Wind-assisted propulsion system (WAPS) is one of the important energy-saving measures for shipping decarbonization. The optimal design and operation control of wind-assisted ships can efficiently harvest and utilize wind energy, and thus further tapping the potential of improving the ship energy efficiency. However, there remains a shortage of the comprehensive analysis of the wind-assisted technologies to provide references for further study and practical applications of the WAPS. Thus, the present progress achieved in the key techniques, including the aerodynamics analysis for different sails, the optimal design and operation control of the ship adopting WAPS, as well as the comprehensive analysis of the sail-diesel hybrid propulsion system (SDHPS), are systematically analyzed. Additionally, the challenges encountered in the development of the WAPS are proposed, and prospective research directions are suggested to boost advancement of the WAPS for the shipping decarbonization. The investigation results indicate that the optimal design of sails and hybrid power systems, along with the applications of energy efficiency optimization strategies, can fully use the wind energy resources and reduce fuel usage of the ship equipped with WAPS. Additionally, it is anticipated that the wind-assisted technology incorporating complicated sea conditions can contribute to a further optimization of ship energy utilization, thereby promoting the low-carbon development of the shipping industry.

Optimization of ship energy efficiency is an efficient measure to decrease fuel usage and emissions in the shipping industry. The accurate prediction model of ship energy usage is the basis to achieve optimization of ship energy efficiency. This study investigates the sequential properties of the actual voyage data from a VLOC. On this basis, a model for predicting ship energy consumption is established by adopting a LSTM neural network that has better prediction performance for sequential datasets. To further enhance the performance of the established LSTM-based model, the network structures and hyperparameters are optimized by using Genetic Algorithm. Lastly, the application analysis is conducted to validate the established GA-LSTM-based model for ship fuel usage prediction. The established model for ship energy usage shows a significant improvement in prediction accuracy, compared to the original LSTM-based model. Meanwhile, the developed prediction model is more accurate than the existing BP, SVR, and ARIMA-based energy consumption models. The prediction errors for the ship's operational energy efficiency adopting the established GA-LSTM-based model can reach as low as 0.29%. Therefore, the established model can effectively predict the ship fuel usage under different conditions, which is essential for the optimization and improvement of ship energy efficiency.