Ship motion identification model based on enhanced Bi-LSTM
ObjectiveAiming at the low prediction precision and poor adaptability of ship models based on the data-driven modeling strategy, an enhanced bi-directional long short-term memory (Bi-LSTM) model is proposed for the high-precision non-parametric modeling of ships. MethodsFirst, the feature extraction...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Chinese Journal of Ship Research
2025-02-01
|
| Series: | Zhongguo Jianchuan Yanjiu |
| Subjects: | |
| Online Access: | http://www.ship-research.com/en/article/doi/10.19693/j.issn.1673-3185.03740 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850045982442520576 |
|---|---|
| author | Haozhe ZHANG Zhibo YANG Xuguo JIAO Chengxing LÜ Peng LEI |
| author_facet | Haozhe ZHANG Zhibo YANG Xuguo JIAO Chengxing LÜ Peng LEI |
| author_sort | Haozhe ZHANG |
| collection | DOAJ |
| description | ObjectiveAiming at the low prediction precision and poor adaptability of ship models based on the data-driven modeling strategy, an enhanced bi-directional long short-term memory (Bi-LSTM) model is proposed for the high-precision non-parametric modeling of ships. MethodsFirst, the feature extraction of the bi-directional time dimension is realized using bi-directional long short-term memory (Bi-LSTM) neural networks. On this basis, the spatial dimension features of the one-dimensional convolutional neural network （1D-CNN） extraction sequence are designed. Then, a multi-head self-attention (MHSA) mechanism is used to deal with the sequence from multiple angles. Finally, using the navigation data of KLVCC2 ships, the prediction effects of the enhanced Bi-LSTM model are compared with those of the Support Vector Machine (SVM), Gate Recurrent Unit (GRU), and long short-term memory (LSTM) models.ResultsThe Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) performance indicators of the enhanced Bi-LSTM model in the test set are lower than 0.015 and 0.011 respectively, and the coefficient of determination（R2）is higher than 0.99913, demonstrating prediction accuracy significantly higher than that of the SVM, GRU, and LSTM models.ConclusionThe proposed enhanced Bi-model has excellent generalization performance and excellent prediction stability and precision, and effectively realizes ship motion identification. |
| format | Article |
| id | doaj-art-fe28a5cd32ae4f05b5911ac5c3e0318e |
| institution | DOAJ |
| issn | 1673-3185 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Editorial Office of Chinese Journal of Ship Research |
| record_format | Article |
| series | Zhongguo Jianchuan Yanjiu |
| spelling | doaj-art-fe28a5cd32ae4f05b5911ac5c3e0318e2025-08-20T02:54:35ZengEditorial Office of Chinese Journal of Ship ResearchZhongguo Jianchuan Yanjiu1673-31852025-02-01201768410.19693/j.issn.1673-3185.03740ZG3740Ship motion identification model based on enhanced Bi-LSTMHaozhe ZHANG0Zhibo YANG1Xuguo JIAO2Chengxing LÜ3Peng LEI4School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, ChinaObjectiveAiming at the low prediction precision and poor adaptability of ship models based on the data-driven modeling strategy, an enhanced bi-directional long short-term memory (Bi-LSTM) model is proposed for the high-precision non-parametric modeling of ships. MethodsFirst, the feature extraction of the bi-directional time dimension is realized using bi-directional long short-term memory (Bi-LSTM) neural networks. On this basis, the spatial dimension features of the one-dimensional convolutional neural network （1D-CNN） extraction sequence are designed. Then, a multi-head self-attention (MHSA) mechanism is used to deal with the sequence from multiple angles. Finally, using the navigation data of KLVCC2 ships, the prediction effects of the enhanced Bi-LSTM model are compared with those of the Support Vector Machine (SVM), Gate Recurrent Unit (GRU), and long short-term memory (LSTM) models.ResultsThe Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) performance indicators of the enhanced Bi-LSTM model in the test set are lower than 0.015 and 0.011 respectively, and the coefficient of determination（R2）is higher than 0.99913, demonstrating prediction accuracy significantly higher than that of the SVM, GRU, and LSTM models.ConclusionThe proposed enhanced Bi-model has excellent generalization performance and excellent prediction stability and precision, and effectively realizes ship motion identification.http://www.ship-research.com/en/article/doi/10.19693/j.issn.1673-3185.03740identification (control systems)non-parametric modellingone-dimensional convolutional neural network (1d-cnn)bi-directional long short-term memory （bi-lstm）neural networkmulti-head self-attention mechanism |
| spellingShingle | Haozhe ZHANG Zhibo YANG Xuguo JIAO Chengxing LÜ Peng LEI Ship motion identification model based on enhanced Bi-LSTM Zhongguo Jianchuan Yanjiu identification (control systems) non-parametric modelling one-dimensional convolutional neural network (1d-cnn) bi-directional long short-term memory （bi-lstm）neural network multi-head self-attention mechanism |
| title | Ship motion identification model based on enhanced Bi-LSTM |
| title_full | Ship motion identification model based on enhanced Bi-LSTM |
| title_fullStr | Ship motion identification model based on enhanced Bi-LSTM |
| title_full_unstemmed | Ship motion identification model based on enhanced Bi-LSTM |
| title_short | Ship motion identification model based on enhanced Bi-LSTM |
| title_sort | ship motion identification model based on enhanced bi lstm |
| topic | identification (control systems) non-parametric modelling one-dimensional convolutional neural network (1d-cnn) bi-directional long short-term memory （bi-lstm）neural network multi-head self-attention mechanism |
| url | http://www.ship-research.com/en/article/doi/10.19693/j.issn.1673-3185.03740 |
| work_keys_str_mv | AT haozhezhang shipmotionidentificationmodelbasedonenhancedbilstm AT zhiboyang shipmotionidentificationmodelbasedonenhancedbilstm AT xuguojiao shipmotionidentificationmodelbasedonenhancedbilstm AT chengxinglu shipmotionidentificationmodelbasedonenhancedbilstm AT penglei shipmotionidentificationmodelbasedonenhancedbilstm |