Conventional resistance prediction method of proxy models takes main scale ratios, ship form coefficients, and other similar parameters as inputs. Compared to CFD calculations, in which the complete hull form is used as input, prediction method with lower information density of proxy models results in lower prediction accuracy. In this paper, a high-dimensional, high-precision resistance prediction method was proposed for ship hulls using 4108 sets of complete hull geometry feature tensors as input and employing neural networks as proxy models. The total resistance coefficient of the ship was taken as the output. Dimensionless treatment of the hull forms was conducted at first and feature tensors were extracted as inputs. Next, a neural network model was constructed, comprising input layers, hidden layers, and an output layer. Finally, the feature tensors of the hull forms and the corresponding total resistance coefficients were fed into the neural network, and the model was trained using error back propagation until the loss function converges. The research findings in this paper can provide theoretical and technical support for high-dimensional proxy model-based resistance performance prediction.

Fatigue damage assessment for marine structures subjected to various random environmental loadings is an important issue at the design stage. In many situations, the responses of marine structures present wide-band and non-Gaussian properties. In this paper, a neural network model was developed to predict the fatigue damage caused by wide-band non-Gaussian random processes. Many power spectra with different values of bandwidth parameters, inverse slope of the S-N curve, and skewness and kurtosis of non-Gaussian processes were used to train and validate the developed neural network model. In order to determine the optimal neural network structure, the effects of input neurons, the numbers of hidden layer neutrons and hidden layers on the prediction accuracy were investigated. Through case studies with realistic bimodal spectra, by taking the fatigue damage estimated by time-domain rain-flow counting method as reference, it is demonstrated that the developed neural network model is more accurate and robust than the existing frequency-domain methods for fatigue damage assessment of wide-band non-Gaussian random processes.

High-resolution time variant flow field data is the key to the study of turbulence flow. Limited by measurement methods, simulation efficiency and data storage, it is still difficult to obtain high-resolution turbulent flow data directly in some circumstances. In this paper, based on the low-dimensional representation model of flow time-history data, a neural network-based feature coding prediction model and high-resolution turbulence flow reconstruction method were proposed. Firstly, a low-dimensional representation model of the turbulence flow was established based on the one-dimensional convolution networks; then, an artificial neural network model was employed to establish the mapping between the measuring point coordinates and feature coding system, and the prediction of feature coding for the unknown measuring points was realized; finally, based on feature coding, the decoder in the representation model was utilized to generate turbulence flow time history data at unknown positions. Turbulence flow with Re=2.2×10⁴ around a square cylinder was studied, and the low dimensional representation model and flow generation model were trained and verified. The method proposed in this paper is a high-precision turbulence flow data reconstruction method which can be widely used in one-point-based sensor data processing. It is a new approach for the reconstruction of turbulence flow field time-history data.

Riser deployment is an important step in deepwater drilling, during which the spider is the primary support of the riser system. At the same time, the harsh deepwater environment leads to a high risk of riser deployment. To ensure the safety of riser deployment, firstly, a joint distribution model of environmental parameters was constructed. Then, an intelligent prediction model of structural response based on IAGA-BRNN was determined. Finally, the method of structure reliability assessment for riser deployment was established combining Monte Carlo, and a case study was carried out. Results show that most parameters in the joint distribution model of environment obey Weibull distribution and Beta distribution. The prediction model proposed in this paper performs well in all the prediction indicators, and has a stronger prediction ability compared with the conventional prediction model. The equivalent stress and maximum axial force are the first and secondary limitation factors of the riser deployment. In addition, as the number of hang-off riser increases, the reliability is on the decline, and wave height is the main limiting factor of operational reliability.

For low-frequency line spectrum control in naval and other engineering fields, a nonlinear energy sink vibration isolation system dynamics model considering a flexible foundation was established, and the nonlinear dynamics of the system was analyzed using the harmonic balance method and Runge-Kutta method. The influence of the foundational parameters on the amplitude-frequency characteristics of the system was explored, and the nonlinear dynamical behavior of the system at the resonant frequency was analyzed. The influence law of mass ratio, cubic stiffness, and damping on the damping effect of nonlinear energy sink was explored with vibration power flow as the evaluation parameter. For the computational model analyzed, research shows: when the foundation stiffness is weak, the nonlinear energy sink has a large effect on the amplitude and frequency response characteristics of the equipment; for specific parameters, the state of motion of the base and the equipment at the first order resonant frequency may be different; the nonlinear energy sink has a superior damping effect, reducing the peak power flow to the base by 13.95 dB in this example.

Cavitation is a widely-existing fluid dynamics phenomenon in nature, and its theoretical modeling and numerical simulation methods have long formed an important direction in the field of fluid mechanics. In this paper, the essence of phase transition in cavitation, the mathematical and physical description of cavitation flows, especially the main research results of cavitation models for numerical simulation of cavitation flows are reviewed, providing support for the study of cavitation flow.

In this paper, the open-source computational fluid dynamics software OpenFOAM was used to simulate the effect of plunging breaker waves and non-breaking waves on the typical column of an offshore platform in the extreme ocean environment. The purpose was to compare and analyze the variation of wave loads and structural stress in the column under the above two wave types. The motion of the fluids was simulated based on the Reynolds-averaged Navier-Stokes equations combined with k-ω SST turbulence model. The numerical results show that the breaking wave load on the column is much higher than the non-breaking wave load under the same design wave parameter input. The maximum stress values for each structure of the column under non-breaking wave loads are less than the yield limit of material. However, under the plunging breaker load, the maximum stress of some structures exceeds the yield limit of materials and cannot meet the requirements of structural safety. Therefore, the impact of breaking wave load on structural strength should be considered in the safety design of marine structures to ensure that the structure has sufficient safety margins.

Welding residual stress has a significant impact on the fatigue life of a welding structure. Meanwhile, welding residual stress is not invariable, but will be redistributed with crack propagation. Therefore, the coupling study of welding residual stress redistribution and crack propagation is very important to predict the fatigue life of a welded structure accurately. Based on thermal elastic-plastic finite element method and extended finite element method (XFEM), a fatigue life analysis method considering the coupling of residual stress redistribution and crack propagation was proposed in this paper. Taking the tensile fatigue sample of TC4 titanium alloy as an example, the redistribution of the welding residual stress along with crack propagation was studied with the extended finite element method. The welding residual stress distribution in front of the crack tip during crack propagation and the fatigue crack propagation a-N curve under the redistribution of weld residual stress were calculated by cyclic iteration. The calculation results show that the welding residual stress at the crack tip increases firstly and then decreases with the crack propagation. Compared with the results based on constant value of the residual stress, the extended finite element fatigue life analysis method considering the redistribution of the residual stress is more accurate to predict the fatigue lives of welding structures.

The exciting forces generated by the propeller during ship operation will cause the vibration of propulsion shafting, and the shafting vibration will also have feedback to the propeller, causing complex spatial motion. There is a two-way fluid-structure coupling problem in the propeller-shafting system. To investigate this complex dynamic problem, the numerical model for simulating the coupling of shafting multi-degree-of-freedom vibration and propeller viscous flow field was established in this paper, based on the finite element (FEM) and computational fluid dynamics (CFD) methods. The iterative solution of the two-way coupling was realized by carrying out secondary development in the flow field solver, and several numerical examples were simulated to study the variation characteristics of fluid exciting and vibration response. The results show that, the simulation method proposed in this paper has practical values, and the convergence and accuracy of the two-way fluid-structure coupling simulation can meet the engineering requirements. The computing speed for solving the coupling system of this method is fast, and no additional computing resources are required. The two-way coupling effect and unbalanced mass have significant influence on the amplitudes at rotating frequency while the non-uniform inflows have significant influence on the amplitudes at blade passing frequency.

Aluminum alloys have been widely used in the ship industry for their low density, high specific strength and specific stiffness. However, compared with steel, the strength of aluminum alloy is low. To improve its strength, JDA1b aluminum alloy, which is often used in die casting and outfitting parts of ships, was taken as the research object. Pre-strain tensile, pre-bend tests and dynamic tensile tests were carried out to investigate the effects of pre-strain and pre-bend on the mechanical performance of JDA1b alloy, and the effects of strain rate on the flow behaviors of the alloy were also investigated. The results show that increasing the strain rate can increase the flow stress and tensile strength of the material; the yield stress and tensile strength of this material increase with the increase of pre-strain, and the elongation decreases, and that the increase of pre-bend is favorable to improve the bending yield load, bending stiffness and damage displacement of the material. A new dynamic constitutive model considering ultimate stress and critical strain was proposed, which allows the flow stress to be predicted more precisely at various strain rates over a wide range of 1~800/s, and the fitting goodness-of-fit value reached 0.999. This study provides methods to improve the strength of aluminum alloys, and the proposed constitutive model is conducive to the improvement of the accuracy of the simulation of mechanical performance of parts.