The reliability of hydraulic pipelines in waterjet propulsion devices is crucial to the navigation safety of waterjet-propelled ships. To overcome the limitations of traditional methods in real-time detection, positioning accuracy, and environmental adaptability, this paper proposes a method for leak detection and localization of waterjet propulsion pipelines based on a backpropagation (BP) neural network and Amesim simulation. A hydraulic system simulation model of a certain type of waterjet propulsion device is built using Amesim software and system simulation signals under different pipeline leak locations are collected to form the dataset. A BP neural network model is then constructed, trained, and validated to achieve fault localization. The prediction results of the BP neural network model are in good agreement with experimental measurements, showing a strong linear relationship, which indicates that the BP neural network model has satisfactory predictive performance. This study can provide a technical reference for precise leak localization and condition assessment of hydraulic pipelines in complex ship cabin environments.

This paper focuses on the fluid-structure interaction (FSI) phenomena occurring during the operation of the composite rotor blades of the underwater vehicle thruster. The bidirectional FSI numerical method based on the finite element method (FEM) in ABAQUS and the computational fluid dynamics (CFD) method in STAR CCM+ has been used to calculate and analyze the open water performance, pressure distribution, blade deformation and stress of the composite blades in unsteady flow field under different advance coefficients. In addition, two solutions for negative volume mesh are proposed. The results show that the FSI effect on the composite rotor can cause partial thrust loss, and the vibration frequency of the composite blades in the FSI process mainly concentrates near the first-order blade frequency. When the advance coefficient is lower, it is also observed that the larger the axial load on the blades, the greater the axial deformation, and vice versa. The maximum stress caused by the FSI effect occurs on the root of the pressure side of the blade and the smaller the advance coefficients, the greater the maximum stress. The FSI effect is significant under low advanced coefficients. Both solutions can effectively solve the negative volume mesh problem.