Timely and effective maintenance is imperative to minimize operational disruptions and ensure the reliability of marine vessels. However, given the low early warning rates and poor adaptability under complex conditions of previous data-driven fault prediction methods, this paper presents a hybrid deep learning model based on multi-layer attention mechanisms for predicting faults in a marine diesel engine. Specifically, this hybrid model first introduces a Convolutional Neural Network (CNN) and self-attention to extract local features from multi-feature input sequences. Then, we utilize Long Short-Term Memory (LSTM) and multi-head attention to capture global correlations across time steps. Finally, the hybrid deep learning model is integrated with the Exponential Weighted Moving Average (EWMA) to monitor the operational status and predict potential faults in the marine diesel engine. We conducted extensive evaluations using real datasets under three operating conditions. The experimental results indicate that the proposed method outperforms the current state-of-the-art methods. Moreover, ablation studies and visualizations highlight the importance of fusing multi-layer attention, and the results under various operating conditions and application scenarios demonstrate that this method possesses predictive accuracy and broad applicability. Hence, this approach can provide decision support for condition monitoring and predictive maintenance of marine mechanical systems.

In inland waterways, there is a high density of various objects, with a predominance of small objects, which can easily affect navigation safety. To improve the navigation safety of inland ships, this paper proposes a new lightweight water-surface object-detection model named LWS-YOLOv7, which is based on the baseline model YOLOv7. Firstly, the localization loss function is improved and the w-CIoU function is introduced to reduce the model’s sensitivity to position deviations of small objects and to improve the allocation accuracy of positive and negative sample labels. Secondly, a new receptive field amplification module named GSPPCSPC is proposed to reduce the model’s parameters and enhance its receptive field. Thirdly, a small-object feature-fusion layer, P2, is added to improve the recall rate of small objects. Finally, based on the LAMP model pruning method, the weights with lower importance are pruned to simplify the parameters and computational complexity of the model, facilitating the deployment of the model on shipborne devices. The experimental results demonstrate that, compared to the original YOLOv7 model, the map of LWS-YOLOv7 increased by 3.1%, the parameters decreased by 38.8%, and the GFLOPS decreased by 28.8%. Moreover, the model not only has better performance and higher speed for input images of different sizes, but it can also be applied to different meteorological conditions.

Smoke simulation is a crucial yet challenging aspect of constructing ship fire scenarios. For the Eulerian smoke simulation method, the low-resolution grid results in a loss of smoke detail, while the high-resolution grid faces significant computational costs. To address this issue, a detail enhancement approach is proposed for smoke simulation in ship fire scenarios based on vortex particles, aiming at high-realism smoke simulation on a low-resolution grid. The simulation domain is first discretized using a low-resolution grid to compute the basic flow. Next, the vortex particles are sampled within the grid, and the loss of vorticity is measured before and after vortex stretching to compensate for the missing smoke details. In our approach, a geometric method is employed to efficiently capture the stretching of vortex structures. The computational results demonstrate that turbulence details can be effectively captured in a low-resolution grid while maintaining the real-time performance of the simulation. The practical application value of our approach is demonstrated in improving the realism of ship fire scenarios.

In the domain of ocean engineering, the authenticity of visual systems is a major challenge in developing marine simulators. A simulation strategy based on the smoothed particle hydrodynamics (SPH) simulation method is proposed in this study to enhance the realism of fluid–solid coupling scenes in a marine simulator visual system. Based on the SPH method, the water particles are constrained in each iteration according to the two physical fields of velocity divergence and density by setting an intermediate velocity. In the simulation of the fluid–structure interaction scenario, the contribution of the volume of the rigid model to the water particles is represented by a spatial map and then incorporated into the calculation of the pressure from the water particles according to the positional relationship between the water particles and the boundary. This strategy can effectively ensure the realism of the interaction between the rigid body and the waves on the one hand and significantly improve the speed of the marine simulator visual system on the other. The experiments show that this strategy can effectively save a significant amount of time and provide theoretical and technical references for enhancing the realism of a marine simulator visual system.