Path planning is crucial for autonomous underwater vehicles (AUVs) and plays a vital role in ocean engineering. To improve the search efficiency and accuracy, this study proposed a three-dimensional path-planning method for AUVs based on the interval multi-objective secretary bird optimization algorithm (IMOSBOA). This method addressed path-planning challenges under imprecise current predictions and uncertain hazard source locations. First, the marine environment was modeled in three dimensions using the interval theory. Second, the danger levels and navigation times were set as the optimization objectives to construct a three-dimensional path-planning mathematical model. Finally, IMOSBOA was proposed and applied to solve the optimization problem. To verify the optimization performance of the new algorithm, its planning results were compared with those of the other algorithms. The simulation results demonstrated that the robustness and search capability of the proposed algorithm surpass those of comparative algorithms.

The operational efficiency and reliability of the ship’s lubrication oil system directly impact the vessel’s safety. Traditional reliability analysis methods struggle to effectively handle the system’s dynamic characteristics and multi-source data analysis. To address these issues, this study proposes an innovative method that integrates feature dimensionality reduction, a dynamic Bayesian network of gravity model to improve the accuracy of system reliability analysis. First, the proportional hazards model is used to evaluate the operational reliability of each component, providing a quantitative basis for assessing the system’s health status through failure rate estimation. Then, a dynamic Bayesian network model is employed for overall system reliability analysis, fully considering the impact of multi-state devices and different maintenance strategies. The proposed DBN-based reliability assessment method achieves significant improvements over the traditional Fault Tree Analysis (FTA). The reliability of the main lubrication oil system (GUB) increases from 0.169 to 0.261, representing a 9.2% improvement; under scheduled maintenance conditions, the system reliability stabilizes at approximately 0.9873 after $0.4\times {10}^5$ h, compared to only 0.24 without maintenance. The proposed method effectively evaluates the reliability of the lubrication oil system, and the maintenance strategy using this method can greatly improve the reliability, providing strong support for scientifically guiding maintenance decisions.

Rolling bearings constitute critical rotating components within rolling mill equipment. Production efficiency and the operational safety of the whole mechanical system are directly governed by their operational health state. To address the dual challenges of the over-reliance of conventional diagnostic methods on expert experience and the scarcity of fault samples in industrial scenarios, we propose a virtual–physical data fusion-optimized intelligent fault diagnosis framework. Initially, a dynamics-based digital twin model for rolling bearings is developed by leveraging their geometric symmetry. It is capable of generating comprehensive fault datasets through parametric adjustments of bearing dimensions and operational environments in virtual space. Subsequently, a symmetry-informed architecture is constructed, which integrates multi-scale convolutional neural networks with attention mechanisms and bidirectional gated recurrent units (MCNN-AT-BiGRU). This architecture enables spatiotemporal feature extraction and enhances critical fault characteristics. The experimental results demonstrate 99.5% fault identification accuracy under single operating conditions. It maintains stable performance under low SNR conditions. Furthermore, the framework exhibits superior generalization capability and transferability across the different bearing types.

Ship target detection is a prerequisite for achieving automated monitoring in ship detection systems. To address the challenge of accurately detecting ship targets in complex water environments, this study proposes a ship target detection method based on an improved YOLOv11 framework. To enhance the model’s ability to perceive and fuse features across multiple scales and in complex backgrounds, an Iterative Attention Feature Fusion (iAFF) module and a Biformer module are integrated at the end of the backbone network. The iAFF module iteratively optimizes multi-scale features through a two-stage attention mechanism, effectively focusing on key target regions, thereby improving the model’s detection capability for small, medium-sized, and occluded ships. The Biformer module leverages its innovative Bi-level Routing Attention (BRA) mechanism to enhance the modeling of global semantic information while reducing computational complexity, mitigating false detections caused by occlusions among ship targets, and consequently improving detection precision. This study employs the Minimum Point Distance Intersection over Union (MPDIoU) loss function, which more comprehensively measures the similarity between predicted and ground-truth bounding boxes by optimizing the distances of their key geometric points, effectively enhancing the accuracy of bounding box regression. Experimental results show that the proposed model achieved 93.96% mAP, 92.93% recall, and 94.97% precision on a self-built ship dataset, surpassing mainstream detection algorithms including YOLOv11 in multiple metrics. The model has only 2.90 M parameters, achieving a good balance between accuracy and efficiency. This provides an accurate and efficient solution for intelligent ship supervision.