Local ice load estimation using LSTM-based missing value imputation for strain gauge data in icebreaking vessels
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study investigates a method for estimating the missing strain data from hull-mounted strain gauges during ice collisions, focusing on the icebreaking research vessel (IBRV) Araon. Strain gauges installed on the internal partition walls of the vessel are used to measure the hull response to ice loads encountered during operations in polar regions. Annual research efforts aim to estimate the local ice load on the hull; however sensor data are often missing values, making accurate estimations challenging. These missing values disrupt the strain calculation, which relies on an influence coefficient matrix derived from multidirectional forces and ice impact dy-namics. Simple interpolation methods such as mean substitution or regression analysis are insufficient because of the complex and multidirectional nature of sea ice collisions. To address this issue, we propose a Long Short-Term Memory (LSTM)-based interpolation method. LSTM models are well-suited to this task because of their ability to handle long-term dependencies, mitigate gradient loss issues, and effectively process time-series data of varying lengths. The proposed approach demonstrated enhanced accuracy in estimat-ing missing strain data, offering a robust solution for analyzing hull-ice interactions in extreme environments.
Abstract
This study investigates a method for estimating the missing strain data from hull-mounted strain gauges during ice collisions, focusing on the icebreaking research vessel (IBRV) Araon. Strain gauges installed on the internal partition walls of the vessel are used to measure the hull response to ice loads encountered during operations in polar regions. Annual research efforts aim to estimate the local ice load on the hull; however sensor data are often missing values, making accurate estimations challenging. These missing values disrupt the strain calculation, which relies on an influence coefficient matrix derived from multidirectional forces and ice impact dy-namics. Simple interpolation methods such as mean substitution or regression analysis are insufficient because of the complex and multidirectional nature of sea ice collisions. To address this issue, we propose a Long Short-Term Memory (LSTM)-based interpolation method. LSTM models are well-suited to this task because of their ability to handle long-term dependencies, mitigate gradient loss issues, and effectively process time-series data of varying lengths. The proposed approach demonstrated enhanced accuracy in estimat-ing missing strain data, offering a robust solution for analyzing hull-ice interactions in extreme environments.
참고문헌 (30)
- S. -R. Cho, "Improvement of influence coefficient matrix for local ice load estimation on icebreaking research vessel ARAON", Journal of the Society of Naval Architects of Korea, 58(5), pp.330~338 (2021)
- J. -C. Kim, "Study on auto-mated imputation of missing sections for digital data pre-processing", Journal of Multimedia, 24(2), pp.245~254 (2021)
- C. -G. Lee, "Prediction of missing data and sensor fault detection using multivariate statistical analysis", Korean Chemical Engineering Research, 45(1), pp.87~92 (2007)
- Y. Li, "Nearest neighbor imputation using spatial-temporal correlations in wireless sensor networks", Information Fusion, 15, pp.64~79 (2014)
- H. -S. Kim, "Missing value estimation and anomaly detection framework for semiconductor manufac-turing data using generative adversarial networks", Journal of Korean Intelligent Systems Society, 28(4), pp.393~400 (2018)
- Y. -N. Han, "Robust and explainable smart meter data missing value imputation technique", Journal of Korean Institute of Electronic Com-merce, 27, pp.21~43 (2022)
- S. -H. Jung, "Study on machine learning-based automatic correction and analy-sis prediction model for data missing sections", Journal of Multimedia, 25(2), pp.257~268 (2022)
- Q. Suo, "Recurrent imputation for multivariate time series with missing values", Proceedings of the 2019 IEEE International Conference on Healthcare Informatics (ICHI), pp.1~3 (2019)
- A. S. Dhevi, "Imputing missing values using Inverse Dis-tance Weighted Interpolation for time series data", Pro-ceedings of the 2014 Sixth International Conference on Ad-vanced Computing (ICoAC), pp.255~259 (2014)
- B. Al-Helali, "A new im-putation method based on genetic programming and weighted KNN for symbolic regression with incomplete data", Soft Computing, 25(8), pp.5993~6012 (2021)
- W. -C. Lin, "Missing value imputation: A re-view and analysis of the literature (2006–2017)", Artificial Intelligence Review, 53(2), pp.1487~1509 (2020)
- S. -R. Cho, "Modification of local ice load estimation based on field measurements in the Arctic Ocean for icebreaking research vessel ARAON", Journal of Ocean Engineering, 33(2), pp.161~167 (2019)
- "Overfitting and underfitting"[URL]
- T. W. Liao, "Clustering of time series data—a survey", Pat-tern Recognition, 38(11), pp.1857~1874 (2005)
- F. Murtagh, "Algorithms for hierarchical clustering: an overview, II", Wiley Interdisciplinary Re-views: Data Mining and Knowledge Discovery, 7(6), pp.e1219~ (2017)
- C. Van Steen, "Localization and characterization of corrosion damage in reinforced concrete by means of acoustic emission and X-ray computed tomography", Construction and Building Ma-terials, 197, pp.21~29 (2019)
- "Decision Tree vs. Random Forest – Which Algorithm Should you Use?"[URL]
- "Practical Guide to Outlier Detection Methods"[URL]
- Z. Chen, "Analyzing and modeling inter-sensor relationships for strain monitoring data and missing data imputation: a copula and functional data-analytic ap-proach", Structural Health Monitoring, 18(4), pp.1168~1188 (2019)
- "Understanding Long Short-Term Memory (LSTM)"[URL]
- H. -B. Heo, "Signal separation and continuous missing value imputation of strain gauge in the icebreaker sensor system", Applied Ocean Research, 141, pp.103711~ (2024)
- J. Smith, "Graph neural networks for restoring incomplete environmental sensor networks by modeling spatial correlations", Environmental Data Sci-ence, 10(3), pp.45~58 (2022)
- J. Doe, "Transformer-based meth-ods for missing value imputation in time-series data", Ap-plied Intelligence, 51(7), pp.3623~3639 (2021)
- M. Kim, "A novel transformer archi-tecture for weather forecasting and data imputation", IEEE Access, 11, pp.178340~178352 (2023)
- S. Lee, "Variational autoencoders for structural health monitoring: A generative approach to data imputation", Smart Structures and Systems, 29(5), pp.977~988 (2022)
- A. Johnson, "Generative models for medical imaging data reconstruction: A variational autoen-coder approach", IEEE Transactions on Medical Imaging, 42(6), pp.1512~1523 (2023)
- J. Chung, "Long short-term memory networks in sensor data reconstruction and speech recognition", Neural Networks and Learning Sys-tems, 37(4), pp.512~526 (2021)
- M. Khan, "Applying LSTM for struc-tural health monitoring data imputation: A review of meth-odologies and challenges", Journal of Structural Health Monitoring, 15(4), pp.683~698 (2022)
- A. Rahman, "LSTM-based approaches for healthcare data imputation: Ensuring robust patient monitoring", IEEE Journal of Biomedical and Health Infor-matics, 27(9), pp.3718~3729 (2023)