Ship Fuel Consumption Prediction based on MFO-BP

The International Maritime organization (IMO) has become more restrictive on ship emission standards recently. Improving ship energy efficiency and reducing ship energy consumption have become important areas for the development of the shipping industry. Based on the moth flame optimization (MFO) algorithm and the improved back propagation (BP) neural network, the MFO-BP regression model is established in this paper. The weight and threshold of BP neural network are optimized by MFO algorithm, and each threshold and weight of BP neural network is regarded as the optimization object, which reduces iteration times of the MFO-BP and improves prediction accuracy of fuel consumption during ship sailing. Finally, the predictive effect of the MFO-BP model is validated. From the prediction results, the MFO-BP model has higher prediction accuracy for ship fuel consumption compared with other prediction models.