Offshore personnel drift trajectory prediction method

• Main Authors: DU LIBIN, SHI RUNJIE, MA YUNGE, LI ZHENGBAO, GAO JIE, JIA XUAN
• Format: Patent
• Language: Chinese; English
• Published: 24.11.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention, which belongs to the drifting trajectory prediction field, discloses a maritime personnel drifting trajectory prediction method comprising the following steps: acquiring maritime personnel drifting trajectory data, and preprocessing the drifting trajectory data; constructing a training set and a test set about the time sequence based on the preprocessed data set; constructing a dilated convolution-GRU network model based on a dual self-attention mechanism, the dilated convolution-GRU network model comprising a feature multi-head self-attention module, a dilated convolution network module, a two-layer GRU network module and a time sequence self-attention module, and training the model by using the training set; and using the trained model to predict the drift trajectory of the maritime personnel at future moments. According to the method, a deep learning method is adopted, a dilated convolution-GRU network model of a dual self-attention mechanism is constructed, trajectory features are fully ext