论文信息 - A Real-Time Prediction Method for Ship Heave Motion Using Conv-Bi-LSTM Model

A Real-Time Prediction Method for Ship Heave Motion Using Conv-Bi-LSTM Model

When the ship is sailing at sea, affected by wind, waves and other factors, it will produce a complex rocking motion, which has an impact on carrier-borne aircraft takeoff and land and cargo handover. In order to improve the safety of ship operation, a prediction model of ship heave motion was established based on Conv-Bi-LSTM neural network. The International Towing Tank Conference(ITTC) wave spectrum and Response Amplitude Operator (RAO) were used to generate the ship motion data with six degrees of freedom under three to six sea states. The prediction results of the proposed model are compared with those of the LSTM model, BP model, and Kalman model. And compared with the ordinary Kalman model, the mean absolute error(MAE) of the proposed algorithm has been improved by 44.03%, 53.57%, 61.08%, and 76.69% in sea states of 3 to 6. On this basis, a heave motion prediction model based on multi-feature information is designed. The results show that the prediction model based on Conv-Bi-LSTM has higher prediction accuracy and better adaptability to all sea states.

Ya Zhang | W. Gao | Shiwei Fan | Xiaofeng Wei | Baojin Ping

[1] Lei Li,et al. A New Method of Inland Water Ship Trajectory Prediction Based on Long Short-Term Memory Network Optimized by Genetic Algorithm , 2022, Applied Sciences.

[2] Dingjie Xu,et al. An EMD-SVR model for short-term prediction of ship motion using mirror symmetry and SVR algorithms to eliminate EMD boundary effect , 2020 .

[3] Wen Zheng,et al. Multi-step traffic flow prediction method based on the Conv1D + LSTM , 2020, 2020 Eighth International Conference on Advanced Cloud and Big Data (CBD).

[4] Wenyang Duan,et al. The input vector space optimization for LSTM deep learning model in real-time prediction of ship motions , 2020 .

[5] Sheng Dong,et al. A novel model to predict significant wave height based on long short-term memory network , 2020 .

[6] Abhishek Samanta,et al. A Review of Convolutional Neural Networks , 2020, 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE).

[7] Yong Yu,et al. A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures , 2019, Neural Computation.

[8] Bin Han,et al. Research on Real-Time Local Rainfall Prediction Based on MEMS Sensors , 2018, J. Sensors.

[9] S. Hochreiter,et al. Long Short-Term Memory , 1997, Neural Computation.

[10] Xiong Hu,et al. Short-Term Prediction in Vessel Heave Motion Based on Improved LSTM Model , 2021, IEEE Access.