All hydraulic machinery has a tip clearance, which not only produces tip-leakage vortexes (TLVs), but also reduces the energy performance of the machinery. In addition, tip clearance leads to cavitation and attendant vibration and noise. Therefore, investigating tip-leakage cavitating flow and noise characteristics is of great practical importance. In this paper, the energy performance and noise characteristics of NACA0009 hydrofoils with different tip clearance sizes are studied. A large eddy simulation model and Schnerr–Sauer cavitation model are employed to simulate tip-leakage cavitating flow. Additionally, a broadband noise source model and the Ffowcs Williams–Hawkings (FW–H) equation are used to calculate the noise source and far-field radiated noise characteristics, respectively. Results show that the numerical simulation of cavitation vortex and velocity field is in good agreement with the experimental data, illuminating the characteristics of energy performance, flow pattern, cavitation flow, broadband noise source, and near-field and far-field radiated noise. Compared with the original NACA0009 hydrofoil, the tip clearance reduces the noise of the Curle dipole on the hydrofoil surface and Proudman noise around the hydrofoil. Moreover, study of the far-field noise shows that the directivity curve of the overall sound pressure level (SPL) is distributed in a butterfly shape, symmetrically. Evidently, the tip clearance size has a large impact on the energy performance of the hydrofoil, the intensity of the TLV, and the cavitation. This paper lays a solid foundation for further research on cavitation flow in large-scale hydraulic machinery.

The velocity of ocean currents significantly affects the trajectory prediction of ocean drifters and the safe navigation of intelligent vessels. Currently, most ocean current predictions focus on time-based forecasts at specific fixed points. In this study, deep learning based on the flow field prediction model (CNNs–MHA–BiLSTMs) is proposed, which predicts the changes in ocean currents by learning from historical flow fields. Unlike conventional models that focus on single-point current velocity data, the CNNs–MHA–BiLSTMs model focuses on the ocean surface current information within a specific area. The CNNs–MHA–BiLSTMs model integrates multiple convolutional neural networks (CNNs) in parallel, multi-head attention (MHA), and bidirectional long short-term memory networks (BiLSTMs). The model demonstrated exceptional modelling capabilities in handling spatiotemporal features. The proposed model was validated by comparing its predictions with those predicted by the MIKE21 flow model of the ocean area within proximity to Dalian Port (which used a commercial numerical model), as well as those predicted by other deep learning algorithms. The results showed that the model offers significant advantages and efficiency in simulating and predicting ocean surface currents. Moreover, the accuracy of regional flow field prediction improved with an increase in the number of sampling points used for training. The proposed CNNs–MHA–BiLSTMs model can provide theoretical support for maritime search and rescue, the control or path planning of Unmanned Surface Vehicles (USVs), as well as protecting offshore structures in the future.