In order to establish a proper geometry of an Unmanned Underwater Vehicle (UUV) for stable motion control and energy usage reduction, this paper analyzes the hydrodynamic performance of a complex shape underwater vehicle and develops a systematic Computational Fluid Dynamics (CFD) simulation method to solve the hydrodynamic parameters of the system. Based on the simulation method and their results, the streamlines and pressure distributions of the water flow around the underwater vehicle are analyzed, and the geometric model design is improved based on the drag characteristics. Also, a comparison scheme is designed to evaluate the vehicle model before and after the geometry improvement. Simulation result shows that the design schemes brings 18% drag reductions in surge direction and 32% in heave direction. Moreover, by establishing the physical and mathematical models of the UUV on a physical simulation platform, a complete model of the underwater vehicle is constructed, laying the foundation for further simulations and experiments.

Remotely operated underwater vehicles (ROVs) have been widely used in deep-sea resource exploitation and industrial engineering operations. To perform these tasks accurately in the deep-sea environment, stable motion control has become a key area of research on ROV systems, which has led to the importance of analyzing the hydrodynamic characteristic of ROVs. But a systematic methodology for analyzing the hydrodynamic characteristics of ROVs is still lacking nowadays. In this paper, systematic numerical simulation methods for analyzing hydrodynamic characteristics and shape optimization of a work-class ROV are conducted, and details of simulation procedures based on computational fluid dynamics are studied, which can be a foundation for robust controller design.

Submarine pipelines are the main means of transporting oil and gas produced offshore. The present work proposed a deep learning technology to identify damage caused by characteristic events and abnormal events using pipeline images collected by remotely operated vehicles (ROVs). The EfficientNet and You Only Look Once (YOLO) models were used in this study to classify images and detect events. The results show that the EfficentNet model achieved the highest classification accuracy at 93.57 percent, along with a recall rate of 88.57 percent. The combining of the EfficentNet and YOLOv5 models achieved a higher accuracy of detecting submarine pipeline events and outperformed any other methods. A new decision-making system that integrates the operation and maintenance of the model is proposed and a convenient operation is realized, which provides a new construction method for the rapid inspection of submarine pipelines. Overall, the results of this study show that images acquired via ROVs can be applied to deep learning models to examine submarine pipeline events. The deep learning model is at the core of establishing an effective decision support system for submarine pipeline inspection and the overall application framework lays the foundation for practical application.