• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.123-128
• /
• 1998

This paper proposes design of LFT-based fuzzy controllers for model-following, which are better than the previous input-output linearization controllers, which are not able to follow the model system states and which do not guarantee the stability of all states. The method proposed in this paper provides a LFT-based Takagi-Sugeno(T-S) fuzzy controller with guaranteed stability and model-following via the following steps: First, using LFT(Linear Fractional Transformation) and T-S fuzzy model, controllers, are obtained. Next, error dynamics are obtained for model-following, and errors go to 0(zero). Finally, a T-s fuzzy controller that can stabilizxe the system with the requirement on the control input satisfied is obtained by solving the LMIs with the MATLAB LMI Control Toolbox and a model-following controller is obtained. Simulations are performed for the LFT-based T-S fuzzy controller designed by the proposed method, which show better performance than the results of input-out ut linearization controller.

• Journal of applied mathematics & informatics
• /
• 제18권1_2호
• /
• pp.649-656
• /
• 2005

In this paper we consider a fuzzy least absolute deviation method in order to construct fuzzy linear regression model with fuzzy input and fuzzy output. We also consider two numerical examples to evaluate an effectiveness of the fuzzy least absolute deviation method and the fuzzy least squares method.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.543-548
• /
• 1998

An image of a set that produces a multiset from an ordinary set and its extension to fuzzy multisets is considered. For each input element, its image is added to the output regardless whether or not there already exists the same image in the output. theoretical properties such as commutativity of the image with $\alpha$-cut or multiset addition are proved. Generalization to the image by multivariable functions is moreover defined.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.356-361
• /
• 1990

This paper presents a new self organizing fuzzy linguistic control (SOFLC) strategy for application to an arc welding process control. The proposed SOFLC is based on on-line modification of the control rules according to the extent of deviation of the one step ahead predictive output of the process from the desired output. The Predictive output of the process is estimated by a fuzzy predictor which is updated from the input and output data of the process. The rule base of the fuzzy subsets describing the control rules is modified by the improving mechanism based on the hill climbing approach. Simulation results show that this proposed SOFLC improves the response of the process in presence of the variation of the process dynamic characteristics.

• 대한의용생체공학회:의공학회지
• /
• 제12권3호
• /
• pp.203-208
• /
• 1991

Balancing left/right cardiac output is essential for the automatic control of total artificial hearts(TAH). A fuzzy logic-based control method is presented. We use left atrial pressure( LAP) ann right a'rial pressure( RAP ) as indicators for left/right balancing. The fuzzy controller has four input variables which are measured LAP and RAP and their gradients. Desired variations in left cardiac output(LCO) and right cardiac output(RCO) are cal- culated to keep LAP and RAP within the Physiological limlts. Computer simulations were performed to adjust fuzzy membership functions for variables and verify this control method. Results from simulations showed that LAP and RAP returned to the physiological limits while AoP and PAP stayed within the physiological limits.

• Journal of applied mathematics & informatics
• /
• 제18권1_2호
• /
• pp.591-601
• /
• 2005

The results of fuzzy linear regression are very sensitive to irregular data. When this points exist in a set of data, a fuzzy linear regression model can be incorrectly interpreted. The purpose of this paper is to detect irregular data and to propose robust fuzzy linear regression based on M-estimators with triangular fuzzy regression coefficients for crisp input-output data. Numerical example shows that irregular data can be detected by using the residuals based on M-estimators, and the proposed robust fuzzy linear regression is very resistant to this points.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 V
• /
• pp.2807-2810
• /
• 2003

In this paper, we propose a fuzzy control method for improving the control performance by automatically tuning the scaling factor. The proposed method is that automatically tune the input scaling factor and the output scaling factor of fuzzy logic system through neural network. Used neural network is ADALINE (ADAptive Linear NEron) neural network with delayed input. ADALINE neural network has simple construct, superior learning capacity and small computation time. In order to verify the effectiveness of the proposed control method, we performed simulation. The results showed that the proposed control method improves considerably on the environment of the disturbance.

• Communications for Statistical Applications and Methods
• /
• 제17권2호
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• 한국지능시스템학회논문지
• /
• 제25권1호
• /
• pp.57-62
• /
• 2015

본 논문에서는 전기설비들의 신속하고 효율적인 진단을 위해 차 영상을 통한 퍼지 추론 기반 열화 진단 시스템을 설계한다. 전기 기기의 열화 진단이 시작 되면 처음 정상 상태의 온도와 비교하여 이상 영역을 검출한다. 검출된 영역은 퍼지 추론 알고리즘을 사용하여 열화를 진단한다. 퍼지 추론 알고리즘에서, 퍼지 규칙은 If-then형식으로 정의되고, look-up 테이블로 규칙을 표현한다. 온도와 온도의 변화량을 입력 변수로 사용한다. 입력변수의 퍼지수를 표현하기 위해 삼각형 멤버쉽 함수를 사용하였으며, 출력변수에는 singleton 멤버쉽 함수를 사용하였다. 최종 출력은 퍼지 추론 방법의 무게 중심법을 사용하여 계산한다. 전기 설비로부터 취득한 실험 데이터는 제안된 시스템의 성능을 평가하기 위하 사용한다.

• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.777-784
• /
• 2006

본 논문에서는 부분최소법 (PLS: Partial least square)과 c-퍼지 모델트리를 적용하여 클로로필-a 농도의 예측 모델을 제안한다. 제안된 방법은 모든 입력속성을 고려하여 퍼지 클러스터에 의해 계산된 중심벡터를 설정한 후, 각각의 중심벡터들과 입력속성간의 소속도를 이용하여 내부 노드를 형성하고, 형성된 내부노드에서 PLS를 적용하여 지역모델(Local model)을 구축한다. 노드의 분리기준으로서 부모노드(patent node)에서 구축된 모델에서 계산된 에러값이 자식노드(child node)에서 계산된 에러값보다 클 경우에 분기가 이루어진다. 최종 단계에서는 임의의 입력데이터와 잎노드에서 계산된 클러스터 중심값과 비교하여 소속도가 높은 클러스터에 속한 지역모델을 선택하여 출력값을 예측한다. 제안된 방법의 우수성을 보이기 위해 수질 데이터를 대상으로 실험한 결과 기존의 모델트리 방식에 비하여 향상된 성능을 보임을 알 수 있었다.