Influence of different Machine learning algorithms on Prediction Model of Fuel Consumption of Inland Ships

An accurate prediction of ship fuel consumption is of great significance to the economy of ship operations. To study the influence of different machine learning algorithms on the prediction of ship fuel consumption, an inland river cruise ship has been considered as the research object. Based on the actual operation data obtained by the energy efficiency data acquisition system of the real ship, a prediction model of the ship's main engine fuel consumption was established using the Multi-Layer Perceptron Regression, Decision Tree Regression, Random Forest Regression, K-Nearest Neighbor, Extra Trees Regression and Support Vector Regression algorithms. Mean absolute error, mean square error, root mean square error, and coefficient of determination were used to evaluate the accuracy of the model, and the effect of different machine learning algorithms on the inland ship fuel consumption prediction model was investigated under different data volumes. The results show that the Extra Trees Regression and Random Forest Regression models perform best, and the amount of modelling data has a significant impact on the training time of the Random Forest Regression and Support Vector Regression models.