A Novel Machine Learning Model Using CNN-LSTM Parallel Networks for Predicting Ship Fuel Consumption

With continuous increasing of carbon emission, prediction of ship fuel consumption is gaining significance in reduction of energy consumption and emissions for ships. This paper proposes a novel model of parallel network by combining convolutional neural network and long short-term memory (CNN-LSTM). The proposed model integrates three advantages. The CNN part of proposed model can extract spatial features, the LSTM part of proposed model can capture temporal relationships, and the parallel structure of proposed model can obtain feature fusion from both of CNN and LSTM based on multi-source data. Experimental outcomes reveal that CNN-LSTM parallel networks can obtain best results of MAE and RMSE, which outperformed single LSTM, single CNN and other neural networks with decreasing of 48.06%, 64.06% and 48.56% in MAE, and 35.71%, 58.25% and 37.85% in RMSE.