• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.336-339
• /
• 2006

모델 예측 제어 시스템은 이동 제어 구간에서 원하는 출력과 예측된 출력의 차이를 최소화하는 현재의 제어 입력을 적용하는 방식을 사용한다. 제약조건이 있는 경우이거나 비선형 시스템 문제의 경우는 주어진 함수를 최소화하는 최적화 문제를 풀기가 힘들다. 본 논문에서는 모델 예측 제어 시스템의 최적화 문제를 실수 코딩 유전 알고리즘을 이용하여 효율적으로 구할 수 있음을 보인다. 또한 실수코딩 유전알고리즘이 여러 가지 면에서 디지털코딩 유전알고리즘보다 더 자연스럽고 유리함을 모의실험을 통해 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.125-129
• /
• 2010

본 연구에서는 실수 코딩을 사용하는 유전 알고리즘의 문제공간이 n차원 구면으로 제한된 경우에 사용 할 교배 연산자와 변이 연산자를 제안하고, 이를 실제로 사용한 실험 결과를 제시한다. n차원 실수 공간에서 일반적으로 사용되는 연산자를 n차원 구면에 사영하는 방법을 사용하였으며, 해의 범위가 제한된 경우에 사용할 해의 수선 방법도 제안하였다. 제안된 연산자를 사용하며 몇 가지 최적화 문제를 푸는 실험을 한 결과 평균 오차율 2.0%내에서 최적해를 구함을 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.562-567
• /
• 2006

Model Predictive Control(MPC) system uses the current input which minimizes the difference between the desired output and the estimated output in the receding horizon scheme. In many cases (for example, system with constraints or nonlinear system), however, it is not easy to find the optimal solution to the above problem. In this paper, we show that real number coding genetic algorithm can be used to solve the optimal problem for MPC effectively. Also, we show by simulation that the real coding algorithm is mote natural and advantageous than the digital coding one.

• Journal of Navigation and Port Research
• /
• v.31 no.3 s.119
• /
• pp.247-252
• /
• 2007

The container crane is one of the most important equipments at container terminal. If its working time in cycle could be reduced then container terminal efficiency and service level can be increased. So there are many i1forts to reduce working time of container cranes. It means how to design the controller with good performance which has small overshoot and swing motion of container crane. We, in this paper, present a state feedback controller based on LQ theory incorporating a RCGA which means real-coded genetic algorithm RCGA can search state feedback gains under given objective function. A set of simulation works are carried out in order to prove the control effectiveness of the proposed methods.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.399-404
• /
• 2006

The container crane is one of the most important equipment in container terminal. If its working time in cycle could be reduced then container terminal efficiency and service level can be increased. So there are many efforts to reduce working time of container crane. It means how to design the controller with good performance which has small overshoot and swing motion of container crane. We, in this paper, present a state feedback controller not based on LQ theory but RCGA which means real-coded genetic algorithms. RCGA can search state feedback gains in given objective function. several cases of simulations are carried out in order to prove the control effectiveness of the proposed methods.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.11a
• /
• pp.111-116
• /
• 2004

In this paper, parameters of a given DC motor system are estimated using the model adjustment technique and the real coded genetic algorithm(RCGA) technique. A number of tuning methods, based on experience and experiment, such as Ziegler-Nichols, Cohen-Coon, IMC, L-ITAE Method have been proposed to obtain parameters for the PID controller. This paper proposes estimating parameters of PID controller using RCGA. The performance of the proposed algorithm is demonstrated through simulations and experiences.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.515-521
• /
• 2007

To increase the stevedore efficiency and service level at container terminal, it is essential to reduce working time of container crane which has a bottle neck in the logistic flow of container. The working speed and safety are required to be improved by controlling the movement of the trolley as quick as possible without big overshoot and any residual swing motion of container in the vicinity of target position. This paper presents optimal state feedback control using RCGAs in the case of existing constrained conditions

• Journal of Power System Engineering
• /
• v.13 no.4
• /
• pp.68-73
• /
• 2009

The mathematical model has a different response character with the real system because this mathematical model has the modeling errors and the imprecise value of system's parameters. Therefore to find the value of system parameters as possible as near by real value in the model is necessary to design the controlled system. This study concern about the identification method to estimate the parameter for the magnetic bearing system with RCGA(Real Coded Genetic Algorithm). Firstly, we will get the mathematical model from the current amplifier circuit and the magnetic bearing system. Secondly we will get the step response data in this circuit and system. Finally, we will estimate the unknown parameter's value from the data.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.284-290
• /
• 2003

It is very important to minimize the weight of shaft from the viewpoint of economics and manufacture. For minimizing effectively the diameter of shaft in torsional shafting, authors developed computer program using the real-coded genetic algorithm which is one of optimizing techniques and based on real coding representation of genetic algorithm. In order to confirm the accuracy and effectiveness of the developed computer program, the computational results by the developed program were compared with those of conventional strength, stiffness and vibration designs for a generator shafting.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.5
• /
• pp.599-605
• /
• 2007

This paper presents a method for identifying various systems based on input-output data and a real-coded genetic algorithm(RCGA). The advantages of this technique are, first, it is not dependent on the deterministic or stochastic nature of the systems and, second, the globally optimized models for the original systems can be identified without the need of a differentiable measure function of linearly separable parameters. Under suitable hypotheses, the estimation error is shown to converge in probability to zero. The performance of the proposed algorithm is demonstrated through several simulations.