• 한국통신학회논문지
• /
• 제33권6C호
• /
• pp.480-486
• /
• 2008

전송 신호의 높은 PAPR (Peak-to-Average Power Ratio)은 OFDM (Orthogonal Frequency Division Multiplexing)의 주된 문제점중의 하나이다. PTS (Partial Transmit Sequences) 기법은 OFDM 신호의 PAPR의 통계를 개선하는 기법이다. 그러나 PTS 기법에서 위상 가중치의 선택을 위한 계산 복잡도는 서브블록의 수에 따라 지수적으로 증가한다. 본 논문에서는 ${\mu}$-GA (micro-Genetic Algorithm) 기반의 위상 가중치 탐색 알고리즘을 적용한 낮은 계산 복잡도를 갖는 PTS 기법을 제안한다. 위상 가중치의 탐색은 랜덤하게 생성한 5 개체의 개체군으로부터 시작한다. 이 중에서 적합도가 가장 큰 엘리트와 토너먼트 선택 방법에 의해 나머지 4 개체를 선택하고 교배 연산을 통해 다음 세대를 구성한다. 만일 생성된 세대가 수렴한다면 엘리트를 제외한 나머지 개체를 다시 랜덤하게 생성한다. 일정 세대 이상 PAPR이 개선되지 않거나 사전에 정해진 최대 세대수까지 진행하면 탐색을 종료한다. 제안하는 PTS 기법의 성능을 평가하기 위해 PAPR의 CCDF (Complementary Cumulative Distribution Function)를 이전의 PTS 기법과 비교한다.

• 소성∙가공
• /
• 제5권4호
• /
• pp.269-280
• /
• 1996

A new approach to die shape optimal design in extrusion is presented. The approach consists of a FEM analysis model to predict the value of the objective function a design model to relate the die profile with the design variables and a genetic algorithm based optimaization procedure. The approach was described in detail with emphasis on our modified micro genetic algorithm. Comparison with theoretical solutions was made to examine the validity of the predicted optimal die shapes. The approach was then applied to revealing the optimal die shapes with regard to various objective functions including those for which the design sensitivities can not be deter-mined analytically.

• 한국구조물진단유지관리공학회 논문집
• /
• 제12권4호
• /
• pp.161-167
• /
• 2008

본 연구에서는 고등해석과 유전자 알고리즘을 이용한 트러스 구조물의 최적설계를 수행하였다. 본 연구에서 사용한 고등해석은 기하학적 비선형과 재료적 비선형을 동시에 고려한다. 최적화 알고리즘으로 마이크로 유전자 알고리즘을 사용하였다. 목적함수로 구조물의 중량을 사용하였으며, 제약조건식은 구조시스템의 하중-저항능력 및 변위 조건을 고려하였다. 제안된 방법에 의한 최적설계 결과를 기존의 연구결과와 비교하여 그 타당성을 증명하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.853-858
• /
• 1993

The error back-propagation(BP) algorithm is widely used for finding optimum weights of multi-layer neural networks. However, the critical drawback of the BP algorithm is its slow convergence of error. The major reason for this slow convergence is the premature saturation which is a phenomenon that the error of a neural network stays almost constant for some period time during learning. An inappropriate selections of initial weights cause each neuron to be trapped in the premature saturation state, which brings in slow convergence speed of the multi-layer neural network. In this paper, to overcome the above problem, Micro-Genetic algorithms(.mu.-GAs) which can allow to find the near-optimal values, are used to select the proper weights and slopes of activation function of neurons. The effectiveness of the proposed algorithms will be demonstrated by some computer simulations of two d.o.f planar robot manipulator.

• Structural Engineering and Mechanics
• /
• 제23권4호
• /
• pp.387-407
• /
• 2006

A Genetic Algorithm (hereinafter GA) based optimum design algorithm and program for plane steel frames with partially restrained connections is presented. The algorithm was incorporated with the refined plastic hinge analysis method, in which geometric nonlinearity was considered by using the stability functions of beam-column members and material nonlinearity was considered by using the gradual stiffness degradation model that included the effects of residual stress, moment redistribution by the occurrence of plastic hinges, partially restrained connections, and the geometric imperfection of members. In the genetic algorithm, a tournament selection method and micro-GAs were employed. The fitness function for the genetic algorithm was expressed as an unconstrained function composed of objective and penalty functions. The objective and penalty functions were expressed, respectively, as the weight of steel frames and the constraint functions which account for the requirements of load-carrying capacity, serviceability, ductility, and construction workability. To verify the appropriateness of the present method, the optimum design results of two plane steel frames with fully and partially restrained connections were compared.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2007년 추계학술발표대회 개요집
• /
• pp.57-59
• /
• 2007

• 한국항해항만학회지
• /
• 제30권2호
• /
• pp.137-143
• /
• 2006

The optimum grillage design belongs to nonlinear constrained optimization problem. The determination of beam scantlings for the grillage structure is a very crucial matter out of whole structural design process. The performance of optimization methods, based on penalty functions, is highly problem-dependent and many methods require additional tuning of some variables. This additional tuning is the influences of penalty coefficient, which depend strongly on the degree of constraint violation. Moreover, Binary-coded Genetic Algorithm (BGA) meets certain difficulties when dealing with continuous and/or discrete search spaces with large dimensions. With the above reasons, Real-coded Micro-Genetic Algorithm ($R{\mu}GA$) is proposed to find the optimum beam scantlings of the grillage structure without handling any of penalty functions. $R{\mu}GA$ can help in avoiding the premature convergence and search for global solution-spaces, because of its wide spread applicability, global perspective and inherent parallelism. Direct stiffness method is used as a numerical tool for the grillage analysis. In optimization study to find minimum weight, sensitivity study is carried out with varying beam configurations. From the simulation results, it has been concluded that the proposed $R{\mu}GA$ is an effective optimization tool for solving continuous and/or discrete nonlinear real-world optimization problems.

• 한국강구조학회 논문집
• /
• 제17권2호통권75호
• /
• pp.173-181
• /
• 2005

본 연구는 유한요소법과 고도화된 마이크로 유전알고리즘을 조합하여 자유 진동하는 박판 구조물에 대한 손상 규명을 다룬다. 조합된 방법에 의해 역 문제를 해결하기 위하여, 본 연구는 측정 데이터로서 구조물의 모드 형상 대신 몇 개의 고유진동수를 사용한다. 본 연구에서 제안한 방법은 손상된 요소를 탐지할 수 있을 뿐만 아니라 손상의 개수, 위치 그리고 정도를 추정할 수 있다. 제안된 방법의 타당성을 검증하기 위하여 알고리즘은 임의의 손상을 갖는 강으로 된 지유진동 박판 구조물을 대상으로 적용하였다. 기존의 단순 유전알고리즘에 비하여 본 연구에서 제안한 알고리즘은 수치적 효율성에서 큰 장점을 갖는다. 수치해석 예제들은 고유모드 대신 단지 몇 개의 고유진동수 값만으로도 마이크로 유전알고리즘은 박판의 손상을 정확히 규명할 수 있음을 보여준다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2008년도 정기 학술대회
• /
• pp.416-421
• /
• 2008

A Metropolis genetic algorithm (MGA) is a newly-developed hybrid algorithm combining simple genetic algorithm (SGA) and simulated annealing (SA). In the algorithm, favorable features of Metropolis criterion of SA are incorporated in the reproduction operations of SGA. This way, MGA alleviates the disadvantages of finding imprecise solution in SGA and time-consuming computation in SA. It has been successfully applied and the efficiency has been verified for the practical structural design optimization. However, applicability of MGA for the wider range of problems should be rigorously proved through the solution of mathematical optimization problems. Thus, performances of MGA for the typical mathematical problems are investigated and compared with those of conventional algorithms such as SGA, micro genetic algorithm (${\mu}GA$), and SA. And, for better application of MGA, the effects of acceptance level are also presented. From numerical Study, it is again verified that MGA is more efficient and robust than SA, SGA and ${\mu}GA$ in the solution of mathematical optimization problems having various features.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.608-611
• /
• 2003

In this paper, laser direct micromaching is developed to fabricate micro patterns using UV laser ( λ$_3$= 355 nm). Experimentally, laser beam paths mainly influences the surface shape quality. Thus. we proposed laser beam path generator by extracting shape data in a blueprint worked through CAD modeler and using genetic algorithm that considers the characteristics of laser beam. The results show that various shapes of micro patterns could be manufactured using proposed method in this paper.