Evaluation of main engine energy efficiency based on BP neural network

  Objectives  During the voyage of a ship, the operating parameters of the ship and its main engine need to be analyzed so as to objectively judge the current working state of the main engine and accurately evaluate its energy efficiency.

  Methods  Taking good ship operation records as samples, and combined with principal component analysis and the BP neural network algorithm, a ship navigation state identification model and main engine fuel consumption model are built. During the voyage of a ship, these two models are used to analyze the real-time operating parameters of the ship in order to obtain the normal value of the main engine fuel consumption under current working conditions. The model of a 300 000-ton ocean bulk carrier is used to calculate and verify the models, the normal value is compared with the actual fuel consumption value of the main engine, which is based on the residual value of the two, and the current energy efficiency state of the diesel engine is then evaluated.

  Results  The validation results show that the correct rate of the navigation state identification model is 98.05% and the average error margin of the fuel consumption model is 3.47%, thus proving the two models to be more reliable.

  Conclusions  The results of this research can provide references for the energy efficiency management of intelligent ships.