Open AccessResearch on High Accuracy Prediction of Ship Attitude Based on Improved Neural Network Method
Author(s) -
Bo Xu,
Yang Cheng
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/4/042059
Subject(s) - artificial neural network , computer science , artificial intelligence
In view of the difficult problem of ship attitude prediction accuracy and the features of ship attitude change, a prediction model of high accuracy of ship attitude based on the improved neural network is proposed. Firstly the data of ship attitude is collected and de-noised. Then the high accuracy approximation to the features of ship attitude changes is carried out by using the improved neural network, some defects of which are improved. Finally the simulation experiment of ship attitude prediction is conducted. The experimental results show that the improved neural network can improve the accuracy of the ship attitude prediction and overcome the disadvantages of the large errors in the other ship attitude prediction models and the advantages of the ship attitude effect are very obvious.