• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.6
• /
• pp.1010-1016
• /
• 2004

In this paper, a scheme for estimating the parameters of solar cells and a NN-based emulator for predicting the maximum power point are presented. The diode model with series and shunt resistors is used to estimate parameters highly affecting its V-I characteristic curve and both a real-coded genetic algorithm and the model adjustment technique are employed. For implementing the emulator, a multi-layered neural network incorporating with the BP algorithm is used. A set of simulation works using both field data and generated data are carried out to demonstrate the effectiveness of the proposed method.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2003.04a
• /
• pp.177-184
• /
• 2003

The purposes of this study are to develop the real coding genetic algorithm and to obtain the shape optimization of a cable domes by using this scheme. Generally, the structural performance of the cable dome is influenced very sensitively by prestress, geometry and length of the mast because of flexible structures. So, it is very important to decide the optimum shape to get maximum stiffness of cable domes. We use the two models to verify the usefulness of this algorithm for shape optimization and analyze the roof system of Seoul olympic gymnastic arena as one analytical model of practical structures

• Journal of Navigation and Port Research
• /
• v.32 no.10
• /
• pp.851-856
• /
• 2008

Construction of large-scale container ports with the productivity improvements in container cranes shortened time of staying port to increase the level of service it harbors efforts accelerated. About container crane system exerted on the input, which is designed to look good performance considering the states feedback control system. The states observer designed of container cranes state variables that are expected to measurement noise or particular measurement signal. In the status of existing research, the feedback gain matrix and the state observer gain matrix are searched by being separated solving. But the feedback gain matrix and the state observer gain matrix are searched by RCGAs at once that be used robust search method in this paper.