• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제1권1호
• /
• pp.87-94
• /
• 2001

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2005년도 동계학술발표대회 논문집
• /
• pp.223-228
• /
• 2005

This study develops an optimization program to use optimum design of building HVAC system reducing building energy use and cost. Doe20pt developed is an interface program between DOE2 and GenOpt to perform the optimization procedure more easily. The optimum results can be used to estimate the economical efficiency concerning the building management.

• Journal of Mechanical Science and Technology
• /
• 제20권10호
• /
• pp.1557-1566
• /
• 2006

We present a procedure for the application of global orthogonal polynomial into an atmospheric re-entry maneuvering problem. This trajectory optimization is imbedded in a family of canonically parameterized optimal control problem. The optimal control problem is transcribed to nonlinear programming via global orthogonal polynomial and is solved a sparse nonlinear optimization algorithm. We analyze the optimal trajectories with respect to the performance of re-entry maneuver.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.902-907
• /
• 2004

In this paper, a multi-step optimization using a G.A. (Genetic Algorithm) with variable penalty function is introduced to the structural design optimization of a 5-head route machine. Our design procedure consist of two design optimization stage. The first stage of the design optimization is static design optimization. The following stage is dynamic design optimization stage. In the static optimization stage, the static compliance and weight of the structure are minimized simultaneously under some dimensional constraints and deflection limits. On the other hand, the dynamic compliance and the weight of the machine structure are minimized simultaneously in the dynamic design optimization stage. As the results, dynamic compliance of the 5-head router machine was decreased by about 37％ and the weight of the structure was decreased by 4.48％ respectively compared with the simplified structure model.

• 한국자동차공학회논문집
• /
• 제21권4호
• /
• pp.16-22
• /
• 2013

In this study, we propose the method of optimally changing material of BIW for minimizing weight while satisfying vehicle requirements on static stiffness. First, we formulate a material selection optimization problem. Next, we establish the CAE procedure of evaluating static stiffness. Then, to enhance the efficiency of design work, we integrate and automate the established CAE procedure using a commercial process integration and design optimization (PIDO) tool, PIAnO. For effective optimization, we adopt the approach of metamodel based approximate optimization. As a sampling method, an orthogonal array (OA) is used for selecting sampling points. The response values are evaluated at the sampling points and then these response values are used to generate a metamodel of each response using the linear polynomial regression (PR) model. Using the linear PR model, optimization is carried out an evolutionary algorithm (EA) that can handle discrete design variables. Material optimization result reveals that the weight is reduced by 44.8% while satisfying all the design constraints.

• 한국자동차공학회논문집
• /
• 제21권5호
• /
• pp.8-14
• /
• 2013

In this study, we propose the method of optimally selecting material of front pillar (A-pillar) and package tray for minimizing weight while satisfying vehicle requirements on static stiffness and dynamic stiffness. First, we formulate a material selection optimization problem. Next, we establish the CAE procedure of evaluating static stiffness and dynamic stiffness. Then, to enhance the efficiency of design work, we integrate and automate the established CAE procedure using a commercial process integration and design optimization (PIDO) tool, PIAnO. For effective optimization, we adopt the approach of metamodel based approximate optimization. As a sampling method, an orthogonal array (OA) is used for selecting sampling points. The response values are evaluated at the sampling points and then these response values are used to generate a metamodel of each response using the radial basis function regression (RBFr). Using the RBFr models, optimization is carried out an evolutionary algorithm that can handle discrete design variables. Material optimization result reveals that the weight is reduced by 49.8% while satisfying all the design constraints.

• Journal of the Korean Data and Information Science Society
• /
• 제20권5호
• /
• pp.829-835
• /
• 2009

다구찌 파라미터 설계는 품질특성의 변동을 최대한 줄이면서 동시에 품질특성의 평균을 목표치 가까이 가져가기 위한 설계인자의 최적조건을 찾는 방법이다. 제품의 설계단계에서 품질특성과 여러 개의 설계인자와의 관계는 복잡한 비선형 형태를 가지는 경우가 대부분이다. 신경망에서 유연한 모형선택과 학습능력은 알 수 없는 복잡한 비선형 형태를 파악하는데 아주 유용한 도구이다. 본 연구는 파라미터 설계에서 설계인자의 최적조건을 찾기 위하여 신경망을 이용한 최적화 방안을 제안하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제2권2호
• /
• pp.95-107
• /
• 2001

This paper is devoted to the parameter optimization of unmanned aerial vehicle's (UAV) flight control laws. Optimization procedure is based on the ideas of mixed $H_2/H_{\infty}$ control of multi-model plants. By using this approach, some partial $H_2$-terms defining the performance of nominal and parametrically perturbed Flight Control System (FCS) responses to deterministic command signals in stochastic atmosphere as well as $H_{\infty}$-terms defining robustness of the FCS can be incorporated in the composite cost function. Special penalty function imposed on the location of closed-loop system's poles keeps the speed of response and oscillatory properties for both nominal and perturbed FCS in reasonable limits. That is the reason why this procedure may provide reasonable trade-off between the performance and robustness of FCS that are very important especially for UAV. Its practical importance is illustrated by case studies of lateral and longitudinal control of small UAV.

• Journal of Electrical Engineering and Technology
• /
• 제7권4호
• /
• pp.493-500
• /
• 2012

In this paper the performance of meta-heuristics algorithms such as GA (Genetic Algorithm), DE (Differential Evolution), PSO (Particle Swarm Optimization) and SA (Simulated Annealing) for the problem of TTC enhancement using FACTS devices are compared. In addition to that in the assessment procedure of TTC two novel techniques are proposed. First the optimization algorithm which is used for TTC enhancement is simultaneously used for assessment of TTC. Second the power flow is done using Broyden - Shamanski method with Sherman - Morrison formula (BSS). The proposed approach is tested on WSCC 9 bus, IEEE 118 bus test systems and the results are compared with the conventional Repeated Power Flow (RPF) using Newton Raphson (NR) method which indicates that the proposed method provides better TTC enhancement and computational efficacy than the conventional procedure.

• Journal of Advanced Marine Engineering and Technology
• /
• 제33권1호
• /
• pp.19-27
• /
• 2009

Globally, customer appreciation and demand for quieter products has driven noise control engineers to develop efficient and quieter products in a relatively short time. In the vehicles and ship industry, noise has become an important attribute because of the competitive market and increasing customer awareness. Noise reduction is often achieved through structural modifications by typical approaches. In the present paper, author describes a fundamental study on optimum design of curvature. Bezier curve. and rib attachment to reduce noise from simple panel using a genetic algorithm(GA). The acoustic optimization procedure employed p-FEM for structural analysis, the Rayleigh integral method for acoustic analysis and the GA for searching optimum design. In the optimization procedure. the objective function to be minimized is the average sound power radiated from an objective structure over a given frequency range $0{\sim}300$ Hz.