Prediction of Ocean Wave Height Suitable for Ship Autopilot

Autor: Yuchao Zheng, Ranran Lou, Wen Wang, Zhihan Lv, Xinfang Li
Rok vydání: 2022
Předmět:
Zdroj: IEEE Transactions on Intelligent Transportation Systems. 23:25557-25566
ISSN: 1558-0016
1524-9050
DOI: 10.1109/tits.2021.3067040
Popis: Ships are usually disturbed by waves when they are traveling at sea. When the waves are large, it is not conducive to driving safety, comfort and economy. Therefore, this paper proposed a new type of automatic driving scheme, which links the wave height prediction with ship driving. By studying the accurate prediction of wave height, ships can adjust their course in real time to ensure that they always travel in the area with the lowest wave height. According to the different driving conditions of ships in the open sea and the offshore sea, we designed two wave height prediction models based on LSTM, which are suitable for the above two types of sea areas. In particular, when we created the open sea model, we selected the data of the location points other than the predicted point as the training data. After comparative testing, the two types of models have reached satisfactory accuracy, which provided support for the ship automatic driving scheme proposed in this paper.
Databáze: OpenAIRE