A life cycle carbon emission assessment method is proposed to comprehensively evaluate the carbon emission reduction capacity of hydrogen-electric hybrid ships.

First, an energy flow model of the power system is established using the Matlab/Simulink software platform. Hydrogen consumption and electricity consumption under actual operating conditions are then calculated, and the life cycle carbon emissions are obtained. Finally, sensitivity analysis is performed on carbon emissions from different power sources and hydrogen sources.

The results of an inland river ferry show that compared with the traditional diesel engine power system, the hydrogen-electric hybrid system can reduce carbon emissions by 30.24% in one operation cycle. The sensitivity analysis results show that the carbon emissions of the hydrogen-electric hybrid system are not necessarily better than those of the traditional diesel power system, so it is recommended to use renewable energy for hydrogen production and power generation to significantly reduce carbon emissions (up to 94.2%).

The results of this study can provide references for the power system design of green ships.

The class imbalance problems which are prevalent in the condition monitoring data of marine diesel engines significantly deteriorate the performance of data-driven models for the automatic and accurate identification of the health condition of engines. In this paper, a graph convolutional network (GCN) model based on probability similarity between samples is proposed to solve the classification problem of unbalanced datasets.

First, the Kullback-Leibler divergence is introduced to calculate the probability similarity between samples and mine the nonlinear relationship, and a probability topological graph is constructed to represent the similarity of samples. Graph learning is then introduced to learn and extract the correlations between adjacent samples in addition to their own features, providing more information for the imbalanced classification task. After multi-layer graph learning, the higher-level features of each node are extracted.

The two cases of the simulation model and bench test clearly show that the proposed method efficiently extracts more information based on aggregating neighboring samples'features, and improves the classification accuracy under imbalanced datasets.

The precision and recall rate of the proposed GCN model are higher than those of other state-of-the-art algorithms, giving it certain practical application value.

There are multiple operation conditions for ships navigation in inland river waterway, such as sailing downstream, upstream as well as in rapid stream, but the traditional ship-engine-propeller matching method can only ensure that the inland ships meet the design requirements when they travels upstream. Under downstream conditions, the ship propulsion's efficiency and energy utilization rate of main engine are both low, resulting in high fuel consumption and less cost-effectivness. To this end, the optimal design of ship-engine-propeller matching for the inland ships under multiple conditions is carried out.

First, the parameters of an inland ship's propulsion system under various conditions are designed, and the results are compared to ascertain the influence of each design parameter on the overall propulsion system. Then, the design process of the propulsion system is analyzed, and a mathematical model is established with navigation cost and propulsion system efficiency as the objective functions, and the design parameters of the propeller, main engine power and ship speeds (upstream & downstream) as variables. Finally, the main engine power and design parameters of propulsion system are determined balancing both economy and efficiency using the NSGA-II algorithm.

The design parameters obtained using this method are easily adapted to the traffic environment of inland ships, making them more economical.

The results of this study can not only provide design tools for the selection of ship propulsion systems, but also provide a theoretical basis for its practical application.