The invention provides a ship trajectory prediction method and system, and relates to the field of waterway traffic, heuristic algorithms and deep learning, AI S ship data is acquired, and a Lagrange interpolation method is adopted to carry out interpolation processing on the data; according to a preset time interval, track point information of ship driving is extracted from the interpolated data, and a historical track point time sequence is formed; processing a historical track point time sequence by using the constructed track prediction model, and generating and outputting a track point time sequence of a future time period; the trajectory prediction model is constructed based on a multi-head space-time self-attention mechanism and a bidirectional gating recurrent neural network, an artificial fish swarm algorithm is adopted to perform hyper-parameter optimization on the trajectory prediction model, and the optimized trajectory prediction model is trained to obtain a final trajectory prediction model; according to the method, the ship trajectory prediction precision is improved, so that the channel passing efficiency is improved, the channel freight volume is increased, meanwhile, the supervision capability on marine ships is improved, and marine traffic accidents are reduced.
本发明提出了一种船舶轨迹预测方法及系统,涉及水路交通、启发式算法和深度学习领域,获取AI S船舶数据,采用拉格朗日插值法对数据进行插值处理;依据预设的时间间隔,从插值后的数据中提取船舶行驶的轨迹点信息,组成历史轨迹点时间序列;利用构建好的轨迹预测模型对历史轨迹点时间序列进行处理,生成并输出未来时间段的轨迹点时间序列;轨迹预测模型基于多头时空自注意力机制和双向门控循环神经网络构建,采用人工鱼群算法对轨迹预测模型进行超参数寻优,对寻优后的轨迹预测模型进行训练,得到最终的轨迹预测模型;本发明提升船舶轨迹预测的精度,从而提高航道通行效率和增强航道货运量,同时提高对海上船舶的监管能力,减少海上交通事故。
Ship trajectory prediction method and system
一种船舶轨迹预测方法及系统
2024-03-12
Patent
Electronic Resource
Chinese
IPC: | G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Ship route prediction method based on ship trajectory clustering
European Patent Office | 2021
|Ship Trajectory Prediction with Social History LSTM
IEEE | 2023
|Unpowered ship trajectory prediction method, device and equipment and storage medium
European Patent Office | 2022
|