• 한국전기전자재료학회논문지
• /
• 제21권1호
• /
• pp.73-78
• /
• 2008

A resistor network model for the horizontal AlInGaN LED was investigated, The parameters of the proposed model are extracted from the test dies and $350{\mu}m$ LED, The center of the P-area is the optimal position of a P-electrode by the simulation using the model. Also the optimal chip size of the LED for the new target current was investigated, Comparing the simulation and fabrication result, the errors for the forward voltage and the light power are average 0,02 V, 8 % respectively, So the proposed resistor network model with the linear forward voltage approximation and the exponential light power model are useful in the simulation for the horizontal AlInGaN LED.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.295-298
• /
• 1996

In this paper, a self-tuning optimal control algorithm is proposed to retain the optimal performance of an active suspension system, when the vehicle has some time varying parameters and parameter uncertainties. We consider a 2 DOF time-varying quarter car model which has the parameter variation of sprung mass, suspension spring constant and suspension damping constant. Instead of solving algebraic riccati equation on line, we propose a neural network approach as an alternative. The optimal feedback gains obtained from the off line computation, according to parameter variations, are used as the neural network training data. When the active suspension system is on, the parameters are identified by the recursive least square method and the trained neural network controller designer finds the proper optimal feedback gains. The simulation results are represented and discussed.

• International Journal of Control, Automation, and Systems
• /
• 제5권5호
• /
• pp.515-525
• /
• 2007

In this paper, we develop a co-design methodology of stochastic optimal controllers and network parameters that optimizes the overall quality of control (QoC) in networked control systems (NCSs). A new dynamic model for NCSs is provided. The relationship between the system stability and performance and the sampling frequency is investigated, and the analysis of co-design of control and network parameters is presented to determine the working range of the sampling frequency in an NCS. This optimal sampling frequency range is derived based on the system dynamics and the network characteristics such as data rate, time-delay upper bound, data-packet size, and device processing time. With the optimal sampling frequency, stochastic optimal controllers are designed to improve the overall QoC in an NCS. This co-design methodology is a useful rule of thumb to choose the network and control parameters for NCS implementation. The feasibility and effectiveness of this co-design methodology is verified experimentally by our NCS test bed, a ball magnetic-levitation (maglev) system.

• 한국항해학회지
• /
• 제25권4호
• /
• pp.323-333
• /
• 2001

This paper presents a decision making model for the cruise ship management. A network based optimization model has been developed for a single cruise ship operation. It gives optimal itinerary patterns over the planning period for the cruise ship managers wanting to maximize profit from the cruise ship operation. A network solution method to find the optimal solution is also developed. This network model can be equivalently transformed into a linear programming model, which makes the implementation of the model quite practical however complicated the given set of possible itineraries may be. The ship scheduling network developed in this study can also be used as a general framework to describe all possible cruise ship itineraries the cruise ship manager can figure out.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제13권1호
• /
• pp.22-30
• /
• 2005

The purpose of this study is to present a method to determine the optimal stop time of HVAC using the Artificial Neural Network model, which is one of the learning methods. For this, the performance of determining the stop time of HVAC for unexperienced learning data was evaluated, and time interval for measurement of input data and permissible error needed for practical application of ANN model were presented using the results from daily simulation.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.137-143
• /
• 2019

As the performance of computers increases, the use of deep learning, which has faced technical limitations in the past, is becoming more diverse. In many fields, deep learning has contributed to the creation of added value and used on the bases of more data as the application become more divers. The process for obtaining a better performance model will require a longer time than before, and therefore it will be necessary to find an optimal model that shows the best performance more quickly. In the artificial neural network modeling a tuning process that changes various elements of the neural network model is used to improve the model performance. Except Gride Search and Manual Search, which are widely used as tuning methods, most methodologies have been developed focusing on heuristic algorithms. The heuristic algorithm can get the results in a short time, but the results are likely to be the local optimal solution. Obtaining a global optimal solution eliminates the possibility of a local optimal solution. Although the Brute Force Method is commonly used to find the global optimal solution, it is not applicable because of an infinite number of hyper parameter combinations. In this paper, we use a statistical technique to reduce the number of possible cases, so that we can find the global optimal solution.

• 컴퓨터교육학회논문지
• /
• 제5권3호
• /
• pp.27-35
• /
• 2002

대학의 정보화 예산을 체계적으로 편성하기 위하여 대학의 전산자원중에서 중요한 PC와 소프트웨어 관리 및 활용에 대한 모델과 네트워크의 적정 속도에 대한 모델을 제안한다. 보유 PC의 활용도 증진을 위한 대책, PC 유지 보수의 문제점과 대책, PC의 효율적인 확충과 교체 방안, 소프트웨어 구입과 효율적인 활용방안을 제안한다. 또한 정보 시스템의 마스터플랜 수립의 핵심부분인 네트워크 환경과 관리를 위한 적정한 모델을 제안한다. 네트워크를 내부망과 외부망으로 구분하여 네프워크의 적정 속도를 산정하기 위한 수석모델을 제안한다. 그리고 대학이라는 조직의 특성을 살리고 보안을 유지할 수 있는 방안을 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 하계학술대회 논문집 A
• /
• pp.51-53
• /
• 1993

This paper proposes a design of the tracking controller using artificial neural network and the compare the result with a result of optimal controller. In practical use, conventional Optimal controller has some limits. First, optimal controller can be designed only for linear system. Second, for many systems state observation is difficult or sometimes impossible. But the controller using artificial neural network does not need mathmatical model of the system including state observation, so it can be used for both linear and nonlinear system with no additional cost for nonlinearity. Designed multi layer neural network controller is composed of two parts, feedforward controller gives a steady state input & feedback controller gives transient input via minimizing the quadratic cost function. From the comparison of the results of the simulation of linear & nonlinear plant, the plant controlled by using neural network controller shows the trajectory similar to that of the plant controlled by an optimal controller.

• 한국수자원학회논문집
• /
• 제32권1호
• /
• pp.71-81
• /
• 1999

본 연구의 목적은 유전자 알고리즘 최적화기법을 이용하여 설계기준에 합당한 제약조건을 고려한 최소경비의 관망시스템의 설계를 목적으로 한다. 수리학적 제약조건들은 수리모의프로그램(KYPIPE)과 연계하여 가능해 영역을 수시로 검증하였다. 유전자 알고리즘은 비교적 새로운 최적화기법이다. 유전자 알고리즘은 매우 강력한 탐색능력을 가지고 있으며 특히 비선형 문제를 해결하는데 탁월한 성능을 가진다고 알려져 있다. 유전자 알고리즘은 계산결과로 제시되는 결정변수인 관경은 연속적인 수치가 아닌 이산적인 규격의 표준관경인 상업용 관경으로 제시되며 펌프용량까지 최적화시키는 효율적인 최적설계를 도모하고자 한다. 본 모형은 가상 및 실제 관망시스템에 적용하였다. 그 중 하나는 많은 다른 연구자들에 의한 간단한 관망에 사용된 논문들로부터 채택하였다. 그 결과의 비교는 이 연구에서 개발된 모형의 적합성을 보여준다. 또한, 본 모형은 최적펌프용량도 결정할 수 있으며 그 적용성을 검증하기 위하여 고양시에 적용시켜 보았다. 개발된 모형은 비교적 간단한 방법으로 관망시스템의 최적설계에 성공적으로 적용시킬 수 있음이 판명되어져 왔다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2873-2875
• /
• 2005

The optimal structure of the conventional Fuzzy Polynomial Neural Networks (FPNN)[3] depends on experience of designer. For the conventional Fuzzy Polynomial Neural Networks, input variable number, number of input variable, number of Membership Functions(MFs) and consequence structures are selected through the experience of a model designer iteratively. In this paper, we propose the new design methodology to find the optimal structure of Fuzzy Polymomial Neural Network by using Genetic Algorithms(GAs)[4, 5]. In the sequel, It is shown that the proposed Advanced Genetic Algorithms based Fuzzy Polynomial Neural Network(Advanced GAs-based FPNN) is more useful and effective than the existing models for nonlinear process. We used Medical Imaging System(MIS)[6] data to evaluate the performance of the proposed model.