Ship trajectory prediction method and system based on one-dimensional convolutional neural network and lstm

Abstract

The present invention relates to a ship trajectory prediction method based on one-dimensional convolutional neural network and LSTM, comprising the following steps: data preprocessing step: preprocessing the trajectory data collected by ship AIS including ship position, speed and course information Obtain trajectory segmentation data; feature extraction step: use a one-dimensional convolutional neural network to perform feature extraction optimization on trajectory segmentation data, and combine the extracted advanced features with the trajectory segmentation data to construct input data for trajectory prediction training Trajectory prediction model training step: import the input data into the LSTM neural network model to learn the hidden ship motion law in the trajectory data; track prediction step: use the ship motion law to predict the position of the ship at the next moment. Compared with other existing forecasting methods, the present invention has better forecasting accuracy, lower mean square error and faster forecasting.

Description

technical field [0001] The invention belongs to the technical field of intelligent prediction, and in particular relates to a ship trajectory prediction method and system based on a one-dimensional convolutional neural network and LSTM. Background technique [0002] The characteristics of ship navigation and vehicle driving are different, there is no obvious road network constraint, the track is more random, and the prediction is more difficult. The traditional ship trajectory prediction method adopts the method of constructing dynamic equations. This type of method requires professional knowledge support, and needs to be modified according to different ships and scenarios, and the adaptability of the method is poor. The current mainstream method is to use machine learning, which can perform parameter learning based on historical trajectories and current driving trajectories, so that the prediction model has better adaptability. The representative prediction methods based o...

AI Technical Summary

Problems solved by technology

[0003] In view of the above analysis, the present invention aims to disclose a ship trajectory prediction method and system based on one-dimensional convolutional neural network and LSTM to solve the problem of ship trajectory prediction

Images