• 대한기계학회논문집A
• /
• 제34권12호
• /
• pp.1793-1803
• /
• 2010

가중치법이나 목표계획법을 이용하여 다목적함수 최적화를 수행할 때 설계자는 각 함수에 적절한 가중치나 목표값을 설정해 주어야 한다. 하지만 파라미터를 잘못 설정하게 되면 파레토 최적해를 얻지못하기 때문에 이는 설계자에게 큰 부담이 된다. 최근에 데이터의 분포특성만을 이용하여 데이터의 평균과 함수 사이의 거리를 표현하는 마하라노비스 거리(MD)를 최소화하는 MTS기법이 개발되었다. 이 방법은 파라미터를 설정하지 않아도 되는 장점이 있지만 최적해가 참고데이터의 평균으로 수렴하는 단점이 있다. 따라서 본 연구에서는 방향성이 없는 기존의 MD에 방향성을 부여한 새로운 거리 척도인 SMD를 제안하였다. 그리고 SMD법이 계산과정에서 각 함수의 가중치를 자동으로 반영하고 평균에서 가장 멀리 위치한 한 점을 항상 파레토 최적해로 제공한다는 것을 2개의 단순예제를 통해 검증하였다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.323-335
• /
• 1999

In this paper, we propose a new hybrid model of artificial neural networks(ANNs) and genetic algorithm (GA) to optimal feature transformation and feature weighting. Previous research proposed several variants of hybrid ANNs and GA models including feature weighting, feature subset selection and network structure optimization. Among the vast majority of these studies, however, ANNs did not learn the patterns of data well, because they employed GA for simple use. In this study, we incorporate GA in a simultaneous manner to improve the learning and generalization ability of ANNs. In this study, GA plays role to optimize feature weighting and feature transformation simultaneously. Globally optimized feature weighting overcome the well-known limitations of gradient descent algorithm and globally optimized feature transformation also reduce the dimensionality of the feature space and eliminate irrelevant factors in modeling ANNs. By this procedure, we can improve the performance and enhance the generalisability of ANNs.

• 제어로봇시스템학회논문지
• /
• 제4권2호
• /
• pp.163-169
• /
• 1998

In this paper, we design an optimal model following ${\mu}-$synthesis control system for fuel-injection of diesel engine which has robust performance and satisfactory command tracking performance in spite of uncertainties of the system. To do this, we give gain and dynamics parameters to the weighting functions and apply genetic algorithm with reference model to the optimal determination of the weighting functions that are given by the D-K iteration method which can design ${\mu}-$synthesis controller in the state space. These weighting functions are optimized simultaneously in the search domain which guarantees the robust performance of the system. The ${\mu}-$synthesis control system for fuel-injection designed by the above method has not only the robust performance but also a better command tracking performance than those of the ${\mu}-$synthesis control system designed by trial-and-error method. The effectiveness of this ${\mu}-$synthesis control system for fuel-injection is verified by computer simulation.

• 한국군사과학기술학회지
• /
• 제13권6호
• /
• pp.951-957
• /
• 2010

An optimal path generation method considering the safety of UGV(Unmanned Ground Vehicle) is proposed and demonstrated through examples. Among various functions of UGV, real-time obstacle avoidance is a key issue to realize realistic scenario in FCS(Future Combat Systems). A two-dimensional narrow corridor environment is considered as a test field. For each step of UGV movement, two objectives are considered: One is to minimize the distance to the target and the other to maximize the distance to the nearest point of an obstacle. A weighted objective function is used in the optimization problem. Equality and inequality constraints are taken to secure the UGV's dynamics and safety. The weighting factors are controlled by a fuzzy controller which is constructed by a fuzzy rule set and membership functions. Simulations are performed for two cases. First the weighting factors are considered as constant values to understand the characteristics of the corresponding solutions and then as variables that are adjusted by the fuzzy controller. The results are satisfactory for realistic situations considered. The proposed optimal path generation with the fuzzy control is expected to be well applicable to real environment.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.701-706
• /
• 1998

A design method of rule -based fuzzy modeling is presented for the model identification of complex and nonlinear systems. The proposed rule-based fuzzy modeling implements system structure and parameter identification in the efficient form of " IF..., THEN,," statements. using the theories of optimization and linguistic fuzzy implication rules. The improved complex method, which is a powerful auto-tuning algorithm, is used for tuning of parameters of the premise membership functions in consideration of the overall structure of fuzzy rules. The optimized objective function, including the weighting factors, is auto-tuned for better performance of fuzzy model using training data and testing data. According to the adjustment of each weighting factor of training and testing data, we can construct the optimal fuzzy model from the objective function. The least square method is utilized for the identification of optimum consequence parameters. Gas furance and a sewage treatment proce s are used to evaluate the performance of the proposed rule-based fuzzy modeling.

• 전자공학회논문지SC
• /
• 제37권2호
• /
• pp.8-15
• /
• 2000

본 연구는 가중함수의 주파수 영역 해석에 의한 H∞ 최적 제어기를 설계하고 이를 대상 시스템에 적용하여 해석하였다. 이는 가중함수와 개 루프 전달함수에서 견실성을 만족하는 영역과 매개변수 γ의 최적 값이 존재하는 영역을 도시하고 H∞ 최적 제어기를 구성하기 위한 알고리즘을 간략화 시킬 수 있다. 또한 제안된 방법에 의해 설계된 제어기는 플랜트 불확실성의 변화에도 불구하고 어떠한 동작점에서도 원하는 사양과 성능을 만족하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 B
• /
• pp.587-589
• /
• 1997

In this paper we design the model following ${\mu}$-synthesis control system for optimal fuel-injection of diesel engine using genetic algorithms. To do this, we give gain and dynamics parameters to the weighting functions and apply genetic algorithms with reference model to the optimal determination of weighting functions that are given by D-K iteration method which can design ${\mu}$-synthesis controller in the state space. These weighting functions are optimized simultaneously in the search domain selected adequately. The effectiveness of this ${\mu}$-synthesis control system for fuel-injection is verified by computer simulation.

• 조명전기설비학회논문지
• /
• 제13권2호
• /
• pp.102-110
• /
• 1999

본 연구에서는 유전 알고리즘을 사용하여 복잡한 최적화의 과정이없이 가중치 행렬 Q, R을 동시에 최적화함으로써 상태변수들의 결합과 동작점의 변화에 따른 시스템의 파라미터 변동 등에도 불구하고 기준모델의 출력을 최적으로 추종하는 모델 추종형 제어 시스템을 설계법으로 제시하고 이를 보일러-터빈 설비를 위한 모델 추종형 다변수 제어 시스템의 설계에 적용하고자 한다. 또한 컴퓨터 시뮬레이션을 통하여 설계된 모델 추종형 제어 시스템의 성능을 비교고찰하고 그 유용성을 확인하다.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2000년도 추계학술발표논문집
• /
• pp.251-254
• /
• 2000

The critical problem in dealing with multiple characteristics is how to compromise the conflict among the selected levels of the design parameters for each individual characteristic. In this study, First, Methodology using SN ratio optimized by univariate technique is proposed and a parameter design procedure to achieve the optimal compromise among several different response variables is developed. Second, to solve the issue on the optimal design for multiple quality characteristics, this study modelled the expected loss function with cross-product terms among the characteristics and derived range of the coefficients of the terms. The model will be used to determine the global optimal design parameters where there exists the conflict among the characteristics, which shows difference in optimal design parameters for the individual characteristics. Third, this paper propose a decision model to incorporates the values assigned by a group of experts on different factors in weighting decision of characteristic. Using this model, SN ratio of taguchi method for each of subjective factors as well as values of weights are used in this comprehensive method for weighting decision of characteristic.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1986년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 17-18 Oct. 1986
• /
• pp.209-211
• /
• 1986

The continuous time linear quadratic problem (LQP) has been applied to the control of a 8-tray distillation column using the code VASP. The weighting matrices for the state variables and control variables were adjusted iteratively. The simulation results of the optimal control with 2 inputs and 2 outputs showed that the LQP method is very satisfactory for a rapid response and feedback control, and any desired response could be obtained by adjusting the weighting matrices Q under = and R under =. The feedback gain matrix K under = was also determined.