Application of artificial neural network in the prediction method of ship navigation resistance in ice areas
In order to ensure the safety of ships sailing in polar ice regions,accurate prediction of ice resistance plays an important role.In recent years,artificial neural network(ANN)machine learning has been widely used in the field of ships.In this study,the machine learning method is used to design a model to predict the ice re-sistance of polar ships.With reference to the existing empirical formula,high-quality characteristic parameters are selected for input,and the model neural network is drilled by sufficient ship model experimental data.Based on the establishment of radial basis function(RBF)neural network model,genetic algorithm(GA)is used to optimize the model.The research results show that the genetic algorithm based on the input seven high-quality characteristic parameters has a strong generalization effect on the optimization of the radial basis neural network(RBF-GA)model.Compared with the real ship experimental data,it is proved that the average error is less than 8％,and its high accuracy can be applied to the prediction of ice resistance.
polar regionship navigationice resistancegenetic algorithmradial basis function neural net-workship model experiment
NETL
NSTL
万方数据
