基于循环神经网络的船摇数据实时预测

Real Time Prediction of Ship-swaying Data Using Recurrent Neural Network

航天测量船船体姿态数据实时预测具有重要的意义。针对测量船船摇运动建立了基于循环神经网络的预测模型,详细描述了适用于本文模型的船体姿态数据集构建以及预测模型的实现过程。在该模型的基础上,利用实测数据对船体姿态数据进行短时预测,并将预测结果与滤波方法进行了比较,实验结果验证了算法的有效性。

Real-time prediction of the TT&C ship’s ship-swaying data is of great significance.A prediction model based on recurrent neural network was established for measuring the motion of ship-swaying.It was described in detail the realization process of the prediction model.In addition,it constructed datasets suitable for this model.Based on this model,short-term prediction of ship-swaying is carried out by using the real measured data,and the prediction results are compared with the filtering method.The experimental results verify the effectiveness of the proposed algorithm.