The key to improving the fuel economy of plug-in hybrid electric vehicles (PHEVs) lies in the energy management strategy (EMS). Existing EMS often neglects engine operating conditions, leading to frequent start–stop events, which affect fuel economy and engine lifespan. This paper proposes an Integrated Engine Start–Stop Dynamic Programming (IESS-DP) energy management strategy, aiming to optimize energy consumption. An enhanced rule-based strategy is designed for the engine’s operating conditions, significantly reducing fuel consumption during idling through engine start–stop control. Furthermore, the IESS-DP energy management strategy is designed. This strategy comprehensively considers engine start–stop control states and introduces weighting coefficients to balance fuel consumption and engine start–stop costs. Precise control of energy flow is achieved through a global optimization framework to improve fuel economy. Simulation results show that under the World Light Vehicle Test Cycle (WLTC), the IESS-DP EMS achieves a fuel consumption of 3.36 L/100 km. This represents a reduction of 6.15% compared to the traditional DP strategy and 5.35% compared to the deep reinforcement learning-based EMS combined with engine start–stop (DDRL/SS) strategy. Additionally, the number of engine start–stop events is reduced by 43% compared to the DP strategy and 16% compared to the DDRL/SS strategy.

When the unmanned aerial vehicle (UAV) is applied to three-dimensional (3D) reconstruction of the offshore ship, it faces two problems: the battery capacity limitation of the UAV and the disturbance of the wind in the environment. Wind disturbance is generally not considered in the path planning process of the existing UAV 3D reconstruction path planning research. Therefore, the planned path is only suitable for no-wind or light-wind scenarios. For the 3D reconstruction of ship targets, we propose a UAV path planning method that can satisfy both reconstruction efficiency and wind disturbance resistance requirements. Firstly, the concept of model surface complexity is proposed to generate a more efficient candidate view set. Secondly, the Min–Max strategy and a new viewpoint construction method are used to generate the initial path. Thirdly, combined with the wind field model, a method for generating a stable path against wind disturbance based on the idea of interval optimization is proposed. Experimental results demonstrate that our method can adaptively determine the number of sample points and viewpoints according to ship’s geometric characteristics and further reduce the number of viewpoints without significantly affecting the reconstruction quality; the path planned by our method is also stable against wind disturbance.

When conducting accident analysis, the assessment of risk is one of the important links. Moreover, with regards to crew training, risk cognition is also an important training subject. However, most of the existing researches only rely on a single or a few data sources. It is necessary to fuse the collected multi-source data to obtain a more comprehensive risk evaluation model. There are few studies on the three-dimensional (3D) multi-modal data-fusion-based trajectory risk cognition. In this paper, a fuzzy logic-based trajectory risk cognition method is proposed based on multi-model spatial data fusion and accident data mining. First, the necessity of multi-model spatial data fusion is analysed and a data-fusion-based scene map is constructed. Second, a risk cognition model fused by multiple factors, multi-dimensional spatial calculations as well as data mining results is proposed, including a novel ship boundary calculation approach and newly constructed factors. Finally, a radar chart is used to illustrate the risk, and a risk cognition system is developed. Experiment results confirm the effectiveness of the method. It can be applied to train human operators of unmanned ship systems.

The goal of depth estimation is to obtain the depth image which reflects the distance between the object and the camera point. Depth image can provide depth information for tasks, such as three-dimensional (3D) reconstruction and distance perception. With the development of the environment perception research of the unmanned ship and unmanned aerial vehicle (UAV), depth estimation has been widely used in the field of water transportation. However, the research of ship depth estimation based on monocular images has just started, and there is no unsupervised deep learning depth estimation method for ship target based on single view UAV image. This paper proposes an unsupervised deep learning ship depth estimation method based on single view UAV images. Firstly, the realistic rendering software is used to construct a new ship training dataset with simple backgrounds and regular lighting conditions. Secondly, based on the differentiable rendering framework, a knowledge distillation depth estimation network is designed to train a student network with much smaller number of model parameters. Finally, the ship depth estimation network is obtained through unsupervised training. The experiment results show that the designed knowledge distillation depth estimation network can generate better depth estimation results compared with the current state-of-the-art (SOTA) method, and the weight file size of our model is smaller.