• 제목/요약/키워드: design evolution

검색결과 967건 처리시간 0.028초

신경회로망 모델을 이용한 철도 현가장치 설계변수 최적화 (Optimization of Design Variables of Suspension for Train using Neural Network Model)

  • 김영국;박찬경;황희수;박태원
    • 한국소음진동공학회:학술대회논문집
    • /
    • 한국소음진동공학회 2002년도 춘계학술대회논문집
    • /
    • pp.1086-1092
    • /
    • 2002
  • Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of a given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a mega model that has a regression model made by sampling data through simulation. In this paper, the neural network is used a mega model that have twenty-nine design variables and forty-six responses. After this mega model is constructed, multi-objective optimal solutions are achieved by using the differential evolution. This paper shows that this optimization method using the neural network and the differential evolution is a very efficient tool to solve the complex optimization problem.

  • PDF

유조선 화물창내 대형 브라켓 치수 최적화 연구 (A Study on Size Optimization of the Big Bracket in the Cargo Hold of Crude Oil Tanker)

  • 신상훈;이종환;김도현;권진칠
    • 대한조선학회 특별논문집
    • /
    • 대한조선학회 2005년도 특별논문집
    • /
    • pp.63-68
    • /
    • 2005
  • Optimum design of the big brackets is performed through iterated 3-D FE analyses to meet the permissible limits of stress, which consumes an excessive amount of calculation time. Therefore, this study has been prepared to determine rapidly and accurately an optimum size and scantling of the big brackets at the initial design stage. The generalized slope deflection method (GSDM) based on the span point concept is applied to enhance the efficiency of iterated structural analyses. The accuracy and applicability of the present method is verified by comparing with a detail 3-D FE analysis of web frame structures. As an optimization technique, evolution strategies (ES) are applied using discrete design variables for practical design.

  • PDF

신경회로망 모델을 이용한 철도 현가장치 설계변수 최적화 (Optimization of Design Variables of a Train Suspension Using Neural Network Model)

  • 김영국;박찬경;황희수;박태원
    • 한국소음진동공학회논문집
    • /
    • 제12권7호
    • /
    • pp.542-549
    • /
    • 2002
  • Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of given design variables and chance them to get a bettor design. Even though commercial simulation codes are used, the computational time and cost remains non-trivial. Therefore, malty researchers have used a mesa model made by sampling data through simulation. In this paper, four mesa-models for each index group such as ride comfort, derailment Quotient, unloading radio and stability index, are constructed by use of neural network. After these meta models are constructed, multi-objective optimization are achieved by using the differential evolution. This paper shows that the optimization of design variables using the neural network model is very efficient to solve the complex optimization Problem.

Optimal Design of Piezoelectric Cantilever Fan by Three-Dimensional Finite Element Analysis

  • Kim Byoung-Jai;Rho Jong-Seok;Jung Hyung-Kyo
    • KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
    • /
    • 제5B권1호
    • /
    • pp.90-94
    • /
    • 2005
  • As the structure of the piezoelectric bimorph cantilever becomes increasingly more complicated, a more accurate and efficient analysis of piezoelectric media is needed. In this paper, the piezoelectric transducer is analyzed by using the three-dimensional finite element method. The validity of the three-dimensional finite element routine is confirmed by comparing the experimental result. The resonance characteristics, such as resonance frequency and anti-resonance frequency, of the piezoelectric cantilever are calculated by the experimentally verified three dimensional finite element method. Subsequently, the characteristics, such as mechanical displacement and impedance, are calculated at the resonance frequency. Besides, to design the piezoelectric bimorph cantilever shape that maximizes displacement at the tip, the ES (Evolution Strategy) algorithm is applied. Finally, optimal design for the fan of the piezoelectric cantilever is fulfilled to obtain maximum displacement at the tip. From these results, the application potentiality of the piezoelectric bimorph cantilever fan is identified.

유전알고리즘을 이용한 비선형 시스템의 지능형 퍼지 제어기 설계 (Design of Intelligent Fuzzy Controller for Nonlinear System Using Genetic Algorithm)

  • 김문환;주영훈;박진배
    • 한국지능시스템학회논문지
    • /
    • 제14권5호
    • /
    • pp.593-597
    • /
    • 2004
  • 본 논문은 비선형 시스템의 새로운 퍼지 제어기 설계 기법을 제안한다. 기존의 퍼지 제어기 설계 방법들은 안정도 조건을 만족시키는 제어 이득을 얻기 위해 수학적인 접근을 통해 해를 찾는 방법들이 많이 연구되었다 하지만 플랜트와 제어 방법에 따라 이러한 수학적인 접근이 힘든 경우가 있다 본 논문에서는 이를 해결하기 위해 깊은 수학적인 접근이 아닌 지능적인 접근 방법을 사용하여 안정화된 퍼지 제어기의 설계하는 기법을 제안한다. 제안된 기법은 퍼지 제어기의 안정화 조건을 만족시키는 제어 이득을 전략 기반 유전 알고리즘을 사용하여 동정한다 전략 기반 유전 알고리즘은 제어기의 안정화 조건을 만족시키는 해를 찾기 위해 전략적으로 교차와 돌연변이를 변화시킨다. 전력 기반 유전 알고리즘은 제어기의 안정화 조건을 만족시키는 해를 찾기 위해 전략적으로 교차와 돌연변이 영역을 변화시킴으로서 빠르게 해를 찾는다. 최종적으로 모의 실험을 통해 제안된 기법의 우수성을 확인하였다.

다목적함수 최적화기법을 이용한 유조선의 최적구조설계 (Optimum Structural Design of Tankers Using Multi-objective Optimization Technique)

  • 신상훈;장창두;송하철
    • 한국전산구조공학회논문집
    • /
    • 제15권4호
    • /
    • pp.591-598
    • /
    • 2002
  • 공학적 설계에 있어 많은 문제들은 몇 가지 목적함수들을 동시에 최소화하여야 할 필요가 있을 경우가 있다. 선박설계에 있어, 종래에는 자재비 경감과 재화중량 증가를 위해 최소중량설계가 구조 설계의 주된 목적이었으나, 값싼 노동력을 내세운 후발 조선국과의 치열한 국제 경쟁을 극복하기 위해서는 보다 경제성 있는 선박 건조 기술 개발이 선행되어야 할 것이다. 이에 따라 본 연구에서는 다목적함수 최적화기법을 이용한 선체 구조의 보다 합리적인 설계 방안에 대한 연구를 수행하여 실제 건조된 유조선을 대상으로 중량, 건조비 등의 경제성을 비교 평가하였다. 다목적 함수로는 유조선의 중량과 건조비로 하였으며 최적화 기법으로는 확률론적 탐색법인 ES(Evolution Strategies)를 이용하였다. 건조비 모델은 상대 건조비 개념을 도입하였고, 종강도 부재는 선급규정에 의해, 횡강도 및 횡격벽 부재는 직접해석법인 일반화된 경사처짐법을 사용하여 설계에 적용하였다. 다목적함수 최적화 결과로부터 도출된 Pareto 최적 설계점들에 대하여, 요구운임률을 각각 산정함으로써 이들 최적 설계점들 중에서 가장 경제성이 뛰어난 선박 설계 방안을 제시하였다.

Overview of the Benefits of Structural Fire Engineering

  • Jowsey, Allan;Scott, Peter;Torero, Jose
    • 국제초고층학회논문집
    • /
    • 제2권2호
    • /
    • pp.131-139
    • /
    • 2013
  • The field of structural fire engineering has evolved within the construction industry, driven largely by the acceptance of performance-based or goal-based design. This evolution has brought two disciplines very close together - that of structural engineering and fire engineering. This paper presents an overview of structural systems that are frequently adopted in tall building design; typical beams and columns, concrete filled steel tube columns and long span beams with web openings. It is shown that these structural members require a structural analysis in relation to their temperature evolution and failure modes to determine adequate thermal protection for a given fire resistance period. When this is accounted for, a more explicit understanding of the behaviour of the structure and significant cost savings can be achieved. This paper demonstrates the importance of structural fire assessments in the context of tall building design. It is shown that structural engineers are more than capable of assessing structural capacity in the event of fire using published methodologies. Rather than assumed performance, this approach can result in a safe and quantified design in the event of a fire.