• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 추계학술대회 학술발표 논문집 제16권 제2호
• /
• pp.19-22
• /
• 2006

Type-2 fuzzy 이론은 기존의 퍼지 이론보다 패턴의 불확실성에 대한 제어를 더 향상시킬 수 있다. 반면에 계산 량이 커지는 문제점 때문에 본 논문에서는 type-2 fuzzy set 대신에 secondary membership이 interval의 형태를 갖는 interval type-2 fuzzy set을 기존의 radial basis function(RBF) neural network에 적용시킨 interval type-2 fuzzy RBF neural network를 제안한다. 제안한 알고리즘은 interval type-2 fuzzy membership function에 의하여 패턴들의 불확실성을 좀 더 잘 제어하여 기존의 RBF neural network의 성능을 향상시킬 수 있다. 본 논문에서는 제안한 알고리즘의 타당성을 보이기 위하여 여러 데이터 집합에 대한 분류 결과를 보인다.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권2호
• /
• pp.195-203
• /
• 2016

In order to overcome the influence of system stability and accuracy caused by uncertainty, estimation errors and external disturbances in Eight-Rotor MAV, L2 gain control method was proposed based on interval type II fuzzy neural network identification here. In this control strategy, interval type II fuzzy neural network is used to estimate the uncertainty and non-linearity factor of the dynamic system, the adaptive variable structure controller is applied to compensate the estimation errors of interval type II fuzzy neural network, and at last, L2 gain control method is employed to suppress the effect produced by external disturbance on system, which is expected to possess robustness for the uncertainty and non-linearity. Finally, the validity of the L2 gain control method based on interval type II fuzzy neural network identifier applied to the Eight-Rotor MAV attitude system has been verified by three prototy experiments.

• 전기학회논문지
• /
• 제62권5호
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.

• 대한전자공학회논문지TE
• /
• 제39권4호
• /
• pp.363-369
• /
• 2002

본 논문은 적응성 뉴로-퍼지 인터페이스 시스템(Adaptive Neuro-Fuzzy Inference System : ANFIS)과 웨이브렛 변환 다중해상도 분해(multi-resolution Analysis : MRA)을 기반으로 한 웨이브렛 신경망을 가지고 임의의 비선형 함수 학습 근사화를 개선하는 것이다. ANFIS 구조는 벨형 퍼지 소속 함수로 구성이 되었으며, 웨이브렛 신경망은 전파 알고리즘과 역전파 신경망 알고리즘으로 구성되었다. 이 웨이브렛 구성은 단일 크기이고, ANFIS 기반 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 1차원과 2차원 함수에서 웨이브렛 전달 파라미터 학습과 ANFIS의 벨형 소속 함수를 이용한 ANFIS 모델 기반 웨이브렛 신경망의 웨이브렛 기저 수 감소와 수렴 속도 성능이 기존의 알고리즘 보다 개선되었음을 확인하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제14권2호
• /
• pp.172-182
• /
• 2013

This paper focuses on the modeling and intelligent control of the new Eight-Rotor MAV, which is used to solve the problem of the low coefficient proportion between lift and gravity for the Quadrotor MAV. The Eight-Rotor MAV is a nonlinear plant, so that it is difficult to obtain stable control, due to uncertainties. The purpose of this paper is to propose a robust, stable attitude control strategy for the Eight-Rotor MAV, to accommodate system uncertainties, variations, and external disturbances. First, an interval type-II fuzzy neural network is employed to approximate the nonlinearity function and uncertainty functions in the dynamic model of the Eight-Rotor MAV. Then, the parameters of the interval type-II fuzzy neural network and gain of sliding mode control can be tuned on-line by adaptive laws based on the Lyapunov synthesis approach, and the Lyapunov stability theorem has been used to testify the asymptotic stability of the closed-loop system. The validity of the proposed control method has been verified in the Eight-Rotor MAV through real-time experiments. The experimental results show that the performance of the interval type-II fuzzy neural network based adaptive sliding mode controller could guarantee the Eight-Rotor MAV control system good performances under uncertainties, variations, and external disturbances. This controller is significantly improved, compared with the conventional adaptive sliding mode controller, and the type-I fuzzy neural network based sliding mode controller.

• 한국지능시스템학회논문지
• /
• 제12권5호
• /
• pp.397-404
• /
• 2002

본 논문에서는 퍼지와 웨이브렛 변환의 다해상도 분해(MRA)를 가진 퍼지 개념을 이용한 웨이브렛 신경망을 제안하고, 또한 이 시스템을 이용하여 임의의 비선형 함수 학습 근사화를 개선하고자 한다. 여기에서 퍼지 개념은 벨(bell)형 퍼지 소속함수를 사용하였다. 그리고 웨이브렛의 구성은 단일 크기를 가지고 있으며, 퍼지 개념을 이용한 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 웨이브렛 변환의 다해상도 분해, 벨형 퍼지 소속 함수 그리고 학습을 위한 역전파 알고리즘을 이용한 이 구조는 기존의 알고리즘보다 근사화 성능이 개선됨을 모의 실험을 통하여 1차원, 2차원 함수에서 확인하였다.

• Journal of Power Electronics
• /
• 제13권1호
• /
• pp.139-160
• /
• 2013

In this paper, an intelligent robust control system (IRCS) for precision tracking control of permanent-magnet synchronous motor (PMSM) servo drives is proposed. The IRCS comprises a recurrent wavelet-based interval type-2 fuzzy-neural-network controller (RWIT2FNNC), an RWIT2FNN estimator (RWIT2FNNE) and a compensated controller. The RWIT2FNNC combines the merits of a self-constructing interval type-2 fuzzy logic system, a recurrent neural network and a wavelet neural network. Moreover, it performs the structure and parameter-learning concurrently. The RWIT2FNNC is used as the main tracking controller to mimic the ideal control law (ICL) while the RWIT2FNNE is developed to approximate an unknown dynamic function including the lumped parameter uncertainty. Furthermore, the compensated controller is designed to achieve $L_2$ tracking performance with a desired attenuation level and to deal with uncertainties including approximation errors, optimal parameter vectors and higher order terms in the Taylor series. Moreover, the adaptive learning algorithms for the compensated controller and the RWIT2FNNE are derived by using the Lyapunov stability theorem to train the parameters of the RWIT2FNNE online. A computer simulation and an experimental system are developed to validate the effectiveness of the proposed IRCS. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the IRCS grants robust performance and precise response regardless of load disturbances and PMSM parameters uncertainties.

• 한국인터넷방송통신학회논문지
• /
• 제17권1호
• /
• pp.173-181
• /
• 2017

산업이 발달함에 따라서 빅데이터가 무수히 생산되고 있으며 이에 따라서 데이터에 내재된 불확실성도 증가하고 있다. 본 논문에서는 데이터에 내재된 불확실성을 다루기 위해 interval type-2 퍼지 클러스터링 방법을 제안하고 이를 이용하여 퍼지뉴럴네트워크를 설계하고 최적화한다. 제안한 클러스터링 방법을 이용하여 퍼지 규칙을 설계하고 학습을 수행한다. 최적화하는 방법으로서 유전자 알고리즘을 이용하고 모델 파라미터들을 최적 탐색한다. 실험에서는 두 가지 패턴 분류를 시행하였으며 두 가지 실험 모두 우수한 패턴 인식 결과를 보여준다. 제안한 네트워크는 증가하는 불확실성을 다룰 수 있는 방법을 제공할 수 있을 것이다.

• 전기학회논문지
• /
• 제58권2호
• /
• pp.399-406
• /
• 2009

In this study, Polynomial Radial Basis Function Neural Network(pRBFNN) based on Fuzzy Inference System is designed and its parameters such as learning rate, momentum coefficient, and distributed weight (width of RBF) are optimized by means of Particle Swarm Optimization. The proposed model can be expressed as three functional module that consists of condition part, conclusion part, and inference part in the viewpoint of fuzzy rule formed in 'If-then'. In the condition part of pRBFNN as a fuzzy rule, input space is partitioned by defining kernel functions (RBFs). Here, the structure of kernel functions, namely, RBF is generated from HCM clustering algorithm. We use Gaussian type and Inverse multiquadratic type as a RBF. Besides these types of RBF, Conic RBF is also proposed and used as a kernel function. Also, in order to reflect the characteristic of dataset when partitioning input space, we consider the width of RBF defined by standard deviation of dataset. In the conclusion part, the connection weights of pRBFNN are represented as a polynomial which is the extended structure of the general RBF neural network with constant as a connection weights. Finally, the output of model is decided by the fuzzy inference of the inference part of pRBFNN. In order to evaluate the proposed model, nonlinear function with 2 inputs, waster water dataset and gas furnace time series dataset are used and the results of pRBFNN are compared with some previous models. Approximation as well as generalization abilities are discussed with these results.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.822-828
• /
• 2018

AC-DC conversion is a necessary for the systems that require DC source. This conversion has been done via rectifiers based on controlled or uncontrolled semiconductor switches. Advances in the power electronics and microprocessor technologies allowed the use of Pulse Width Modulation (PWM) rectifiers. In this paper, dq-axis current and DC link voltage of three-phase PWM rectifier are controlled by using type-2 fuzzy neural network (T2FNN) controller. For this aim, a simulation model is built by MATLAB/Simulink software. The model is tested under three different operating conditions. The parameters of T2FNN is updated online by using back-propagation algorithm. The results obtained from both T2FNN and Proportional + Integral + Derivate (PID) controller are given for three operating conditions. The results show that three-phase PWM rectifier using T2FNN provides a superior performance under all operating conditions when compared with PID controller.