• Journal of Electrical Engineering and Technology
• /
• 제3권1호
• /
• pp.101-107
• /
• 2008

We introduce an optimization of fuzzy set-fuzzy systems based on IG (Information Granules). The proposed fuzzy model implements system structure and parameter identification by means of IG and GAs. The concept of information granulation was coped with to enhance the abilities of structural optimization of the fuzzy model. Granulation of information realized with C-Means clustering helps determine the initial parameters of the fuzzy model such as the initial apexes of the membership functions in the premise part and the initial values of polynomial functions in the consequence part of the fuzzy rules. The initial parameters are adjusted effectively with the help of the GAs and the standard least square method. To optimally identify the structure and the parameters of the fuzzy model we exploit GAs with successive tuning method to simultaneously search the structure and the parameters within one individual. We also consider the variant generation-based evolution to adjust the rate of identification of the structure and the parameters in successive tuning method. The proposed model is evaluated with the performance of the conventional fuzzy model.

• 한국지능시스템학회논문지
• /
• 제12권3호
• /
• pp.193-201
• /
• 2002

교통의 혼잡량이라든가 공기의 쾌적도등을 측정할 때는 상징적인 정보량을 이용한 퍼지 센서 알고리즘을 사용한다. 그런데 퍼지센서를 구현할 경우 몇 개의 상징적인 정보량을 퍼지 규칙으로서 종합하여 출력을 산출하는데 상징적인 정보량을 퍼지 규칙이라는 막연한 방법을 사용하므로서 정확하지 못한 결과를 산출 할 수 밖에 없다. 따라서 본 논문에서는 퍼지 규칙으로 퍼지센서를 구현하는 방법이 아닌 계층분석 방법이라는 분석적인 방법을 이용하여 퍼지센서를 구현하였고 이를 검증하기 위하여 퍼지 규칙방법의 퍼지센서와 계층분석방법의 퍼지센서를 교통량 제어에 적용하여 많은 통과차량수의 검증을 통하여 비교하여 보았다

• 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.

• 한국정보통신학회논문지
• /
• 제13권3호
• /
• pp.505-513
• /
• 2009

Z. cao는 Relation matrix를 사용한 정밀한 추론이 가능한 NFRM(New fuzzy reasoning method)을 제안하였다. 이는 추론의 규칙 수가 적음에도 불구하고 Mamdani의 퍼지 추론방식에 비하여 좋은 성능을 보였다. 그러나 대부분의 퍼지스템의 경우, MIMO 시스템에 적용 시 퍼지 추론규칙을 도출해 내기 힘들고 많은 규칙의 수가 요구되는 단점을 갖는다. 그러므로 본 연구자에 의하여 과거에 Z. Cao's의 퍼지 추론방법을 MIMO 시스템으로 확장된 MIMO 퍼지추론 방식이 제안되었다. 그러나 정밀한 추론을 위하여 relation matrix는 휴리 스틱 (heuristic)한 방법이나 시행착오법을 사용하여 구하였고, 이는 많은 시간과 노력이 필요하다. 본 연구에서는 이러한 relation matrix를 구하기 위하여 시행 착오법에 의해 소요되는 많은 시간과 노력을 줄이고, 더욱 정밀한 추론 성능의 개선을 위하여 경사감소학습법을 사용한 학습기 능을 갖는 MIMO 퍼지추론 방식을 제안하고자 한다. 모의실험은 2축 로봇의 역기구학 문제를 푸는데 적용하여 제안된 추론방식이 좋은 성능을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 추계학술대회 논문집 학회본부
• /
• pp.349-352
• /
• 1991

Fuzzy modelling is a useful method when the variation of plant dynamics is large. In the fuzzy modelling by parameter identification, a new method is proposed in the part of premise parameters identification and in expanding MISO system into MIMO system. Using the proposed method, a fuzzy model of the drum boiler of the thermal power plant can be derived. In addition, feedwater control of the drum by fuzzy controller using the fuzzy model, is simulated.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1181-1186
• /
• 1993

In the paper, a new design method of rule-based fuzzy modeling is proposed for model identification of nonlinear systems. The structure indentification is carried out, utilizing fuzzy c-means clustering. Fuzzy-neural networks composed back-propagation algorithm and linear fuzzy inference method, are used to identify parameters of the premise and consequence parts. To obtain optimal linguistic fuzzy implication rules, the learning rates and momentum coefficients are tuned automatically using a modified complex method.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.524-528
• /
• 1996

Quality information is known to have the characteristic of continuous distribution in many manufacturing processes. It is difficult to describe the process condition by classifying the distribution into discrete ranges which is based on the set concept. Fuzzy control chart has been developed for the control of linguistic data but it still utilizes the dichotomous notion of classical set theory. In this paper, the fuzzy sampling method is studied in order to manage the ambiguous data properly and incorporated for generating fuzzy control chart. The method is based on the fuzzy set concept and considered to be appropriate for the realization of a complete fuzzy control chart. The fuzzy control chart was compared with the conventional generalized p-chart in the sensitivity for quality distribution and robustiness against the noise. The fuzzy control chart with the fuzzy sampling method showed better characteristics.

• 전기학회논문지
• /
• 제67권12호
• /
• pp.1699-1704
• /
• 2018

In this paper, proposed a method to improve of control characteristics for power facility using the adaptive sizing of fuzzy inference method. In the use of the controller based the fuzzy logic, a basic mamdani fuzzy controller is applied. However, when the maximum value and the minimum value have to taken, the fuzzy controller can not take a normal value because of formalized grouping form. In this paper, we combine the conventional methods with single valued sets to compensate for the disadvantage caused by the mamdani method control. Simulation results show that the proposed method has better overshoot and steady state arrival time than the conventional control method.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.103-109
• /
• 2001

Soft sensor is an effective method to deal with the estimation of variables, which are difficult to measure because of the reasons of economy or technology. Fuzzy logic system can be used to develop the soft sensor model by infinite rules, but the fuzzy dividing of variable sets is a key problem to achieve an accurate fuzzy logic model, In this paper, we proposed a new method to develop soft sensor model based on fuzzy neural network. First, using a novel method to divide the variable fuzzy sets by the process input and output data. Second, developing the fuzzy logic model based on that fuzzy set dividing. After that, expressing the fuzzy system with a fuzzy neural network and getting the initial soft sensor model based FNN. Last, adjusting the relative parameters of soft sensor model by the BP learning method. The effectiveness of the method proposed and the preferable generalization ability of soft sensor model built are demonstrated by the simulation.

• 대한수학회논문집
• /
• 제31권1호
• /
• pp.185-198
• /
• 2016

Regression analysis is an analyzing method of regression model to explain the statistical relationship between explanatory variable and response variables. This paper propose a fuzzy regression analysis applying Theils method which is not sensitive to outliers. This method use medians of rate of increment based on randomly chosen pairs of each components of ${\alpha}$-level sets of fuzzy data in order to estimate the coefficients of fuzzy regression model. An example and two simulation results are given to show fuzzy Theils estimator is more robust than the fuzzy least squares estimator.