Search

In order to handle the problem of complex and time-consuming simulation calculation in hull form optimization, the approximate model based on adaptive sampling has been widely used. In this paper, a maximum entropy (ME) adaptive sampling method based on uniform design (UD) is developed based on the Kriging approximate model and the leave-one-out (LOO) error method. Compared with the incremental Latin hypercube design (LHD) method, the adaptive sample distribution obtained by the proposed method are more uniform, and the accuracy of the global approximation model is higher. The proposed method is applied to the S60 hull form optimization, and the effectiveness is verified.

While navigating at sea, ships are influenced by various factors, including wind, waves, and currents, which can result in heave motion that significantly impacts operations and potentially leads to accidents. Accurate forecasting of ship heaving is essential to guarantee the safety of maritime navigation. Consequently, this paper proposes a hybrid neural network method that combines Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory Networks (BiLSTMs), and an Attention Mechanism to predict the heaving motion of ships in moderate to complex sea conditions. The data feature extraction ability of CNNs, the temporal analysis capabilities of BiLSTMs, and the dynamic adjustment function of Attention on feature weights were comprehensively utilized to predict a ship's heave motion. Simulations of a standard container ship's motion time series under complex sea state conditions were carried out. The model training and validation results indicate that, under sea conditions 4, 5, and 6, the CNN-BiLSTM-Attention method demonstrated significant improvements in MAPE, APE, and RMSE when compared to the traditional LSTM, Attention, and LSTM-Attention methods. The CNN-BiLSTM-Attention method could enhance the accuracy of the prediction. Heave displacement, pitch displacement, pitch velocity, pitch acceleration, and incoming wave height were chosen as key input features. Sensitivity analysis was conducted to optimize the prediction performance of the CNN-BiLSTM-Attention hybrid neural network method, resulting in a significant improvement in MAPE and enhancing the accuracy of ship motion prediction. The research presented in this paper establishes a foundation for future studies on ship motion prediction. [ABSTRACT FROM AUTHOR]

This study analyzes the effect of nozzle geometry on the dynamic characteristics of water jets. The flow characteristics of Helmholtz oscillators with three different nozzle shapes (four, six, and eight petals) are investigated using large eddy simulations. The relationship between coherent structures and cavitation is illustrated using the vortex transport equation. The results show that the evolution of cavitation clouds in a Helmholtz cavity results in a periodic change in the jet pressure and the formation of pulsed water jets from petal-shaped nozzles. In addition, the cavitation bubbles inhibit the stretching and expansion of the vortex structure, and the convergence of the turbulent kinetic energy is conducive to maintaining its stability. The four-petal nozzle has the highest velocity at the central axis of the jet at 1.76% higher than that of the six-petal nozzle. When the number of petals in the nozzle is increased from six to eight, the velocity decreases by 7.96%. The streamwise vortex strength of the jet with six petals is enhanced by 61.31% compared to the four-petal case, while the eight-petal nozzle jet is only 11.75% higher than that of the six-petal nozzle. The six-petal nozzle significantly improves the mixing characteristics by slightly reducing the velocity. This study provides guidance for reducing the stagnation pressure loss when using nozzles with special shapes to enhance jet mixing. [ABSTRACT FROM AUTHOR]

Intelligent underwater vehicles hover by way of a hovering control system. To provide design inputs and maneuver guidance, this study focused on the characteristics of intelligent underwater vehicles during hovering control with the propulsion system shut down, established a mathematical model of hovering control and determined injection and drainage functions based on optimal control theory. From analysis simulation experiments, the influence laws of control parameters, control timing and rate of injection and drainage control upon hovering control were deduced. It is proposed that, at the time of control parameter selection, the continuous injection and drainage rate at each time should be reduced as far as possible to relieve the demand on the volume of the reservoir when the requirement of depth control accuracy has been satisfied. In addition, the injection and drainage control should initiate when depth changes exceed 0.5 m. Suggestions are included on the minimum injection and drainage rate required for different initial disturbances. The proposed suggestions guide the design of hovering control systems and hovering control over intelligent underwater vehicles. [ABSTRACT FROM AUTHOR]

Sampling method is an effective tool for building approximated models, which can improve the efficiency of hull form optimisation. A dynamic sampling method (DSM) is introduced herein to improve the accuracy and efficiency of the approximated model by considering the influences of sample quality measures in both input and output parameter spaces. The DSM uses leave-one-out to obtain an estimate of the cross-validation errors, which are maximised to determine the sample points in the design space. The variation is used for the calculation of continuous and multimodal regions. The proposed method is compared, using both numerical examples and hull form optimisation, with traditional sampling methods from the literature. The stem profile's optimisation for KCS based on DSM and static sampling method is performed. And the optimised hull form with less ship resistance is obtained. The comparison results show that DSM performs better than the static sampling method. Abbreviations: AM: approximated models; ACE: accumulative error; AMDSM: approximated models based on dynamic sampling method; AMUD: approximated models based on uniform design; CAMM: continuous and multimodal; CF: covariance function; CFD: computational fluid dynamics; CV: cross validation; CVV: cross validation variance; DSM: dynamic sampling method; eLOO: leave-one-out error; LOO: leave-one-out; LHS: Latin Hypercube Sampling; MAPE: mean absolute predictive error; MCS: Monte Carlo Sampling; NN: neural network; RAAE: relative average absolute error; RMSE: root mean square error; SM: sampling methods; SP: sample points; SSM: static sampling method; TS: test samples; UDL: uniform design; VF: variation function. [ABSTRACT FROM AUTHOR]