Real-time prediction of hull girder loads is of great significance for the safety of ship structures. Some scholars have used neural network technology to investigate hull girder load real-time prediction methods based on motion monitoring data. With the development of deep learning technology, a variety of recurrent neural networks have been proposed; however, there is still a lack of systematic comparative analysis on the prediction performance of different networks. In addition, the real motion monitoring data inevitably contains noise, and the effect of data noise has not been fully considered in previous studies. In this paper, four different recurrent neural network models are comparatively investigated, and the effect of different levels of noise on the prediction accuracy of various load components is systematically analyzed. It is found that the GRU network is suitable for predicting the torsional moment and horizontal bending moment, and the LSTM network is suitable for predicting the vertical bending moment. Although filtering has been applied to the original noise data, the prediction accuracy still decreased as the noise level increased. The prediction accuracy of the vertical bending moment and horizontal bending moment is higher than that of the torsional moment.

Hydrodynamic performance plays an important role on energy consuming and safety for autonomous underwater vehicles (AUVs). The hydrodynamics of the whole process of AUV free running pushed by a rotating propeller was investigated with physics-based simulations by using multi-block hybrid dynamic grids method, URANS, coupled to 6DOF and UDFs. The AUV had cruised for approximately 14.1 s and 7.105 m from stationary to a constant velocity at 300RPM. The simulation results included an acceleration state and a steady state. In the acceleration state, the thrust decreased quickly and had four periodic cycles in one propeller revolution. The thrust amplitude varied as the velocity increased. The computed velocity history was compared to tests and agreed well. In the steady state, the propulsion factors were compared with that in the literature and agreed well. The flow field variations of pressure and velocity were investigated temporally and spatially for the two states.

Underwater gliders have emerged as effective tools for long-term ocean exploration. Employing aircraft for launching underwater gliders could significantly expand their application. Compared to slender underwater vehicles, the distinctive wing structure of underwater gliders may endure huge impact forces when entering water, leading to more intricate impact load characteristics and potential wing damage. This paper employs a computational fluid dynamics approach to analyze the water entry event of an airdropped underwater glider and its impact load behavior. The results indicate that the glider impact load is enhanced prominently by the wing, and that the extent of enhancement is influenced by the entry attitude. At an entry angle of 80°, the glider exhibits the maximum impact load during different water entry angles. In addition, a larger attack angle indicates a higher glider impact load. Our present study holds significant importance for both the hydrodynamic shape design and water entry strategy control of airdropped underwater gliders.