• Journal of Advanced Marine Engineering and Technology
• /
• 제21권2호
• /
• pp.108-116
• /
• 1997

유전알고리즘은 진화원리에서 발견된 몇몇 특징들을 컴퓨터 알고리즘과 결합시켜 복잡한 최적화 문제를 해결하려는 도구로서 1975년 미국의 Holland 교수에 의해 처음으로 개발되었다. 주어진 문제에서 탐색환경이 다변수 또는 다봉(multi-modal)이 되어 대단히 복잡하거나 또는 부분적으로 알려질 경우는, 구배(gradient)에 기초한 재래식 방법을 사용하여 최적화하는 것은 매우 어렵게 되고 경우에 따라서는 불가능할 수도 있다. 이러한 이유로 유전알고리즘과 같은 강인한 탐색법이 요구된다. 유전알고리즘의 장점은 연속성(continuity), 미분가능성(differentiability), 단봉성(unimodality) 등과 같이 탐색공간에 대한 제약으로부터 자유롭다는 것이다. 다시 말하면 목적함수 외 탐색공간에 대한 사전지식을 필요로 하지 않고, 매우 크고 복잡한 공간일지라도 전역해 쪽으로 수렴해 갈수 있다는 것이다. 이러한 특성 때문에 유전알고리즘은 실제 환경에서 많은 복잡한 최적화 문제를 해결하는 방법으로 인정을 받고 있으며, 함수의 최적화, 신경회로망의 학습, 동적시스템의 식별및 제어, 신호처리등 여러 분야에 성공적으로 응용되고 있다. 이러한 중요성에 비해 유전알고리즘에 대한 연구는 국내적으로는 아직 미진한 수준이나 최근 이에 대한 관심이 고조되고 있으며, 또한 그 응용분야도 점점 넓어져 이론 개발과 실질적인 응용에 확산되리라 생각된다. 따라서 본 해설기사는 유전알고리즘의 원리와 응용 사례를 살펴봄으로서 최적화 문제를 해결하려는 독자들에게 조금이나마 도움을 주고자 한다.

• 한국공작기계학회논문집
• /
• 제13권5호
• /
• pp.67-74
• /
• 2004

Laser heat treatment is an effective technique used to improve the tribological properties and also to increase the service life of automobile components such as camshafts, crankshatfs, lorry brake drums and gears. High power $CO_2$ lasers and Nd:YAG lasers are employed for localized hardening of materials and hence are of potential application in the automobile industries. The heat is conducted rapidly into the bulk of the specimen causing self-quenching action to occur and the formation of matrensitic structure. In this investigation, the microstructrual features occurring in Nd:YAG laser hardening SM45C and $STD_11$ steel are discussed with the use of optical microscopic and scanning electron microscopic analysis. Moreover, This paper describes the optimisation of the processing parameters for maximum hardened depth of SM45C and $STD_11$ steel specimens of 10mm thickness by using CW:YAG laser.

• Computers and Concrete
• /
• 제5권5호
• /
• pp.475-490
• /
• 2008

The paper explores the potential of applicability of Genetic programming approach (GP), adopted in this investigation, to model the combined effects of five independent variables to predict the mini-slump, the plate cohesion meter, the induced bleeding test, the J-fiber penetration value, and the compressive strength at 7 and 28 days of self-compacting slurry infiltrated fiber concrete (SIFCON). The variables investigated were the proportions of limestone powder (LSP) and sand, the dosage rates of superplasticiser (SP) and viscosity modifying agent (VMA), and water-to-binder ratio (W/B). Twenty eight mixtures were made with 10-50% LSP as replacement of cement, 0.02-0.06% VMA by mass of cement, 0.6-1.2% SP and 50-150% sand (% mass of binder) and 0.42-0.48 W/B. The proposed genetic models of the self-compacting SIFCON offer useful modelling approach regarding the mix optimisation in predicting the fluidity, the cohesion, the bleeding, the penetration, and the compressive strength.

• Journal of Magnetics
• /
• 제9권2호
• /
• pp.65-68
• /
• 2004

Magnetically soft nanomaterials obtained by controlled crystallisation of metallic glasses are the newest group of materials for inductive components. In particular, research is carried out in the field of alloys for high temperature applications. This kind of materials must meet two basic requirements: good magnetic properties and stability of properties and structure. In the present work the magnetic properties and structure of Fe-Co-Hf-Zr-Cu-B (HIDTPERM-type) alloys were investigated, as well as their stability. Differential thermal analysis, (DTA), X-ray diffractometry (XRD), transmission electron microscopy (TEM), magnetometry (VSM) and quasistatic hysteresis loop recording were used to characterise structure and properties of the alloys investigated. Optimisation against properties and their stability was performed, resulting in formulation of chemical composition of the optimum alloy, as well as its heat treatment.

• Journal of Mechanical Science and Technology
• /
• 제18권3호
• /
• pp.432-442
• /
• 2004

This paper presents a neural network predictor for analysing rigidity variations of hydrostatic bearing system. The designed neural network has feedforward structure with three layers. The layers are input layer, hidden layer and output layer. Two main parameter could be considered for hydrostatic bearing system. These parameters are the size of bearing pocket and the orifice dimension. Due to importancy of these parameters, it is necessary to analyse with a suitable optimisation method such as neural network. As depicted from the results, the proposed neural predictor exactly follows experimental desired results.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1898-1904
• /
• 2003

Laser heat treatment is an effective technique used to improve the tribological properties and also to increase the service life of automobile components such as camshafts, crankshatfs, lorry brake drums and gears. High power $CO_{2}$ lasers and Nd:YAG lasers are employed for localized hardening of materials and hence are of potential application in the automobile industries. The heat is conducted rapidly into the bulk of the specimen causing self-quenching to occur and the formation of matrensitic structure. In this investigation, the microstructrual features occurring in Nd:YAG laser hardening SM45C and $STD_{11}$ steel are discussed with the use of optical microscopic and scanning electron microscopic analysis. Moreover, This paper describes the optimisation of the processing parameters for maximum hardened depth of SM45C and $STD_{11}$ steel specimens of 10mm thickness by using CW Nd:YAG laser.

• 한국자동차공학회논문집
• /
• 제4권1호
• /
• pp.155-164
• /
• 1996

Dual-fuel engines are being researched with emphasis on the possible types of natural gas supply systems. Hence, a three-dimensional combustion model by using finite volume method was developed to provide a fundamental understanding of the auto-ignition of pilot distillate and subsequent burning of natural gas, when the natural gas as well as the distillate was directly injected into a quiescent diesel engine like combustion bomb tests and the numerical results were investigated for the mixed combustion phenomena. With high-pressure natural gas injection, it was found that the gaseous fuel injection characteristics had to be well harmonised with that of the pilot distillate. For better combustion efficiency, however, further researches are required for the optimisation of injection system in the existence of air motion.

• 산업경영시스템학회지
• /
• 제35권4호
• /
• pp.98-109
• /
• 2012

Recently, the optimisation of end-of-life (EOL) product remanufacturing processes has been highlighted. In particular, computer remanufacturing becomes important as the amount of disposed of computers is rapidly increasing. At the computer remanufacturing, depending on the selections of used computer parts, the value of remanufactured computers will be different. Hence, it is important to select appropriate computer parts at the reassembly. To this end, this study deals with a decision making problem to select the best combination of computer parts for minimising the total remanufacturing computer cost. This problem is formulated with an integer nonlinear programming model and heuristic search algorithms are proposed to resolve it.

• 대한조선학회논문집
• /
• 제30권1호
• /
• pp.10-19
• /
• 1993

최적설계는 일반적으로 주어진 설계에 적용할 경제성평가기법을 필요로 한다. 본 연구에서는 선박용 발전장치 설계에 적용되는 경제성평가방법을 제시하였다. 가능한 발전 장치들에 대하여 그 투자액의 회수기간과 순현가를 경제성 지수화 하고 또, 그 설계된 장치의 운전상의 난이도를 평가하여 지수화 하고 이 지수들을 종합하여 종합경제성평가지수를 산출하여 이 지수로 발전장치 선정의 기준으로 삼도록 하였다. 이 방법을 실선의 설계에 적용하여 유용성을 보였다.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제9권5호
• /
• pp.492-498
• /
• 2017

Subsea pipeline route design is a crucial task for the offshore oil and gas industry, and the route selected can significantly affect the success or failure of an offshore project. Thus, it is essential to design pipeline routes to be eco-friendly, economical and safe. Obstacle avoidance is one of the main problems that affect pipeline route selection. In this study, we propose a technique for designing an automatic obstacle avoidance. The Laplacian smoothing algorithm was used to make automatically generated pipeline routes fairer. The algorithms were fast and the method was shown to be effective and easy to use in a simple set of case studies.