Accurately evaluating the buoyancy and stability of damaged ships, particularly the flow rate of the water inflow through damaged openings, is of great significance for ship rescue and emergency repair. A three-dimensional simplified model of inflow for a ship’s damaged side bulkheads is established using the shear stress transport k-epsilon and volume of fluid (VOF) models by STAR-CCM+. Moreover, the flow rates of water inflow through damaged openings with different shapes, characteristic sizes, and central depths are calculated. Furthermore, the corresponding discharge coefficients are obtained, and the relevant rules are summarized. It was found that the influence of water depth on the coefficient is minimal in these work conditions, but from the perspective of the damaged opening’s characteristic dimensions and shape, the variation in the coefficient is more pronounced. Overall, the triangular opening has a higher coefficient than the circular opening, which in turn is higher than that of the square-damaged opening, and the coefficient decreases as the size of the opening increases. Lastly, empirical formulas for two different methods are provided. The research provides a reference for the rescue repair and buoyancy stability assessment of damaged ships.
The rapid and accurate assessment of residual ultimate strength after ship damage is crucial for rescue decision-making and navigation safety, while traditional methods struggle to meet the demands of complex random damage scenarios in terms of efficiency or accuracy. This study proposes a hybrid framework that integrates high-fidelity nonlinear finite element simulation (FEM) and a Bayesian-regularized backpropagation neural network (BPNN). FEM is used to accurately simulate a large number of random damage scenarios, generating a physically credible benchmark dataset. BPNN serves as an efficient surrogate prediction model, with its key parameters—the number of hidden layers and the training algorithm—systematically optimized to enhance generalization capability. The results show that: 1) The FEM simulation results deviate by less than 5% compared to the Smith method, validating the reliability of the dataset. 2) The prediction performance of BPNN is highly dependent on the number of hidden layers and the training algorithm, exhibiting non-monotonic variation, with an optimal parameter combination identified as 8 hidden layers paired with the Bayesian algorithm, achieving a prediction regression value R of 0.91662. 3) Deep networks are prone to overfitting, while shallow networks suffer from insufficient feature capture. 4) The Bayesian algorithm performs best in terms of overfitting resistance and stability. This study not only provides a high-precision and efficient intelligent solution for residual strength assessment of damaged hulls, but its systematic neural network parameter optimization strategy, particularly the approach of identifying optimal depth and selecting anti-overfitting algorithms, also offers important reference for the design of intelligent damage assessment models for similar engineering structures.
The rapid and accurate assessment of residual ultimate strength after ship damage is crucial for rescue decision-making and navigation safety, while traditional methods struggle to meet the demands of complex random damage scenarios in terms of efficiency or accuracy. This study proposes a hybrid framework that integrates high-fidelity nonlinear finite element simulation (NFEM) and a Bayesian-regularized backpropagation neural network (BPNN). NFEM is used to accurately simulate a large number of random damage scenarios, generating a physically credible benchmark dataset. BPNN serves as an efficient surrogate prediction model, with its key parameters—the number of hidden layers and the training algorithm—systematically optimized to enhance generalization capability. The results show that: (1) The NFEM simulation results deviate by less than 5% compared to the Smith method, validating the reliability of the dataset. (2) The prediction performance of BPNN is highly dependent on the number of hidden layers and the training algorithm, exhibiting non-monotonic variation, with an optimal parameter combination identified as 8 hidden layers paired with the Bayesian algorithm, achieving a prediction regression value R of 0.91662. (3) Deep networks are prone to overfitting, while shallow networks suffer from insufficient feature capture. (4) The Bayesian algorithm performs best in terms of overfitting resistance and stability. This study not only provides a high-precision and efficient intelligent solution for residual strength assessment of damaged hulls, but its systematic neural network parameter optimization strategy, particularly the approach of identifying optimal depth and selecting anti-overfitting algorithms, also offers an important reference for the design of intelligent damage assessment models for similar engineering structures.