• 제어로봇시스템학회논문지
• /
• 제12권3호
• /
• pp.221-226
• /
• 2006

In this paper, we study an approach to design a Fuzzy PI controller in HVDC(High Voltage Direct Current) system. In the rectifier of traditional HVDC system, turning on, turning off, triggering and protections of thyristors have lots of problems that can make the dynamic instability and cannot damp the dynamic disturbance efficiently. In order to solve the above problems, we adapt Fuzzy PI controller for the fire angle control of rectifier. The performance of the Fuzzy PI controller is sensitive to the variety of scaling factors. The design procedure dwells on the use of evolutionary computing(Genetic Algorithms, GAs). Then we can obtain factors of the Fuzzy PI controller by Genetic Algorithms. A comparative study has been performed between Fuzzy PI controller and traditional PI controller, to prove the superiority of the proposed scheme.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.519-524
• /
• 1996

This paper describes the application of Genetic Algorithms(GAs) to nonlinear constrained mixed optimization problems. Genetic Algorithms are combinatorial in nature, and therefore are computationally suitable for treating discrete and integer design variables. But, several problems that conventional GAs are ill defined are applicaiton of penalty function that can be adapted to transform a constrained optimization problem into an unconstrained optimization problem into an unconstrained one and premature convergence of solution. Thus, we developed an modified GAs to solve this problems, and two examples are given to demonstrate the effectiveness of the methodology developed in this paper.

• 한국추진공학회지
• /
• 제8권3호
• /
• pp.44-52
• /
• 2004

본 연구에서는 실험데이터와 유전자 알고리즘으로 압축기 성능선도를 생성하는 방법을 제안하였다. 다수의 실험을 통해 엔진의 성능 데이터를 획득하고 회전수에 따른 유량함수, 압력비, 효율의 함수관계를 3차 방정식으로 유도한 후 유전자 알고리즘을 이용하여 미계수를 구하여 압축기 성능선도를 생성하였다. 새롭게 생성한 압축기 성능선도를 이용하여 상용 성능해석 프로그램인 GASTURB로 정상상태 성능해석을 수행하여 검증데이터와 비교하였다.

• 한국항공우주학회지
• /
• 제35권3호
• /
• pp.238-247
• /
• 2007

유전자 알고리즘은 자연선택과 유전법칙을 적용하여 최적해를 탐색하는 방법으로, 본 연구에서 항공기용 가스터빈 엔진의 결함 진단을 위한 학습 알고리즘으로 사용되었다. 성능 저하를 고려한 구성요소는 압축기, 가스발생기 터빈, 동력 터빈이며, 설계점에서 엔진의 단일 구성요소에 대하여 각각 성능 저하 예측을 수행한 후, 이를 바탕으로 결함 진단을 수행하였다. 학습데이터 수의 증가가 유전자 알고리즘을 이용한 성능 저하 예측 및 결함 진단에 미치는 영향을 분석하였으며, 결과적으로 결함치에 대한 RMS 오차율이 모두 3% 이내로 예측됨을 확인하였다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2006년도 제27회 추계학술대회논문집
• /
• pp.285-288
• /
• 2006

유전자 알고리즘은 자연선택과 유전법칙을 적용하여 최적해를 탐색하는 방법으로, 본 연구에서 항공기용 가스터빈 엔진의 결함 진단을 위한 학습 알고리즘으로 사용되었다. 성능 저하를 고려한 구성 요소는 압축기, 가스발생기 터빈, 동력 터빈이며, 설계점에서 엔진의 구성 요소에 대하여 복합 결함 진단을 수행하였다. 그 결과, 압축기, 가스발생기터빈, 동력터빈모두 10% 이내의 오차로 예측됨을 확인하였다.

• 한국지능시스템학회논문지
• /
• 제2권3호
• /
• pp.40-49
• /
• 1992

In this paper, an approach to identify fuzzy rules is proposed. The decision of the optimal number of fuzzy rule is made by means of fuzzy c-means clustering. The identification of the parameters of fuzzy implications is carried out by use of genetic algorithms. For the efficinet and fast parameter identification, the reduction thechnique of search areas of genetica algorithms is proposed. The feasibility of the proposed approach is evaluated through the identification of the fuzzy model to describe an input-output relation of Gas Furnace. Despite the simplicity of the propsed apprach the accuracy of the identified fuzzy model of gas furnace is superior as compared with that of other fuzzy modles.

• Structural Engineering and Mechanics
• /
• 제11권2호
• /
• pp.151-170
• /
• 2001

With increasing competition, the engineering industry is in need of optimization of designs that would lead to minimum cost or weight. Recent developments in Genetic Algorithms (GAs) makes it possible to model and obtain optimal solutions in structural design that can be put to use in industry. The main objective of this paper is to illustrate typical applications of GAs to practical design of structural systems such as steel trusses, towers, bridges, reinforced concrete frames, bridge decks, shells and layout planning of buildings. Hence, instead of details of GA process, which can be found in the reported literature, attention is focussed on the description of the various applications and the practical aspects that are considered in Genetic Modeling. The paper highlights scope and future directions for wider applications of GA based methodologies for optimal design in practice.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.155-157
• /
• 2005

We propose a new category of hybrid multi-layer neural networks with hetero nodes such as Fuzzy Set based Polynomial Neurons (FSPNs) and Polynomial Neurons (PNs). These networks are based on a genetically optimized multi-layer perceptron. We develop a comprehensive design methodology involving mechanisms of genetic optimization and genetic algorithms, in particular. The augmented genetically optimized HFPNN (namely gHFPNN) results in a structurally optimized structure and comes with a higher level of flexibility in comparison to the one we encounter in the conventional HFPNN. The GA-based design procedure being applied at each layer of HFPNN leads to the selection of preferred nodes (FPNs or PNs) available within the HFPNN. In the sequel, two general optimization mechanisms are explored. First, the structural optimization is realized via GAs whereas the ensuing detailed parametric optimization is carried out in the setting of a standard least square method-based learning. The performance of the gHFPNNs quantified through experimentation where we use a number of modeling benchmarks-synthetic and experimental data already experimented with in fuzzy or neurofuzzy modeling.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.252-254
• /
• 2006

The recent improvement in the performance of digital processor, the application of control technology, which used in the HVDC(High Voltage Direct Current) system with the digital processors, has increased. Having this research development as the basis, this paper presents an achievement of progression by tuning the parameter of PI controller based on Genetic Algorithms(GAs) and by controlling with PI controller with a developed simulator by applying the Matrix operating function, voltage source switching element, modified nodal analysis which can include transformer and the backward Euler which does not create the problem of numerical oscillation. As a result, I expect this development in the simulator HVDC System to bring more application in the field of control technology research with an expanded practicality.

• 산업기술연구
• /
• 제31권B호
• /
• pp.45-50
• /
• 2011

Recently, machine olfactory systems that have been proposed as an artificial substitute of the human olfactory system are being studied by many researchers because they can scent dangerous gases and identify the type of gases in contamination areas instead of the human. In this paper, we present an effective design method for the gas identification system. The design method adopted the sequential combination between genetic algorithms and TSK fuzzy logic system. First, the proposed method allowed the designed gas identification system effectively performing the pattern analysis because it was able to avoid the curse of dimensionality caused by use of a large number of sensors. Secondly, the method led the gas identification system to good performance because it was able to deal with drift characteristics of the sensor data by using description ability of the fuzzy system for nonlinear data. In simulation, we demonstrated the effectiveness of the designed gas identification system by using the simulation results of five types of gases.