This study aims to develop an enhanced YOLO algorithm to improve the ship detection performance of synthetic aperture radar (SAR) in complex marine environments. Current SAR ship detection methods face numerous challenges in complex sea conditions, including environmental interference, false detection, and multi-scale changes in detection targets. To address these issues, this study adopts a technical solution that combines multi-level feature fusion with a dynamic detection mechanism. First, a cross-stage partial dynamic channel transformer module (CSP_DTB) was designed, which combines the transformer architecture with a convolutional neural network to replace the last two C3k2 layers in the YOLOv11n main network, thereby enhancing the model’s feature extraction capabilities. Second, a general dynamic feature pyramid network (RepGFPN) was introduced to reconstruct the neck network architecture, enabling more efficient multi-scale feature fusion and information propagation. Additionally, a lightweight dynamic decoupled dual-alignment head (DYDDH) was constructed to enhance the collaborative performance of localization and classification tasks through task-specific feature decoupling. Experimental results show that the proposed DRGD-YOLO algorithm achieves significant performance improvements. On the HRSID dataset, the algorithm achieves an average precision (mAP50) of 93.1% at an IoU threshold of 0.50 and an mAP50–95 of 69.2% over the IoU threshold range of 0.50–0.95. Compared to the baseline YOLOv11n algorithm, the proposed method improves mAP50 and mAP50–95 by 3.3% and 4.6%, respectively. The proposed DRGD-YOLO algorithm not only significantly improves the accuracy and robustness of synthetic aperture radar (SAR) ship detection but also demonstrates broad application potential in fields such as maritime surveillance, fisheries management, and maritime safety monitoring, providing technical support for the development of intelligent marine monitoring technology.

This paper addresses the issue of the poor collision avoidance effect of underactuated surface vehicles (USVs) during local path tracking. A virtual ship group control method is suggested by using Freiner coordinates and a model predictive control (MPC) algorithm. We track the planned path using the MPC algorithm according to the known vessel state and build a hierarchical weighted cost function to handle the state of the virtual vessel, to ensure that the vessel avoids obstacles while tracking the path. In addition, the control system incorporates an Extended Kalman Filter (EKF) algorithm to minimize the state estimation error by continuously updating the ship state and providing more accurate state estimation for the system in a timely manner. In order to validate the anti-interference and robustness of the control system, the simulation experiment is carried out with the “Yukun” as the research object by adding the interference of wind and wave of level 6. The outcome shows that the algorithm suggested in this paper can accurately perform the trajectory-tracking task and make collision avoidance decisions under six levels of external interference. Compared with the original MPC algorithm, the improved MPC algorithm reduces the maximum rudder angle output value by 58%, the integral absolute error by 46%, and the root mean square error value by 46%. The control method provides a new technical choice for trajectory tracking and collision avoidance of USVs in complex marine environments, with a reliable theoretical basis and practical application value.

To address the issues of model uncertainties and external disturbances in path tracking control, a gain-scheduled adaptive Tube-NMPC algorithm is proposed. Tube robust constraints are incorporated into the NMPC framework to enhance disturbance rejection capability, while a gain-scheduling mechanism is employed to achieve online adjustment of control parameters under different operating conditions. An adaptive update-rate strategy is further designed to dynamically regulate the tube contraction parameter, thereby improving the adaptability of the control system to environmental variations. Experiments are conducted under both disturbance-free conditions and disturbance scenarios involving surge force, sway force, and yaw moment disturbances. The results demonstrate that the proposed algorithm achieves superior performance in position tracking, velocity tracking, and control input smoothness. The effectiveness of the proposed method is validated, demonstrating improved path tracking accuracy and control stability under disturbance conditions.

Under 10 min sparse Automatic Identification System (AIS) sampling, the reliability of point-wise motion statistics degrades substantially, and conventional classification methods rely on trajectory interpolation, which may introduce spurious motion patterns. This study proposes a feature-driven framework for fishing vessel type identification that eliminates the need for interpolation preprocessing. A 39-dimensional feature set is constructed using robust statistics, including the median and interquartile range, to characterize trajectory-level behavioral patterns. Adaptive speed interval thresholds are derived through a data-driven approach grounded in Bayesian decision boundaries, thereby removing the dependence on manually defined cut-off values. A backward ablation procedure guided by feature importance ranking identifies a lightweight 12-dimensional feature subset that retains 98.7% of the classification accuracy at a compression rate of 69%. Evaluated on 18,320 fishing vessel trajectories in the East China Sea, the full 39-dimensional feature set achieves a 5-fold cross-validation accuracy of 91.92% (Macro-F1 = 0.919, Kappa = 0.879), with inter-fold standard deviations ranging from 0.002 to 0.004. Comparative experiments demonstrate that three tree-based classifiers all exceed 90% accuracy on the same feature set, confirming that feature robustness, rather than model selection, constitutes the dominant performance factor. LightGBM achieves the optimal trade-off between accuracy and training efficiency, whereas the cross-validation standard deviation of LSTM is approximately 7.5 times greater, indicating that hand-crafted robust features provide superior stability under sparse sampling conditions. The proposed framework requires no fishery-specific prior knowledge and offers a transferable paradigm for sparse AIS trajectory analysis.

A full-cylinder CFD model was developed to investigate methyl decanoate (MD)/diethyl ether (DEE) blends in a MAN B&W 7S80ME-C9 two-stroke diesel engine at 75% load. The model retained the multi-injector configuration, asymmetric spray development, scavenging and exhaust processes, and in-cylinder combustion of the 800 mm-bore engine. Four equal-energy cases, MD100, MD95, MD90, and MD85, were considered, with DEE energy fractions of 0%, 5%, 10%, and 15%. DEE blending regulated spray evaporation, mixture formation, heat-release phasing, and expansion work conversion. Increasing the DEE fraction enhanced evaporation and gas-phase mixing, but stronger mixing did not necessarily improve thermal performance. The peak-pressure trend differed from the net indicated work trend, indicating that work output was governed more by pressure evolution during expansion than by peak pressure alone. MD90 maintained stronger post-injection heat release and a more favorable equivalence-ratio distribution, thereby achieving the highest net indicated work, 6.70% higher than MD100. Although MD90 showed a high mean temperature, it produced the lowest NO and NO₂ emissions because NO_X formation depended on the local coupling of temperature, oxygen availability, equivalence ratio, and residence time. The CO₂ level was lowest for MD100 among the four fuel cases. At 75% load, MD90 provided a favorable balance among heat-release phasing, net indicated work, and emission control across the four investigated fuel cases.

To balance safety, real-time performance, and dynamic feasibility in path planning for unmanned surface vehicles (USVs) operating in complex aquatic environments, the study proposes a hybrid planning framework that integrates a multi-scale A* algorithm with the Dynamic Window Approach (DWA) under Maneuvering Modeling Group (MMG) dynamic constraints. Global path optimization incorporates target-oriented neighborhood expansion, obstacle risk constraints, and a maneuverability cost function to comprehensively evaluate path length and collision risk, thereby enhancing the efficiency of the hybrid global-local planning framework. Local trajectory prediction strictly couples the MMG USV motion model with the DWA algorithm. Real-time optimization of these dynamically constrained trajectories ultimately achieves proactive and safe evasion of dynamic obstacles. Compared with the traditional A* + DWA method, the proposed hybrid method reduces path length and computational time by 5.09% and 31.93%, effectively suppressing abrupt heading changes during dynamic obstacle avoidance. This paper provides an efficient path planning strategy that conforms to USV maneuvering constraints for autonomous navigation and dynamic obstacle avoidance.