• Journal of Ocean Engineering and Technology
• /
• v.25 no.4
• /
• pp.59-65
• /
• 2011

In structural health monitoring (SHM) using electro-mechanical impedance signatures, it is a critical issue for extremely large structures to extract the best damage diagnosis results, while minimizing unknown environmental effects, including temperature, humidity, and acoustic vibration. If the impedance signatures fluctuate because of these factors, these fluctuations should be eliminated because they might hide the characteristics of the host structural damages. This paper presents a long-term SHM technique under an unknown noisy environment for tidal current power plant structures. The obtained impedance signatures contained significant variations during the measurements, especially in the audio frequency range. To eliminate these variations, a continuous principal component analysis was applied, and the results were compared with the conventional approach using the RMSD (Root Mean Square Deviation) and CC (Cross-correlation Coefficient) damage indices. Finally, it was found that this approach could be effectively used for long-term SHM in noisy environments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.334-337
• /
• 2010

디지털 선박 운행시 예기치 못한 상황에 의한 선박 내 화재나 충돌 등 긴급 상황 발생 시에 대형의 해난 사고가 발생할 수 있다. 이에 본 논문에서는 선박 상태를 자체 진단하여 모니터링하고 위험 분석을 통해 관리할 수 있는 시스템을 구현하고자 한다. 해양 디지털선박의 환경, 상황을 수집할 수 있는 무선 센서를 이용하여 수집된 환경 정보를 분석하는 시스템을 제안하였으며, 센싱된 데이터를 분석하기 위하여 역전파 신경망을 설계하였다. 300개의 데이터 집합을 사용하여 역전파 신경망을 실험한 결과 약 96%의 정확도를 가졌다. 제안된 시스템은 하드웨어 (UStar-2400 ISP, UStar-2400, Wireless sensors) 부분과 소프트웨어 부분(User Interface module)으로 구성되며 소프트웨어 부분은 HOST PC에 삽입된다. 그리고 시스템의 정확도를 개선하기 위하여 전방향 에러 정정 시스템(LDPC)을 구현하였고 진단된 결과는 CDMA 방식으로 전송하여 해양디지털선박 감지 모니터링 시스템을 구현했다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.276-283
• /
• 2018

Climate changes consistently cause coastal accidents such as coastal flooding, so the studies on monitoring the marine environments are progressing to prevent and reduce the damage from coastal accidents. In this paper, we propose a new method to predict the sea level which can be applied to coastal monitoring systems to observe the variation of sea level and warn about the dangers. Existing sea level models are very complicated and need a lot of tidal data, so they are not proper for real-time prediction systems. On the other hand, the proposed algorithm is very simple but precise in short period such as one or two hours since we use the measured data from the sensor. The proposed method uses Kalman filter algorithm for harmonic analysis and double exponential smoothing for additional error correction. It is shown by experimental results that the proposed method is simple but predicts the sea level accurately.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.891-898
• /
• 2017

Climate changes consistently cause coastal accidents such as coastal flooding, so the studies on monitoring the marine environments are progressing to prevent and reduce the damage from coastal accidents. In this paper, we propose a new method to estimate the sea level which can be applied to the tidal sensors to monitor the variation of sea level. Existing sea level models are very complicated and need a lot of tidal data, so they are not proper for tidal sensors. On the other hand, the proposed algorithm is very simple but precise since we use the measured data from the sensor to estimate the sea level value in short period such as one or two hours. It is shown by experimental results that the proposed method is simple but predicts the sea level accurately.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.225-233
• /
• 2023

This paper implements a system that monitors human body lifting information in the event of a marine accident. The monitoring system performs ultrasonic communication through a lifting device controller that transmits underwater environment information, and LoRa communication is performed on the water to provide GPS information within 10 km to the control center or mother ship. The underwater lifting controller transmits pneumatic sensor, gyro sensor, and temperature sensor information. In an environment where the underwater conditions increase by one atmosphere of water pressure every 10m in depth, and the amount of air in the instrument decreases by half compared to land, a model of a 60kg underwater mannequin is used. Using one 38g CO2 cartridge in the lifting appliance SMB(Surface Maker Buoy), carry out a lifting appliance discharge test based on the water level rise conditions within 10 sec. Underwater communication constitutes a data transmission environment using a 2,400-bps ultrasonic sensor from a depth of 40m to 100m. The monitoring signal aims to ensure the safety and safe human structure of the salvage worker by providing water depth, water temperature, and directional angle to rescue workers on the surface of the water.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1203-1213
• /
• 2018

In Arctic and Antarctic ocean, remote sensing is the most effective observation for environmental changes due to the inaccessibility of the regions. Even though satellite, UAV (Unmanned Aerial Vehical) are well known remote sensing platforms, and research vessel also used for automatic measurement on the regions, varied environment of Polar regions require time series and wide coverage of data. Especially, in high latitude, apply an optical satellite remote sensing is not easy due to low sun altitude. In this paper, we introduce an operation of hyper-spectrometer (HyperSAS/Satlantic inc.) which is mounted on Ice Breaker Research Vessel ARAON of Korea Polar Research Institute since 2010, to acquire an above water reflectance atomatically through every research cruise on Arctic and Antarctic ocean and transit both regions. In addition to, auxiliary data for the remotely acquired data, in situ water sampling were also obtained. The above water reflectance and in situ water sampling data are continuously acquired since 2010 will contribute to improve an Ocean Color algorithm in the high latitude and help to understand ocean reflectances over from high latitude through low latitude. Preliminary result from above water reflectance showed characteristics of Arctic ocean and Antarctic Ocean and used to develop algorithms for estimating various ocean factors such as chlorophyll and suspended sediment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6A
• /
• pp.399-408
• /
• 2011

Development of smart sensors for structural health monitoring and damage detection has been advanced remarkably in recent years. Nowadays fiber optic sensors, especially fiber Bragg grating (FBG) sensors, have attracted many researchers' interests for their attractive features, such as multiplexing capability, durability, lightweight, electromagnetic interference immunity. In this paper, a damage detection approach of jacket-type offshore structures by principal component analysis (PCA) technique using FBG sensors are presented. An experimental study for a tidal current power plant structure as one of the jacket-type offshore structures was conducted to investigate the feasibility of the proposed method for damage monitoring. It has been found that the PCA technique can efficiently eliminate environmental effects from measured data by FBG sensors, resulting more damage-sensitive features under various environmental variations.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.4 no.4
• /
• pp.61-69
• /
• 2001

Recently, according to the rapid development of computer and electronic technology, most crude oil carriers adopt automated cargo handling system. But an excessive automation makes system so complicate that it could increase the Possibility of accidents due to human error. Although a cargo handling process is done by an expert, the potential of accidents by human factor lies through the whole cargo handling procedure and the current automated system lacks of the functionality to prevent a mis-operation and diagnose the abnormal status of the system. Because the oil concerned accident could be almost a disaster, the primary goal of system development should not be a fully automated system but be a perfectly safe system. This paper deals with the analysis and design of an expert system which can provide mariner with the operational guidance and the facility of crisis management by monitoring system's abnormal condition and human's mis-operation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.2A
• /
• pp.97-108
• /
• 2012

Dynamic responses were measured using long-term monitoring system for Uldolmok tidal current pilot power plant which is one of jacket-type offshore structures. Among the dynamic quantities, the tilt angle was chosen because the low frequency response components can be precisely measured by dynamic tiltmeter, and the natural frequencies and modal damping ratio were successfully identified using proposed LS-FDD (least squared frequency domain decomposition) method. And the effects of tidal height and tidal current velocity on the variation of natural frequencies and modal damping ratios were investigated in time and frequency domain. Also the non-parametric models were tested to model the relationship between tidal conditions and modal properties such as natural frequencies and damping ratios.