Research on Ship Weather Routing Method Based on Dijkstra Algorithm and Neural Network

This article presents the research and development of a method to find optimal fuel routes for ships based on the Dijkstra algorithm, neural network, and weather forecast information. The proposed method uses a HIL simulator to generate a dataset with cases of different amplitudes and directions of environmental disturbances acting on the ship. Based on that dataset and weather forecast information, an algorithm is proposed to find the optimal fuel route for ships based on the Dijkstra algorithm and neural network. Test results show that the algorithm operates reliably and has low errors. The proposed method has the advantage of being simple and effective, especially applicable to ships that do not have past operating data or cannot use such data for security and defense reasons.