • 권영건;박정일
    • 제어로봇시스템학회논문지
    • /
    • 제6권11호
    • /
    • pp.987-994
    • /
    • 2000
  • A Linear Pulse Motor (LPM) is a direct drive motor that has good performance in terms of accuracy, velocity and acceleration compared to the conventional rotating system with toothed belts and ball screws. However, since an LPM needs supporting devices which maintain constant air-gap and has strong nonlinearity caused by leakage magnetic flux, friction and cogging, etc., there are many difficulties in improvement on accuracy with conventional control theory. Moreover, when designing the position controller of LPM, the modeling error and load variations has not been considered. In order to compensate these components, the neural network with conventional feedback controller is introduced. This neural network of feedback error learning type changes the current commands to improve position accuracy. As a result of experiments, we observes that more accurate position control is possible compared to conventional controller.

  • PDF

메타인지 전략 학습을 통한 수학적 사고력 신장 방안 연구 (Metacognitive Learning Methods to Improve Mathematical Thinking)

  • 박혜연;정순모;김응환
    • 한국학교수학회논문집
    • /
    • 제17권4호
    • /
    • pp.717-746
    • /
    • 2014
  • 21세기 지식 기반 사회에 적합한 인재는 자기주도적으로 지적 가치를 창출할 수 있는 자율적이고 창의적인 사고력을 갖춘 사람으로, 수학교육 현장에서는 학생들의 창의사고력이 강조되고 있다. 이러한 창의사고력은 자신의 사고과정을 모니터하고 조절 통제하는 메타인지능력과 밀접한 관련이 있다. 이에 본고에서는 메타인지와 관련된 여러 연구결과들의 통합을 통해 '메타인지능력과 수학적 사고력과의 상관관계, 메타인지 전략을 활용한 교수 학습 방법 및 그 효과, 메타인지 능력 향상을 통한 수학적 사고력 신장 방안'을 고찰하고자 하였다.

  • PDF

딥러닝을 활용한 도시가스배관의 전기방식(Cathodic Protection) 정류기 제어에 관한 연구 (A Study on Cathodic Protection Rectifier Control of City Gas Pipes using Deep Learning)

  • 이형민;임근택;조규선
    • 한국가스학회지
    • /
    • 제27권2호
    • /
    • pp.49-56
    • /
    • 2023
  • 4차 산업혁명으로 인공지능(AI, Artificial Intelligence) 관련 기술이 고도로 성장함에 따라 여러 분야에서 AI를 접목하는 사례가 증가하고 있다. 주요 원인은 정보통신기술이 발달됨에 따라 기하급수적으로 증가하는 데이터를 사람이 직접 처리·분석하는데 현실적인 한계가 있고, 새로운 기술을 적용하여 휴먼 에러에 대한 리스크도 감소시킬 수 있기 때문이다. 이번 연구에서는 '원격 전위 측정용터미널(T/B, Test Box)'로부터 수신된 데이터와 해당시점의 '원격 정류기' 출력을 수집 후, AI가 학습하도록 하였다. AI의 학습 데이터는 최초 수집된 데이터의 회기분석을 통한 데이터 전처리로 확보하였고, 학습모델은 심층 강화학습(DRL, Deep Reinforce-ment Learning) 알고리즘 중(中) Value기반의 Q-Learning모델이 적용하였다. 데이터 학습이 완료된 AI는 실제 도시가스 공급지역에 투입하여, 수신된 원격T/B 데이터를 기반으로 AI가 적절하게 대응하는지 검증하고, 이를 통해 향후 AI가 전기방식 관리에 적합한 수단으로 활용될 수 있는지 검증하고자 한다.

매개변수로 표현되는 도형의 시각화 방안 (The Visualization of figures represented by parameters)

  • 김향숙
    • 한국수학교육학회지시리즈A:수학교육
    • /
    • 제40권2호
    • /
    • pp.317-333
    • /
    • 2001
  • The equations of figures given by rectangular coordinates are used to look into the properties of them, which are very restricted in examining them in the school mathematics. Therefore, it is quite natural to consider the figures in terms of parameters without restriction to coordinates and also, it is possible for the students to analyze them. Thus, the visualization of figures is important for students in mathematics education. In particular, the teaching-learning methods using computers make loose the difficulties of geometry education, and from the viewpoint that various abstract figures can be visualized and that can be obtained by means of this visualization the learning of figures can be accomplished through the direct experience or control. This study is intended to present concretely the aim and its utility to visualize figures represented as parameters with Mathematics. In this paper, we introduce a new teaching-learning method of figures represented by parameters using Mathematica so that the learners establish themselves their knowledge obtained through their search, investigation, supposition and they accomplish the positive transition to advanced learning. So the leasers extend their ability of sensuous intuition to their ability of logical reasoning through their logical intuition. Consequently they can develop the ability of thinking mathematically, so many natural phenomena and physical ones.

  • PDF

신경회로망을 이용한 직접 자기동조제어기의 설계 (Design of a Direct Self-tuning Controller Using Neural Network)

  • 조원철;이인수
    • 전자공학회논문지SC
    • /
    • 제40권4호
    • /
    • pp.264-274
    • /
    • 2003
  • 본 논문에서는 잡음과 시간지연이 존재하며 시스템 파라미터가 변하는 비선형 비최소위상 시스템에 적응하는 신경회로망이 결합된 PID구조를 갖는 일반화 최소분산 자기동조제어기를 제안한다. PID구조를 갖는 자기동조는 PID제어기처럼 구조가 간단하고 계통을 정밀하게 제어하는 자기동조 제어기의 특성을 그대로 유지할 수 있다. 일반화 최소분산 자기동조 제어기 파라미터는 비선형 시스템을 선형시스템으로 간주하고 순환최소자승법으로 추정하며 설계계수의 값은 확률근사법인 Robbins-Monro 알고리듬을 이용하여 자동조정하였다. 역전파 학습 알고리듬을 사용하는 신경회로망 제어기는 비선형 부분의 제어를 보상하기 위해 필터된 기준입력과 필터된 플랜트 출력이 같도록 제어값을 출력한다. 컴퓨터 시뮬레이션을 통해 제안한 방법이 시스템의 파라미터가 변하는 비최소위상 시스템에 잘 적응함을 보였다.

대학생의 가정폭력 경험이 데이팅 폭력 가해에 미치는 영향 (The Effects of Family Violence on Perpetration of Dating Violence among College Students)

  • 정혜정
    • 대한가정학회지
    • /
    • 제41권3호
    • /
    • pp.73-91
    • /
    • 2003
  • This research tested the path model which examined the direct and indirect effects of family violence experience on perpetration of dating violence among college students. Two family violence variables such as witnessing parents' marital violence and being abused by parent were the exogeneous variables in the path model, while the mediated variables were consisted of (1) the social-learning-theory-derived variables such as acceptance of violence, positive outcome expectations of using violence, and aggressive conflict-coping behavior, and (2) control-theory-derived variables such as attachment, belief, and commitment. Data were from self-administered questionnaires completed by 332 male and 469 female students selected by stratified quota sampling method. The path analysis was done for males and females separately, since females reported significantly higher degree of dating violence than males. Results of the path analysis showed that first, for both males and females, being abused by parents directly and indirectly influenced dating violence, while witnessing parents' marital violence did not have effect on dating violence either directly or indirectly. Second, for male students, acceptance of violence and conflict coping behavior found to be the mediated variables in the effect of being abused by parents on dating violence. Third, for females, a control-theory-derived variable of belief as well as all three social learning theory-derived variables mediated the influence of being abused by parents on dating violence.

An Adaptive Fuzzy Current Controller with Neural Network For Field-Oriented Controller Induction Machine

  • Lee, Kyu-Chan;Lee, Hahk-Sung;Cho, Kyu-Bock;Kim, Sung-Woo
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1993년도 하계학술대회 논문집 A
    • /
    • pp.227-230
    • /
    • 1993
  • Recently, the development of novel control methodology enables us to improve the performance of AC-machine drives by using pulse width modulation (PWM) technique. Usually, the dynamic characteristic of induction motor (IM) has been represented by the 5-th order nonlinear differential equation. This dynamics, however, can be reduced to 3-rd order dynamics by applying direct control of IM input current. This methodology concludes that it is much easier to control IM by means of the field-oriented methods employing the current controller. Therefore a precise current control is crucial to achieve a high control performance both in dynamic and steady state operations. This paper presents an adaptive fuzzy current controller with artificial neural network (ANN) for field-oriented controlled IM. This new control structure is able to adaptively minimize a current ripple while maintaining constant switching frequency. Especially the proposed controller employs neuro-computing philosophy as well as adaptive learning pattern recognizing principles with respect to variations of the system parameters. The proposed approach is applied to the IM drive system, and its performance is tested through various simulations. Simulation results show that the proposed system, compared among several known classical methods, has a superb performance.

  • PDF

낮은 자기통제력의 스마트폰중독을 통한 사이버범죄 영향의 매개과정 모형구성과 검증 (Testing a Model for the Effect of Low Self-Control on Cybercrime Mediating by Smartphone Addiction and Its Mediating Process)

  • 이성식;류수민;임수경
    • 한국콘텐츠학회논문지
    • /
    • 제22권9호
    • /
    • pp.401-411
    • /
    • 2022
  • 이 연구는 낮은 자기통제력이 스마트폰 이용상의 사이버범죄에 미치는 영향에서 그 매개과정이 어떠한지의 연구모형을 구성함에 있어 낮은 자기통제력이 스마트폰중독에 영향을 주고 아울러 스마트폰중독이 사회학습과정과 범죄기회의 증가를 가져와 사이버범죄에 영향을 미친다는 연구모형을 구성하고 검증했다. 서울시 대학생 대상의 조사자료의 분석결과 낮은 자기통제력은 스마트폰중독에 유의미한 영향력을 가졌다. 그리고 스마트 폰사용에 중독될수록 불법친구와 접촉할 가능성이 높았고, 불법태도를 학습하며, 또한 불법기회에 노출되어 사이버범죄 가능성이 높은 것으로 나타났다. 또한 낮은 자기통제력은 스마트폰중독의 매개없이도 직접적으로 학습 및 기회요인에 유의미한 영향력을 가져 불법친구와 불법태도에, 그리고 불법기회에 유의미한 영향력을 가졌고 최종 매개변인으로 사회학습 및 기회요인이 사이버범죄에 크게 영향을 미쳤다. 이러한 결과에서 처럼 낮은 자기통제력은 스마트폰중독을 통해 그리고 학습 및 기회요인을 매개로 사이버범죄에 영향을 미치는 것을 제시했다.

균형있는 환경 교육의 목표 달성을 위한 고등학교 환경 교재의 개발 (Development of an Instructional Material for High School Environmental Education to Achiece Balanced Objectives)

  • 박진희;장남기
    • 한국과학교육학회지
    • /
    • 제15권1호
    • /
    • pp.39-53
    • /
    • 1995
  • The purpose of this study was development of 'Environmental Science' of high school appropriate to Sixth Natinal Education Curriculum. In view that ultimate aim of environmental education is forming responsible environmental behaviors and the goals of values and behaviors are as important as knowledges and skills, A new environmental text of high school level was developed and it was based on analysis of seven texts and environmental education in Fifth Korean Curriculum. This text have seven units, 1.Habitates : What're the Meanings?, 2.Nuclear Energy: Can't be Avoid?, 3.Acid Rain : What're the Messages", 4.Ethanol : Is this Future Fuel?, 5.Wastes : A New War!, 6.What're the National and Global Environmental Issues? and 7.Our Water: Can Drink, Really? This text was stressed equally in goals of four environmental education and avoided from the array of knowledges. Therefore included various teaching strategies and independent actions of students. 'Open-ended value learning' and 'free behavior learning' in text were special learning parts for aquisition of values and formation of behaviors. To verify the effects of new developed environmental text, the direct learning was carried out by 286 students in total. Post test scores of experimental groups per each units were significantly higher than those of control groups about four goals, respectively. The Results of questionnaires by 50 teachers from five different schools were as follows. For validity of selecting contents for units, 74% of respondents replied positively. For classification and presentation of four goal-groups, 90% replied positively in validity and 82%, in utility. For validity of various teaching strategies, 88% and for the degree of including student-centered independent actions, 86% replied positively. For importances and expected effects of 'open-ended value learning' and 'free behavior learning', showed positive responses respectively, 88%, 92%. Therefore this text is effective to acheive four goals of environmental education equally.

  • PDF