• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6B
• /
• pp.859-866
• /
• 2010

Digital vessels can occur large a disaster at sea because vessels in fire and collision in case of certain unforeseen circumstances. In this paper, We propose digital vessel context monitoring system through risk analysis. We propose environment information analysis system using wireless sensor that have to acquire marine environment and context of marine digital vessel. For conducting simulation, we chose 300 data sets to train the neural network. As a result, we obtained about 96% accuracy for fire risk context and we obtained 88.7% accuracy for body of vessel risk context. To improve the accuracy of the system, we implement a FEC (Forward Error Correction) block. We implemented digital vessel context monitoring system that transmitted to diagnosis result in CDMA.

• Journal of the Korean Institute of Navigation
• /
• v.20 no.2
• /
• pp.1-13
• /
• 1996

Most of the ShipHandling Simulators of full-mission-bridge system need vast area to install and even PC-based maneuvering simulators are often equipped with Steering Wheel or Engine Telegraphe etc. of data input interface, which necessarily makes the user face with excessive financial burden. These have been one of the obstacles for the officers, captains, pilots and students in access to maneuvering simulation whenever they want to try it in advance prior to actual ship maneuvering. Subsequently, all the officers and captains come to have little chances to train themselves until they arualified as a pilot after a long period of time of realship maneuvering practice on board, which means they have to control they have to control their own ship at sea without clear understanding on her maneuverability when they are forced to do it on the way. And these lack of capability for maneuvering have used so often to result in marine casualties of collision with other ships or pier facilities while maneuvering in harbor. To prevent those accidents by means of enhancing their maneuvering ability, PC-based DeskTop Simulator that allows anyong to access readily at anytime is needed and in conformation to such demand this simulator has been developed. The Software this simulator written in Turbo Pascal Ver. 5.0 has adopted MMG mathmatical model theoretically in part and also it was designed to make it possible that all numeric data inputs and outputs with graphic presentation for maneuvering operation be carried out just only with keyboard and monitor console. With the Simulation software, all the officers, captains, pilots and even students who has a proper computer at hand are expected to be able to make an attempt to simulate the maneuvering of their ownship or any other types of them at any port in which they want to do it.

• Structural Engineering and Mechanics
• /
• v.91 no.1
• /
• pp.75-86
• /
• 2024

In this paper, the porous metal PM-35 is proposed as the filler material of filled thin-walled tubes (FTTs), and a series of experimental study is conducted to investigate the dynamic behavior and energy absorption performance of PM-35 filled thin-walled tubes under impact loading. Firstly, cylinder solid specimens of PM-35 steel are tested to investigate the impact mechanical behavior by using the Split Hopkinson pressure bar set (SHP); Secondly, the filled thin-walled tube specimens with different geometric parameters are designed and tested to investigate the feasibility of PM-35 steel applied in FTTs by the orthogonal test. According to the results of this research, it is concluded that PM-35 steel is with the excellent characteristics of high energy absorption capacity and low yield strength, which make it a potential filler material for FTTs. The micron-sizes pore structure of PM-35 is the main reason for the macroscopic mechanical behavior of PM-35 steel under impact loading, which makes the material to exhibit greater deformation when subjected to external forces and obviously improve the toughness of the material. In addition, PM-35 steel core-filled thin-wall tube has excellent energy absorption ability under high-speed impact, which shows great application potential in the anti-collision structure facilities of high-speed railway and maglev train. The parameter V0 is most sensitive to the energy absorption of FTT specimens under impact loading, and the sensitivity order of different variations to the energy absorption is loading speed V0>D/t>D/L. The loading efficiency of the FTT is affected by its different geometry, which is mainly determined by the sleeve material and the filling material, which are not sensitive to changes in loading speed V0, D/t and D/L parameters.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.