• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.241-246
• /
• 2020

In this paper, we propose a neural network model to converge the marine electric propulsion system and deep learning algorithm to predict the DC/DC converter output current in the electric propulsion regeneration system and to predict the battery charge during regeneration. In order to experiment with the proposed neural network, the input voltage and current of the PCM were measured and the data set was secured on the prototype PCM board. In addition, in order to improve the learning results in the insufficient data set, the scale of the data set was increased through data fitting and its learning was executed further. After learning, the difference between the data prediction result of the neural network model and the actual measurement data was compared. The proposed neural network model effectively showed the prediction of battery charge according to changes in input voltage and current. In addition, by predicting the characteristic change of the analog circuit constituting the DC/DC converter through a neural network, it is determined that the characteristics of the analog circuit should be considered when designing the regeneration system.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2021.11a
• /
• pp.69-71
• /
• 2021

항로표지의 효율적 관리와 연계/수집 정보의 서비스를 위해 스마트 항로표지 정보협력시스템이 요구 되었고, 항로표지 관리, 선박 사용, 육상 정보 활용을 위해서는 서비스 플랫폼이 반드시 고려되어야 한다. IMO e-Navigation 전략 이행을 위해 16개의 해양 서비스가 식별되었고, 해양 서비스 개발을 목적으로 해양 서비스 정의, 기술표준 개발에 관한 표준이 개발되었으며, 정보 교환을 위한 S-100 데이터 모델 적용이 논의 되었다. 해양 서비스 플랫폼 개발과 관련하여 서비스 인증, 검색, 메시지 전송에 관한 MCP가 개발 되었으며, 서비스 플랫폼 평가에 관한 기준이 개발되었다. 본 연구에서는 스마트 항로표지 정보 서비스 플랫폼 개발을 위해 서비스 내역과 정보협력 시스템의 구조를 분석하고, IMO/IALA/IHO 국제기구의 최신 기준에 따른 해양 서비스 플랫폼 구축 방안을 제시 하였다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.958-963
• /
• 2023

Lately, there has been increasing research on the prediction of motion performance using artificial intelligence for the safe design and operation of ships. However, compared to conventional ships, research on small fishing boats is insufficient. In this paper, we propose a model that estimates the motion response essential for calculating the motion performance of small fishing boats using a deep neural network. Hydrodynamic analysis was conducted on 15 small fishing boats, and a database was established. Environmental conditions and main particulars were applied as input data, and the response amplitude operators were utilized as the output data. The motion response predicted by the trained deep neural network model showed similar trends to the hydrodynamic analysis results. The results showed that the high-frequency motion responses were predicted well with a low error. Based on this study, we plan to extend existing research by incorporating the hull shape characteristics of fishing boats into a deep neural network model.

• Aerospace Engineering and Technology
• /
• v.8 no.2
• /
• pp.1-7
• /
• 2009

The Geostationary Ocean Color Imager (GOCI) is under development to provide a monitoring of ocean-color around the Korean Peninsula from geostationary platforms. It is planned to be loaded on Communication, Ocean, and Meteorological Satellite (COMS) of Korea. In this study, the radiometric model of GOCI, which is constructed based on the functional model of sub-system, is introduced. Non-linearity for each channel is analyzed in terms of linear gain and nonlinear gain by using the radiometric model. The non-linearity characteristic is validated by using test data which have been achieved during ground test at payload level. The non-linearity $G^3$/b shows identical characteristic for all channels.

• Journal of Navigation and Port Research
• /
• v.47 no.4
• /
• pp.182-190
• /
• 2023

This study proposes a predictive model using XGBoost and SHapley Additive exPlanation (SHAP) to estimate fuel consumption in bulk carriers. Previous studies have also utilized ship engine data and weather data. However, they lacked reliability in predicted results and explanations of variables used in the fuel consumption prediction model implementation. To address these limitations, this study developed a predictive model using XGBoost and SHAP. It provides research background, scope, relevant regulations, previous studies, and research methodology. Additionally, it explains the data cleaning method for bulk carriers and verifies results of the predictive model.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.257-258
• /
• 2019

이 연구는 기 개발한 간이 선박조종 시뮬레이터의 조종성능 개선에 관한 것이다. 선박조종 시뮬레이터에서 모델선박의 조종성 지수는 임의로 정하는 것이 아니라 가능한 모델대상선박의 실제 움직임과 동등하거나 유사하게 설정되어야 한다. 선행연구에서는 이미 발표된 대학교 실습선(한바다호)의 선박조종 실선데이터를 기반으로 모델선박의 조종성 지수를 도출하였으나, 타각이 10°를 초과할 경우 네 종류의 실선시험 결과와 평균 17.9%의 상대오차가 발생하였다. 이에, 타각 10°, 20° 및 35°에서의 한바다호 조종성 지수에 대해 에르미트 보간을 이용하여 3차 다항식을 산출하고, 이를 모델선박에 적용하였다. 그 결과 타각 35° 이내의 전 구간에서 조종성능의 상대오차가 평균 13.7%에서 11.6%로 약 2.1% 개선됨을 확인하였다.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.358-366
• /
• 2023

This study aimed to provide a solution for improving ship collision alert of the 'accident vulnerable ship monitoring service' among the 'intelligent marine traffic information system' services of the Ministry of Oceans and Fisheries. The current ship collision alert uses a supervised learning (SL) model with survey labels based on large ship-oriented data and its operators. Consequently, the small ship data and the operator's opinion are not reflected in the current collision-supervised learning model, and the effect is insufficient because the alarm is provided from a longer distance than the small ship operator feels. In addition, the supervised learning (SL) method requires a large number of labeled data, and the labeling process requires a lot of resources and time. To overcome these limitations, in this paper, the classification model of collision alerts for small ships using unlabeled data with the semi-supervised learning (SSL) algorithms (Label Propagation and TabNet) was studied. Results of real-time experiments on small ship operators using the classification model of collision alerts showed that the satisfaction of operators increased.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.315-324
• /
• 2022

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.39-41
• /
• 2022

해양정보의 디지털화, e-Navigation 개념의 해양서비스 개발, 차세대 전자해도 도입, 자율운항선박 기술 개발 등 해양 분야의 주요 이슈에 대응하여 핵심 항해안전지원 시설인 항로표지 역할 변화가 요구되고 있다. 특히 국제항로표협회(IALA)의 해양자원명(MRN) 지침과 항로표지 정보교환 표준(S-201) 개발을 통해 항로표지 정보의 디지털화와 정보 서비스화를 강조하고 있으며, e-Navigation 개념의 해양 서비스 개발을 논의 중이다. 본 연구에서는 현행 항로표지 정보시스템 현황을 분석하고, 국가 연구개발 사업으로 추진 중인 스마트 항로표지 및 정보협력 시스템의 구조를 분석하였다. 또한 항로표지 기본 및 수집정보를 이용한 항로표지 정보 서비스 종류를 식별하고 서비스 운영개념을 제안하였다. 본 연구에서 제안하는 항로표지 정보 서비스 운영개념에 따라 항로표지 정보 서비스 센터 구축 및 국제 정보표준 개발 활동이 추진되어야 할 것으로 사료 된다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.127-134
• /
• 2021

In this study, an anomaly detection (AD) algorithm was implemented to detect the failure of a marine air compressor. A lab-scale experiment was designed to produce fault datasets (time-series electric current measurements) for 10 failure modes of the air compressor. The results demonstrated that the temporal pattern of the datasets showed periodicity with a different period, depending on the failure mode. An AD model with a convolutional autoencoder was developed and trained based on a normal operation dataset. The reconstruction error was used as the threshold for AD. The reconstruction error was noted to be dependent on the AD model and hyperparameter tuning. The AD model was applied to the synthetic dataset, which comprised both normal and abnormal conditions of the air compressor for validation. The AD model exhibited good detection performance on anomalies showing periodicity but poor performance on anomalies resulting from subtle load changes in the motor.