폐수처리 시스템의 자동화를 위한 제어규칙 퍼지 모델링

안태천,황형수,오성권 圓光大學校 1995 論文集 Vol.29 No.2

규칙베이스 퍼지모델링의 설계방법을 복잡하고 비선형적인 시스템의 모델동정을 위하여 제안한다. 이 논문에서 제안된 3가지 종류의 규칙베이스 퍼지모델 방법은 간략추론, 선형추론, 변형된 선형추론 퍼지모델링 방법이다. 퍼지규칙의 전반부 구조와 파라미터를 동정하기 위하여 퍼지 클러스터링, 수정된 컴플렉스법이 사용되고, 최적 후반부 파라미터를 동정하기 위해 최소자승법이 사용된다. 가스로 공정의 시계열 데이타의 하수처리공정의 데이타가 제안된 규칙 베이스 퍼지 모델링을 성능평가 하기위해 사용된다. 제안된 모델링 방법이 다른 논문과 비교시 더 높은 정확도를 가진 퍼지모델을 생성함을 이용하여 보인다. A design of rule-based fuzzy modeling is presented for the model identification of complex and nonlinear systems. Three kinds of method for fuzzy modeling presented in this paper include simplified inference(type1), linear inference(type2), and modified linear inference(type3). The fuzzy c-means clustering and modified complex methods are used in order to identify the premise structure and parameter of fuzzy implication rules, respectively and the least square method is utilized for the identification of optimal consequence parameters. Time series data for gas furnace and sewage treatment processes are used to evaluate the performances of the proposed rule-based fuzzy modeling. Comparison shows that the proposed method can produce the fuzzy model with higher accuracy than previous other studies.

터어보-발전기 시스템의 능동적응 이중제어

안태천 圓光大學校 1989 論文集 Vol.23 No.2

본 연구에서는 이너베이션 접근법을 이용한 이중제어 알고리즘과 자기동조 제어를 위한 기존의 극점배치 방법을 결합시켜 안정한 능동적응 이중제어기를 설계하고, 터어보-발전기 시스템에 적응하여 특성을 조사하였다. 이 제어기의 적용도를 조사하기 위해, 조속기 동기기 및 전압조정기로 구성된 9차 쌍 입출력 화력용 터어보-발전기를 선택하여, 실제 시스템과 동일한 특성을 갖는 최적이산치 3차 단일 입·출력 시스템으로 분해하고, 자기동조 기법을 이용한 능동적응 이중제어 시스템을 구성하였다. 능동적응 이중 제어기로 구성된 터어보-발전기 시스템에 단위계단 증분 외란을 인가하고, 디지탈 컴퓨터에 의한 시뮬레이션으로 적응도를 검토한 능동적응 이중 제어기는 극점배치 자기동조 제어기에 비하여 제어손실과 과도상태에서 출력편차 등을 효율적으로 억제함을 입증하였다. This study presents the design method of the active adaptive dual controller that consists of a dual control algorithm and the pole place method, and the analysis of performance characteristics of the active adaptive dual control in relation to the turbo-generator system. The application of the active adaptive dual controller to the 9th order biinputbiouput thermal turbo-generator consisting of governor, synchronous machine and automatic voltage regulator was carried out by decoupling into the 3rd order optimal discrete SI-SO systems. Using a step incremental input as disturbance, computer simulation illustrates that the active adaptive dual controller sharply suppressed the control loss, the output deviation compared favorably with those of a pole placement self-tuning controller.

퍼지 GMDH 알고리즘과 폐수처리 공정 시스템에의 응용

안태천,노석범,황형수,오성권 圓光大學校 1996 論文集 Vol.31 No.2

본 논문에서는 GMDH(Group Method of Data Handling) 알고리즘을 이용하여 퍼지 모델의 구조와 파라미터를 설정하는 알고리즘을 제안하였다. 퍼지 함의 규칙의 전건부 구조와 파라미터를 동정하기 위해 GMDH 알고리즘과 퍼지 추론을 사용하였고 최적의 후건부 파라미터를 동정하기 위해 최소 자승법을 사용하였다. 제안된 모델링 방법의 성능을 평가하기 위해서 가스로 시계열 데이터와 하수처리 데이터를 사용하였다. 제안된 방법을 사용하면 다른 모델에 비해 우수한 성능을 가진 지능 모델을 얻을수 있다. The Proposed fuzzy modeling implements system structure and parameter identification using the GMDH(Group Method of Data Handling) Algorithm. In this method, We use the GMDH algorithm and fuzzy inference to identify the premise structure and parameter of fuzzy implication rules and least square method to identify optimum consequence parameter. Time seris data for gas furnace and wastewatertreatment data are used for purpose of evaluating the performance of the proposed fuzzy.

퍼지-뉴럴 네트워크에 의한 퍼지동정

안태천,황형수,오성권 圓光大學校 1994 論文集 Vol.28 No.2

본 논문에서는 복잡한 비선형 시스템을 모델링하기 위해 퍼지-뉴럴네트워크(FNNs)를 사용한 퍼지규칙의 최적 동정 방법이 제안된다. FNNs는 역전파 알고리즘과 Sugeno의 퍼지추론 방법의 결합으로 구성된다. 퍼지규칙의 구조동정은 기존의 동정에서 반복적인 퍼지분할을 피하기 위해 퍼지 c-means클로스터링을 이용해서 수행된다. FNNs는 퍼지규칙의 전·후반부 파라미터를 동정하기 위해 사용된다. 최적 퍼지규칙을 얻기 위해, FNNs는 학습율과 모멘텀 계수가 수정된 컴플렉스법을 이용하여 자동동조 된다. 가스로 공정의 시계열 데이타는 제안된 규칙베이스 퍼지 모델리의 성능을 평가하기 위해 사용된다. 제안된 모델링 방법이 다른 논문과 비교시 더 높은 정확도를 가진 퍼지모델을 생성함을 보인다. In this paper, an optimal identification method of fuzzy rules using fuzzy neural networks(FNNs) is proposed in order to model the nonlinear complex systems. FNNs are composed by combining back-propagation algorithms and Sugeno's linear fuzzy inference method. The structure identification of fuzzy implication rules is carried out utilizing fuzzy c-means clustering in order to avoid the iterative fuzzy partition in the conventional identification and FNNs are used to identify parameters of premise and comsequence part of fuzzy implication rules. To obtain the optimal fuzzy rules, the learning ratio and momentum coefficients of FNNs are tuned automatically utilizing the modified complex method. Time series data for gas furance are used to evaluate the performance of the proposed rule-based fuzzy modeling.

의사 직접 적응 제어기에 관한 연구

안태천 圓光大學校 1984 論文集 Vol.18 No.2

In this paper, quasi-direct adaptive controllers are studied which control discrete systems represented by linear vector difference equations whose parameters are unknown but constant. A recursive least square method wit a forgetting factor is used for plant parameter identifications. The Bezout identity which is inherent to indirect adaptive control schemes is not solved, and the recursive least square method is also used for controller parameter identifications. The proposed algorithm has a shorter computing time than for the indirect schemes. Convergence of real parameters is investigated by varying the forgetting factor which belongs to the parameter identification algorithm. It is shown that guasi-direct adaptive controllers with a forgetting factor are applicable to nonminimum phase systems. The controllers show that tracking and regulation are independently achieved in the limit with the bounded input and output for a range of initial plant parameter estimates. These approaches indicate that the constant trace identification algorithm yields the satisfactory results.

Hybrid Induction Motor Control Using a Genetically Optimized Pseudo-on-line Method

Tae-chon Ahn,이종석,장경원,J. F. Peters 전력전자학회 2004 JOURNAL OF POWER ELECTRONICS Vol.4 No.3

This paper introduces a hybrid induction motor control using a genetically optimized pseudo-on-line method. Optimization results from the use of a look-up table based on genetic algorithms to find the global optimum of an unconstrained optimization problem. The approach to induction motor control includes a pseudo-on-line procedure that optimally estimates parameters of a fuzzy PID (FPID) controller. The proposed hybrid genetic fuzzy PID (GFPID) controller is applied to speed control of a 3-phase induction motor and its computer simulation is carried out. Simulation results show that the proposed controller performs better than conventional FPID and PID controllers. The contribution of this paper is the introduction of a high performance hybrid form of induction motor control that makes on-line and real-time control of the drive system possible.

INTUITIONISTIC FUZZY (t, s)-CONGRUENCES

Tae Chon Ahn,Kul Hur,Seok Beom Roh 한국지능시스템학회 2006 한국지능시스템학회논문지 Vol.16 No.3

We introduce the notion of intuitionistic fuzzy(t, s)-congruences on a lattice and study some of its properties. Moreover, we obtain some properties of intuitionistic fuzzy congruences on the direct product of two lattices. Finally, we prove that the set of all intuitionistic fuzzy congruences on a lattice forms a distributive lattice.

Data Pattern Estimation with Movement of the Center of Gravity

Tae-Chon Ahn,Kyung-Won Jang,Dong-Du Shin,Hak-Soo Kang,Yang-Woong Yoon 한국지능시스템학회 2006 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.6 No.3

In the rule based modeling, data partitioning plays crucial role because partitioned sub data set implies particular information of the given data set or system. In this paper, we present an empirical study result of the data pattern estimation to find underlying data patterns of the given data. Presented method performs crisp type clustering with given n number of data samples by means of the sequential agglomerative hierarchical nested model (SAHN). In each sequence, the average value of the sum of all inter-distance between centroid and data point. In the sequel, compute the derivation of the weighted average distance to observe a pattern distribution. For the final step, after overall clustering process is completed, weighted average distance value is applied to estimate range of the number of clusters in given dataset. The proposed estimation method and its result are considered with the use of FCM demo data set in MATLAB fuzzy logic toolbox and Box and Jenkins's gas furnace data

Data Pattern Estimation with Movement of the Center of Gravity

Ahn Tae-Chon,Jang Kyung-Won,Shin Dong-Du,Kang Hak-Soo,Yoon Yang-Woong Korean Institute of Intelligent Systems 2006 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.6 No.3

In the rule based modeling, data partitioning plays crucial role be cause partitioned sub data set implies particular information of the given data set or system. In this paper, we present an empirical study result of the data pattern estimation to find underlying data patterns of the given data. Presented method performs crisp type clustering with given n number of data samples by means of the sequential agglomerative hierarchical nested model (SAHN). In each sequence, the average value of the sum of all inter-distance between centroid and data point. In the sequel, compute the derivation of the weighted average distance to observe a pattern distribution. For the final step, after overall clustering process is completed, weighted average distance value is applied to estimate range of the number of clusters in given dataset. The proposed estimation method and its result are considered with the use of FCM demo data set in MATLAB fuzzy logic toolbox and Box and Jenkins's gas furnace data.

INTUITIONISTIC FUZZY IDEALS OF A SEMIGROUP

AHN, TAE-CHON,HUR, KUL,JANG, KYUNG-WON,ROH, SEOK-BEOM The Honam Mathematical Society 2005 호남수학학술지 Vol.27 No.4

We give the characterization of an intuitionistic fuzzy ideal[resp. intuitionistic fuzzy left ideal, an intuitionistic fuzzy right ideal and an intuitionistic fuzzy bi-ideal] generated by an intuitionistic fuzzy set in a semigroup without any condition. And we prove that every intuitionistic fuzzy ideal of a semigroup S is the union of a family of intuitionistic fuzzy principle ideals of S. Finally, we investigate the intuitionistic fuzzy ideal generated by an intuitionistic fuzzy set in $S^1$.