Ship motion attitude prediction device based on neural network

The invention discloses a ship motion attitude prediction device based on a neural network, belongs to the technical field of navigation electronic equipment, and particularly relates to ship motion attitude prediction. The problem of selecting and constructing a proper network model in the prior art is solved, and the problems that the timeliness of data is difficult to guarantee while the ship motion attitude prediction precision is improved, the training speed of a neural network is uncertain, and the prediction real-time performance cannot be guaranteed are solved. The device comprises the following modules: an EMD processing module used for performing EMD processing on input ship motion attitude time series data and decomposing the ship motion attitude time series data into a plurality of IMF component sequences; and the GGNNs module is used for obtaining a prediction result of each IMF component sequence according to the graph structure by adopting the optimal GGNNs model. The ship motion attitude predi