Search

The You Only Look Once (YOLO) series of object detection models is widely recognized for its efficiency and real-time performance, particularly under the challenging conditions of underwater environments, characterized by insufficient lighting and visual disturbances. By modifying the YOLOv9s model, this study aims to improve the accuracy and real-time capabilities of underwater object detection, resulting in the introduction of the YOLOv9s-UI detection model. The proposed model incorporates the Dual Dynamic Token Mixer (D-Mixer) module from TransXNet to improve feature extraction capabilities. Additionally, it integrates a feature fusion network design from the LocalMamba network, employing channel and spatial attention mechanisms. These attention modules effectively guide the feature fusion process, significantly enhancing detection accuracy while maintaining the model's compact size of only 9.3 M. Experimental evaluation on the UCPR2019 underwater object dataset shows that the YOLOv9s-UI model has higher accuracy and recall than the existing YOLOv9s model, as well as excellent real-time performance. This model significantly improves the ability of underwater target detection by introducing advanced feature extraction and attention mechanisms. The model meets portability requirements and provides a more efficient solution for underwater detection. [ABSTRACT FROM AUTHOR]

The submarine is usually affected by free surface and the navigation resistance increases when sailing near the surface. In order to study the specific resistance characteristics of submarine sailing near the surface, the SUBOFF with appendages was taken as the research object, and the calculation model was built based on Star CCM+ fluid simulation software, and the resistance coefficients under different submarine depths and speeds were calculated. Through comparative analysis, the influence of the depth and speed of the submarine on the resistance components was obtained, and the cause of the formation was analyzed. The results show that the influence of the depth of submarine on friction resistance coefficient is small in general. With the increase of the depth of the submarine, the pressure resistance coefficient decreases, and the wave amplitude decreases. The shear wave of Kelvin wave system is more obvious and the effect of scattering is weakened, which is of great significance for the study of submarine concealment. With the increase of speed, friction resistance coefficient decreases, the overall change trend of pressure resistance coefficient is first increased and then decreases. The interference effect between free surface and hull increases first and then decreases at each depth. The wave shape changes and resistance results mutually confirm. The free surface mainly generates waves by interacting with the hull, which affects the resistance characteristics of the submarine. The interference effect is greatly affected by the depth and speed of the submarine.

[Objectives] How to maintain propulsion capability in a CODOG propulsion system damage situation has important significance. [Methods] A ‘Hull-Engine-CPP-Rudder’ simulation model of a CODOG marine power plant is established on Simulink using the modularized method, and a dissymmetrical main engine urgent working mode is proposed and simulated. [Results] The results show that in the dissymmetrical working mode, two different engines cannot work simultaneously at designed capacity. However, by adjusting the pitch of the CPP, one engine can work at designed capacity and the other can work at partial load capacity; under this working mode, if high speed is demanded, the gas turbine should work at designed capacity. The CPP pitch driven by diesel should be maintained at a high value near the maximum. The maximum speed of this working mode is 84.4% of the designed speed, which is higher than the speed of the single shaft working mode driven by a gas turbine. [Conclusions] The research results of this paper can provide useful references for the design of ship propulsion systems.