Ship Motion-Based Prediction of Damage Locations Using Bidirectional Long Short-Term Memory
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.
Abstract
The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.
참고문헌 (19)
- Bertheussen Karolius, K, "Risk-based positioning of flooding sensors to reduce prediction uncertainty of damage survivability", Proceedings of the 13th International Conference on the Stability of Ships and Ocean Vehicles, Kobe (2018)
- Calabrese, F, "A knowledge-based decision support system for shipboard damage control", Expert Systems with Applications, 39(9), pp.8204~8211 (2012)[DOI]
- DNV GL, "Rules for classification ships-Part 3 Hull – Chapter 15 Stability" (2017), Det Norske Veritas
- Hu, L. F, "AM–H method-based decision support system for flooding emergencies onboard warship", Ocean Engineering, 58, pp.192~200 (2013)[DOI]
- Hu, L. F, "Genetic algorithm-based counter-flooding decision model for damaged warship", International Shipbuilding Progress, 62(1–2), pp.1~15 (2015)[DOI]
- IMO, "Revised Interim guidelines for the approval of alternative methods of design and construction of oil tankers under Regulation 13F (5) of Annex 1 of MARPOL 73", 78. Resolution MEPC, 110(49), 2003
- Karolius, K. B, "Risk-based, sensor-fused detection of flooding casualties for emergency response", Ships and Offshore Structures, 16(5), pp.449~478 (2021)[DOI]
- Kim, C, "Design and performance analysis of 1D-CRNN based fault detection system for naval vessel", Master, pp.2020
- Korea Research Institute of Ships & Ocean Engineering (KRISO)., "Development of marine casualty initial response and salvage technical support system" (2017), KRISO
- Lee, D, "Knowledge-based system for safety control of damaged ship", Knowledge-based systems, 19(3), pp.187~191 (2006)[DOI]
- Lee, G. J, "Dynamic orifice flow model and compartment models for flooding simulation of a damaged ship", Ocean Engineering, 109, pp.635~653 (2015)[DOI]
- 노영단, "A Text Content Classification Using LSTM For Objective Category Classification", 한국컴퓨터정보학회논문지, 26(5), pp.39~46 (2021), 한국컴퓨터정보학회[DOI]
- Park, M. K, "A symptom recognition method of diseases for senior user based on language odel", Proceedings of the Korea Information Processing Society Conference, pp.461~463 (2020)
- Ruponen, P, "Flooding prediction onboard a damaged ship", Proceedings of the 11th International Conference on the Stability of Ships and Ocean Vehicles (2012)
- Ruponen, P, "A method for breach assessment onboard a damaged passenger ship", Applied Ocean Research, 64, pp.236~248 (2017)[DOI]
- Son, H. Y, "Prediction of flooded compartment damage locations in ships by using spectrum analysis of ship motions in waves", Journal of Marine Science and Engineering, 10(1), pp.17~ (2021)[DOI]
- Varela, J. M, "A virtual environment for decision support in ship damage control", IEEE Computer Graphics and Applications, 27(4), pp.58~69 (2007)[DOI]
- Varela, J. M, "On-board decision support system for ship flooding emergency response", Procedia Computer Science, 29, pp.1688~1700 (2014)[DOI]
- Varela, J. M, "3D simulation of ship motions to support the planning of rescue operations on damaged ships", Procedia Computer Science, 51, pp.2397~2405 (2015)[DOI]