A Machine-Learning-Based Method for Ship Propulsion Power Prediction in Ice

In recent years, safety issues respecting polar ship navigation in the presence of ice have become a research hotspot. The accurate prediction of propulsion power plays an important role in ensuring safe ship navigation and evaluating ship navigation ability, and deep learning has been widely applied in the field of shipping, of which the artificial neural network (ANN) is a common method. This study combines the scientific problems of ice resistance and propulsion power for polar ship design, focusing on the design of an ANN model for predicting the propulsion power of polar ships. Reference is made to the traditional propulsion power requirements of various classification societies, as well as ship model test and full-scale test data, to select appropriate input features and a training dataset. Three prediction methods are considered: building a radial basis function–particle swarm optimization algorithm (RBF-PSO) model to directly predict the propulsion power; based on the full-scale test and model test data, calculating the propulsion power using the Finnish–Swedish Ice Class Rules (FSICR) formula; using an ice resistance artificial neural network model (ANN-IR) to predict the ice resistance and calculate the propulsion power using the FSICR formula. Prediction errors are determined, and a sensitivity analysis is carried out with respect to the relevant parameters of propulsion power based on the above methods. This study shows that the RBF-PSO model based on nine feature inputs has a reasonable generalization effect. Compared with the data of the ship model test and full-scale test, the average error is about 14%, which shows that the method has high accuracy and can be used as a propulsion power prediction tool.