• Title/Summary/Keyword: radial basis function networks

Search Result 183, Processing Time 0.025 seconds

Hydrological Forecasting Based on Hybrid Neural Networks in a Small Watershed (중소하천유역에서 Hybrid Neural Networks에 의한 수문학적 예측)

  • Kim, Seong-Won;Lee, Sun-Tak;Jo, Jeong-Sik
    • Journal of Korea Water Resources Association
    • /
    • v.34 no.4
    • /
    • pp.303-316
    • /
    • 2001
  • In this study, Radial Basis Function(RBF) Neural Networks Model, a kind of Hybrid Neural Networks was applied to hydrological forecasting in a small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of unsupervised and supervised training patterns. And Gaussian Kernel Function(GKF) was used among many kinds of Radial Basis Functions(RBFs). K-Means clustering algorithm was applied to optimize centers and widths which ate the parameters of GKF. The parameters of RBF Neural Networks Model such as centers, widths weights and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin which is one of the IHP Representative basins in South Korea. 10 rainfall events were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman Neural Networks(ENN) Model. ENN Model is composed of One Step Secant BackPropagation(OSSBP) and Resilient BackPropagation(RBP) algorithms. RBF Neural Networks shows better results than ENN Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model.

  • PDF

Design of Partial Discharge Pattern Classifier of Softmax Neural Networks Based on K-means Clustering : Comparative Studies and Analysis of Classifier Architecture (K-means 클러스터링 기반 소프트맥스 신경회로망 부분방전 패턴분류의 설계 : 분류기 구조의 비교연구 및 해석)

  • Jeong, Byeong-Jin;Oh, Sung-Kwun
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.67 no.1
    • /
    • pp.114-123
    • /
    • 2018
  • This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

Design of RBFNN-Based Pattern Classifier for the Classification of Precipitation/Non-Precipitation Cases (강수/비강수 사례 분류를 위한 RBFNN 기반 패턴분류기 설계)

  • Choi, Woo-Yong;Oh, Sung-Kwun;Kim, Hyun-Ki
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.24 no.6
    • /
    • pp.586-591
    • /
    • 2014
  • In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.

Uncertainty Observer using the Radial Basis Function Networks for Induction Motor Control

  • Huh, Sung-Hoe;Lee, Kyo-Beum;Ick Choy;Park, Gwi-Tae;Yoo, Ji-Yoon
    • Journal of Power Electronics
    • /
    • v.4 no.1
    • /
    • pp.1-11
    • /
    • 2004
  • A stable adaptive sensorless speed controller for three-level inverter fed induction motor direct torque control (DTC) system using the radial-basis function network (RBFN) is presented in this paper. Torque ripple in the DTC system for high power induction motor could be drastically reduced with the foregoing researches of switching voltage selection and torque ripple reduction algorithms. However, speed control performance is still influenced by the inherent uncertainty of the system such as parametric uncertainty, external load disturbances and unmodeled dynamics, and its exact mathematical model is much difficult to be obtained due to their strong nonlinearity. In this paper, the inherent uncertainty is approximated on-line by the RBFN, and an additional robust control term is introduced to compensate for the reconstruction error of the RBFN instead of the rich number of rules and additional updated parameters. Control law for stabilizing the system and adaptive laws for updating both of weights in the RBFN and a bounding constant are established so that the whole closed-loop system is stable in the sense of Lyapunov, and the stability proof of the whole control system is presented. Computer simulations as well as experimental results are presented to show the validity and effectiveness of the proposed system.

Design of Real-time Face Recognition Systems Based on Data-Preprocessing and Neuro-Fuzzy Networks for the Improvement of Recognition Rate (인식률 향상을 위한 데이터 전처리와 Neuro-Fuzzy 네트워크 기반의 실시간 얼굴 인식 시스템 설계)

  • Yoo, Sung-Hoon;Oh, Sung-Kwun;Kim, Hyun-Ki
    • Proceedings of the KIEE Conference
    • /
    • 2011.07a
    • /
    • pp.1952-1953
    • /
    • 2011
  • 본 논문에서는 다항식 기반 Radial Basis Function(RBF)신경회로망(Polynomial based Radial Basis function Neural Network)을 설계하고 이를 n-클래스 패턴 분류 문제에 적용한다. 제안된 다항식기반 RBF 신경회로망은 입력층, 은닉층, 출력층으로 이루어진다. 입력층은 입력 벡터의 값들을 은닉층으로 전달하는 기능을 수행하고 은닉층과 출력층사이의 연결가중치는 상수, 선형식 또는 이차식으로 이루어지며 경사 하강법에 의해 학습된다. Networks의 최종 출력은 연결가중치와 은닉층 출력의 곱에 의해 퍼지추론의 결과로서 얻어진다. 패턴분류기의 최적화는 PSO(Particle Swarm Optimization)알고리즘을 통해 이루어진다. 그리고 제안된 패턴분류기는 실제 얼굴인식 시스템으로 응용하여 직접 CCD 카메라로부터 입력받은 데이터를 영상 보정, 얼굴 검출, 특징 추출 등과 같은 처리 과정을 포함하여 서로 다른 등록인물의 n-클래스 분류 문제에 적용 및 평가되어 분류기로써의 성능을 분석해본다.

  • PDF

Prediction of Blank Thickness Variation in a Deep Drawing Process Using Deep Neural Network (심층 신경망 기반 딥 드로잉 공정 블랭크 두께 변화율 예측)

  • Park, K.T.;Park, J.W.;Kwak, M.J.;Kang, B.S.
    • Transactions of Materials Processing
    • /
    • v.29 no.2
    • /
    • pp.89-96
    • /
    • 2020
  • The finite element method has been widely applied in the sheet metal forming process. However, the finite element method is computationally expensive and time consuming. In order to tackle this problem, surrogate modeling methods have been proposed. An artificial neural network (ANN) is one such surrogate model and has been well studied over the past decades. However, when it comes to ANN with two or more layers, so called deep neural networks (DNN), there is distinct a lack of research. We chose to use DNNs our surrogate model to predict the behavior of sheet metal in the deep drawing process. Thickness variation is selected as an output of the DNN in order to evaluate workpiece feasibility. Input variables of the DNN are radius of die, die corner and blank holder force. Finite element analysis was conducted to obtain data for surrogate model construction and testing. Sampling points were determined by full factorial, latin hyper cube and monte carlo methods. We investigated the performance of the DNN according to its structure, number of nodes and number of layers, then it was compared with a radial basis function surrogate model using various sampling methods and numbers. The results show that our DNN could be used as an efficient surrogate model for the deep drawing process.

Decentralized Robust Adaptive Neural Network Control for Electrically Driven Robot Manipulators with Bounded Input Voltages (제한된 입력 전압을 갖는 전기 구동 로봇 매니퓰레이터에 대한 분산 강인 적응 신경망 제어)

  • Shin, Jin-Ho;Kim, Won-Ho
    • Transactions of the Korean Society for Noise and Vibration Engineering
    • /
    • v.25 no.11
    • /
    • pp.753-763
    • /
    • 2015
  • This paper proposes a decentralized robust adaptive neural network control scheme using multiple radial basis function neural networks for electrically driven robot manipulators with bounded input voltages in the presence of uncertainties. The proposed controller considers both robot link dynamics and actuator dynamics. Practically, the controller gain coefficients applied at each joint may be nonlinear time-varying and the input voltage at each joint is saturated. The proposed robot controller overcomes the various uncertainties and the input voltage saturation problem. The proposed controller does not require any robot and actuator parameters. The adaptation laws of the proposed controller are derived by using the Lyapunov stability analysis and the stability of the closed-loop control system is guaranteed. The validity and robustness of the proposed control scheme are verified through simulation results.

A Neuro-Fuzzy Model Optimization Using Rough Set Theory (러프 집합이론을 이용한 뉴로-퍼지 모델의 최적화)

  • 연정흠;서재용;김용택;조현찬;전홍태
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.10 no.3
    • /
    • pp.188-193
    • /
    • 2000
  • This paper presents an approach to obtain a reduced neuro-fuzzy model for a plant. The Neuro-Fuzzy Network are compose of the Radial Basis Function Networks with Gausis membership and learned by using temporal back propagation. The dependency in rough set theory is used to eliminate rules. Dependency between the condition membership value of each rule in a model and the output of the plant can allow us to see how much contribution the rule is to identify the plant. While the reduced model maintains the same performance as the original one, the selection algorithm can minimize its complexity and redundancy of the structure.

  • PDF

Neural network based modeling of PL intensity in PLD-grown ZnO Thin Films (펄스 레이저 증착법으로 성장된 ZnO 박막의 PL 특성에 대한 신경망 모델링)

  • Ko, Young-Don;Kang, Hong-Seong;Jeong, Min-Chang;Lee, Sang-Yeol;Myoung, Jae-Min;Yun, Ii-Gu
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 2003.07a
    • /
    • pp.252-255
    • /
    • 2003
  • The pulsed laser deposition process modeling is investigated using neural networks based on radial basis function networks and multi-layer perceptron. Two input factors are examined with respect to the PL intensity. In order to minimize the joint confidence region of fabrication process with varying the conditions, D-optimal experimental design technique is performed and photoluminescence intensity is characterized by neural networks. The statistical results were then used to verify the fitness of the nonlinear process model. Based on the results, this modeling methodology can be optimized process conditions for pulsed laser deposition process.

  • PDF

Design of an Adaptive Control System using Neural Network (신경 회로망을 이용한 적응 제어 시스템의 설계)

  • Jang, Tae-In;Rhee, Hyung-Chan;Yang, Hai-Won
    • Proceedings of the KIEE Conference
    • /
    • 1993.07a
    • /
    • pp.231-234
    • /
    • 1993
  • This paper deals with the design of an adaptive controller using neural network. We present RBFMLP Neural Network which consists of serial-connected two networks - Radial Basis Function Network and Multi Layer Perceptron, and then design a controller based on proposed networks with the adaptive control system structure, The plant and parameters of the controller are identified by the neural networks. We use the dynamic backpropagation algorithm for the learning of networks. Simulations represent the superiorities of the proposed network and the controller.

  • PDF