• 제목/요약/키워드: Neural Networks Theory

검색결과 166건 처리시간 0.022초

An Adaptive Autopilot for Course-keeping and Track-keeping Control of Ships using Adaptive Neural Network (Part I: Theoretical study)

  • NGUYEN Phung-Hung;JUNG Yun-Chul
    • 한국항해항만학회:학술대회논문집
    • /
    • 한국항해항만학회 2005년도 추계학술대회 논문집
    • /
    • pp.17-22
    • /
    • 2005
  • This paper presents a new adaptive autopilot for ships based on the Adaptive Neural Networks. The proposed adaptive autopilot is designed with some modifications and improvements from the previous studies on Adaptive Neural Networks by Adaptive Interaction (ANNAI) theory to perform course-keeping, turning and track-keeping control. A strategy for automatic selection c! the neural network controller parameters is introduced to improve the adaptation ability and the robustness of new ANNAI autopilot. In Part II of the paper, to show the effectiveness and feasibility of the proposed ANNAI autopilot, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances are presented.

  • PDF

An Adaptive Autopilot for Course-keeping and Track-keeping Control of Ships using Adaptive Neural Network (Part I: Theoretical Study)

  • Nguyen Phung-Hung;Jung Yun-Chul
    • 한국항해항만학회지
    • /
    • 제29권9호
    • /
    • pp.771-776
    • /
    • 2005
  • This paper presents a new adaptive autopilot for ships based on the Adaptive Neural Networks. The proposed adaptive autopilot is designed with some modifications and improvements from the previous studies on Adaptive Neural Networks by Adaptive Interaction (ANNAI) theory to perform course-keeping, turning and track-keeping control. A strategy for automatic selection of the neural network controller parameters is introduced to improve the adaptation ability and the robustness of new ANNAI autopilot. In Part II of the paper, to show the effectiveness and feasibility of the proposed ANNAI autopilot, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances will be presented.

PC 수직 접합부의 극한 전단 내력 예측에 대한 인공 신경 회로망의 적용 (Application of Artificial Neural Networks to Predict Ultimate Shear Capacity of PC Vertical Joints)

  • 김택완;이승창;이병해
    • 전산구조공학
    • /
    • 제9권2호
    • /
    • pp.93-101
    • /
    • 1996
  • 인공 신경회로망은 인간의 뇌를 전산 모델로 구현한 것으로 상호 연결된 많은 정보 처리 유니트들로 구성되어 있으며, 이를 기초로 논리적인 추론을 수행할 수 있다. 특히, 신경망은 비선형 변수를 많이 포함하고 있는 복잡한 문제 해결에서 더욱 효과적이다. 신경망의 이러한 기능으로 인해 구조분야에서는 비선형적인 각종 구조실험의 결과예측이나 구조계획 그리고 최적 설계에 응용되고 있는 추세이다. 본 논문에서는 인공 신경 회로망의 기본 이론을 설명하고, 현재까지 정립되고 있지 않은 대형 콘크리트 판넬간 수직 접합부의 최대 전단 내력 예측에 기존의 제안식과 인공 신경 회로망의 예측 결과를 비교하여 신경망의 적용가능성을 검토하고자 한다.

  • PDF

Prediction of contact lengths between an elastic layer and two elastic circular punches with neural networks

  • Ozsahin, Talat Sukru;Birinci, Ahmet;Cakiroglu, A. Osman
    • Structural Engineering and Mechanics
    • /
    • 제18권4호
    • /
    • pp.441-459
    • /
    • 2004
  • This paper explores the potential use of neural networks (NNs) in the field of contact mechanics. A neural network model is developed for predicting, with sufficient approximation, the contact lengths between the elastic layer and two elastic circular punches. A backpropagation neural network of three layers is employed. First contact problem is solved according to the theory of elasticity with integral transformation technique, and then the results are used to train the neural network. The effectiveness of different neural network configurations is investigated. Effect of parameters such as load factor, elastic punch radii and flexibilities that influence the contact lengths is also explored. The results of the theoretical solution and the outputs generated from the neural network are compared. Results indicate that NN predicted the contact length with high accuracy. It is also demonstrated that NN is an excellent method that can reduce time consumed.

자동작곡에서 조성과 반복구성을 위한 후처리 방법 및 다수 곡 학습을 위한 평균 신경망 방법 (Postprocessing for Tonality and Repeatability, and Average Neural Networks for Training Multiple Songs in Automatic Composition)

  • 김경환;정성훈
    • 한국지능시스템학회논문지
    • /
    • 제26권6호
    • /
    • pp.445-451
    • /
    • 2016
  • 본 논문에서는 기존의 인공신경망을 이용한 자동작곡에서 음악적으로 부족한 부분을 개선하기 위해 조성을 후처리하는 방법과 멜로디에 반복성을 주는 방법 그리고 다수의 곡을 학습하기 위한 평균 신경망 방법을 제안한다. 인공신경망을 이용하여 작곡된 곡의 멜로디는 인공신경망에 학습된 곡의 멜로디에 따라서 출력되는 것으로 음악적으로 특정한 조성에 맞는 곡이 출력되지 않으며 또한 반복적인 멜로디 구성이 나오기 어렵다. 본 논문에서는 이를 해결하기 위하여 인공신경망이 출력한 멜로디를 음악이론에 따라서 특정한 조성으로 후처리하는 방법과 마디구분을 반복적으로 구성하여 멜로디 진행에 반복을 주는 방법을 제안한다. 또한 기존 연구에서 사용한 다수의 곡을 학습하는 방법은 여러 가지 단점이 있었다. 이를 해결하기 위하여 다수의 곡을 학습하는 방법으로 각 곡을 학습한 인공신경망의 가중치를 평균하여 만든 평균 인공신경망을 사용하는 것을 제안한다. 제안한 방법을 적용하여 작곡한 결과 제안한 방법이 기존의 문제점을 해결하는 것을 확인할 수 있었다.

Formulation of the Neural Network for Implicit Constitutive Model (II) : Application to Inelastic Constitutive Equations

  • Lee, Joon-Seong;Lee, Eun-Chul;Furukawa, Tomonari
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제8권4호
    • /
    • pp.264-269
    • /
    • 2008
  • In this paper, two neural networks as a material model, which are based on the state-space method, have been proposed. One outputs the rates of inelastic strain and material internal variables whereas the outputs of the other are the next state of the inelastic strain and material internal variables. Both the neural networks were trained using input-output data generated from Chaboche's model and successfully converged. The former neural network could reproduce the original stress-strain curve. The neural network also demonstrated its ability of interpolation by generating untrained curve. It was also found that the neural network can extrapolate in close proximity to the training data.

신경 회로망의 원리와 이론적 배경 (Principles and Background of Neural Networks)

  • 이종호
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1992년도 하계학술대회 논문집 A
    • /
    • pp.37-42
    • /
    • 1992
  • 요즘엔 신경회로망에대한 소개나 전망등이 신문이나 잡지에도 종종 오르내리지만 불과 몇해전만해도 대학에서 신경회로망에 관한 세미나공고가 붙게되면 공학이나 컴퓨터를 전공하는 사람들조차도 이것은 의학, 또는 신경생리학에 관련된 세미나일것이라 여기는 일이 종종 있었다. 신경회로망의 개발에 대한 시도는 디지탈 컴퓨터와 거의 때를 같이 하지만 세계적으로는 80년대 후반 이래로 그 효용성이 부각되기 시작하였으며 수많은 과학자들이 오늘도 이 새로운 분야의 가능성에 심혈을 기울이고 있다. 그러면 이처럼 전문가 뿐만아니라 일반인들에게도 호기심을 불러일으키고 있는 신경망이란 무엇인가? 이 강좌에서는 그 특성과 구조와 동작원리에 대하여 살펴보기로 하자.

  • PDF

Fuzzy Relation-Based Fuzzy Neural-Networks Using a Hybrid Identification Algorithm

  • Park, Ho-Seung;Oh, Sung-Kwun
    • International Journal of Control, Automation, and Systems
    • /
    • 제1권3호
    • /
    • pp.289-300
    • /
    • 2003
  • In this paper, we introduce an identification method in Fuzzy Relation-based Fuzzy Neural Networks (FRFNN) through a hybrid identification algorithm. The proposed FRFNN modeling implement system structure and parameter identification in the efficient form of "If...., then... " statements, and exploit the theory of system optimization and fuzzy rules. The FRFNN modeling and identification environment realizes parameter identification through a synergistic usage of genetic optimization and complex search method. The hybrid identification algorithm is carried out by combining both genetic optimization and the improved complex method in order to guarantee both global optimization and local convergence. An aggregate objective function with a weighting factor is introduced to achieve a sound balance between approximation and generalization of the model. The proposed model is experimented with using two nonlinear data. The obtained experimental results reveal that the proposed networks exhibit high accuracy and generalization capabilities in comparison to other models.er models.

인버터형 에어컨 전원용 태양광시스템의 MPPT 동작 특성에 관한 연구 (The Study on the Operating Characteristic of MPPT for Photovoltaic System with Inverter Type Airconditionig System)

  • 유권종;차인수;임중열;김동휘
    • 태양에너지
    • /
    • 제18권3호
    • /
    • pp.129-135
    • /
    • 1998
  • A photovoltaic system is an infinite and clean energy system. A photovoltaic system consists of a solar cell array, a converter, a inverter and a control unit. It is necessary that the Maximum Power Point Tracker(MPPT) is applied to the photovoltaic system because the output power of solar cell array is varied with irradiation, temperature and external effects. In this paper, the neural networks theory, one of the control methods, is applied to track the maximum power point of the photovoltaic system. The MPPT using neural networks theory is proposed to improve existing energy converter efficiency. Also the theory is applied to operation of inverter type airconditionig system.

  • PDF

Wavelet Theory와 신경회로망을 이용한 전력 품질 외란의 검출 및 식별 (On the detection and Classification of Power Quality Disturbances using Wavelet Theory and Neural Networks)

  • 김봉수;김승조;남상원;김진오
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1994년도 추계학술대회 논문집 학회본부
    • /
    • pp.69-71
    • /
    • 1994
  • The objective of this paper is to present a systematic approach to detect and classify automatically Power Quality Disturbances by applying the recent advances in digital signal processing techniques including wavelet theory and neural networks. To demonstrate the validity of the derived result, computer simulation results are included.

  • PDF