This study aims to indirectly identify tire impact loads and their distribution characteristics by analyzing structural responses, providing a basis for deck design and safety assessment. A load inversion method based on Green's function is proposed.

The study focuses on the stiffened plate of a ship deck. The impact load is represented as a superposition of unit impulse loads based on Green's function. The Green's function kernel matrix is derived through finite element simulations. An inversion model is formulated by combining the Tikhonov regularization method with the generalized cross-validation （GCV） criterion. For both single and multiple tire impact scenarios, the influence of multi-source loads on inversion accuracy is analyzed. The load distribution characteristics for three typical wheel load distribution forms—convex, saddle, and concave—are inverted by equivalently dividing the force application area and applying unit impulse loads.

The proposed method effectively identifies the time history and distribution characteristics of tire impact loads, with a relative error of less than 5%. Specifically, the inversion based on strain and displacement responses achieves higher accuracy, with errors below 2%. Even with 5% noise interference, the inversion results remain consistent with the actual loads.

The proposed method addresses the challenges such as short impact load duration, limited structural response range, and multi-source impact load interactions. It provides a novel approach for identifying wheel loads on real ships, with significant engineering applicability.

The dynamic ultimate strength of a hull girder is a crucial parameter for assessing ship safety. In the context of ships being subjected to dynamic loads such as wave-induced and slamming loads during navigation, making accurate calculation of the dynamic ultimate strength of the hull girder is of great significance for ship designers to predict structural performance and ensure ship safety. However, existing research on the calculation of the dynamic ultimate strength of the hull girder remains limited, and traditional methods often face challenges in terms of computational efficiency. Therefore, this study aims to address the challenge of efficiently calculating the dynamic ultimate strength of a hull girder and proposes a more efficient calculation method.

The proposed approach is the dynamic Smith method, which is based on the traditional Smith method. Firstly, considering the strain rate effect of materials under dynamic load, the Cowper−Symonds model is introduced to modify the yield strength of materials. This modification is essential as the dynamic yield strength of materials increases with the increase of strain rate. Secondly, the stress−strain relationship of stiffened plate elements under different strain rates is taken into account. Xiong's empirical formula for the dynamic ultimate strength of stiffened plates is adopted to correct the stress−strain curve, ensuring more accurate calculation of member stress. Finally, the inertia force generated during the dynamic response of the hull girder structure is considered. By calculating the acceleration caused by the change of the neutral axis of the cross-section in the Smith method iteration process, the inertia force of each unit is obtained, and then the impact of inertia force on the dynamic ultimate strength is corrected.

The results show that when the angular velocity of the end-face rotation is less than 1, the error between the dynamic ultimate strength calculated by the dynamic Smith method and that by the finite element method is less than 10%. Specifically, for the box girder model and the hull girder model of a VLCC based on ISSC 2012, the dynamic Smith method shows strong agreement with the finite element results in the low-to-medium angular velocity range. However, when the angular velocity is greater than 1, the error between the two methods becomes larger.

In conclusion, the dynamic Smith method is a significant extension of the traditional Smith method. Compared with the finite element method, it can remarkably improve the calculation efficiency for calculating the dynamic ultimate strength of a hull girder, especially when the end-face rotation angular velocity is less than 1. For the correction of the stress-strain relationship curve in the dynamic Smith method, when the strain rate is less than 0.4, the stress-strain curve is calculated based on strain rate hardening; when the strain rate is greater than or equal to 0.4, the empirical formula is used. This research provides a novel approach to ship safety assessment and provides valuable guidance for ship design and structural strength analysis.

This study analyzes the influence of lateral loads on the ultimate strength and collapse modes of stiffened panels subjected to combined loads.

Nonlinear finite element software ABAQUS is used to set up numerical models and perform numerical simulations under combined loads on different models. The out-of-plane displacement fields are captured and decomposed with buckling modes. The modal amplitude-axial load curves of different models are obtained, and the deformation process of stiffened panels is quantified. The deformation behaviors and collapse modes of stiffened panels in different load cases are then analyzed in combination with cloud diagrams.

The results show that the lateral load in combined load cases causes the yielding of the stiffeners at the endings before the ultimate state, resulting in the increase of the overall buckling mode's amplitude. As the lateral load increases, the overall buckling of the stiffened panels becomes the dominant collapse mode under combined load cases.

The findings of this study reveal the relationship between local and global buckling mode amplitudes and collapse modes during the deformation process of stiffened panels, and can provide useful references for the design of ship frame structures.

As creating finite element models for the finite element analysis of ship structures is time-consuming and highly dependent on engineers' experience, this paper proposes a knowledge-based fast finite element modeling method to solve this problem.

The proposed method makes full use of the existing model data of the CAD system and shares model data between the CAD and CAE systems through model features. First, based on expert knowledge, the CAD geometric features are marked with engineering semantics to generate CAD information models. Second, the feature reduction of the CAD information model is carried out based on the constructed knowledge rules. Finally, the neutral file XML is used to construct a knowledge-based data transfer and matching method which allows the geometric features and attribute information to be matched with the pre-constructed CAE parameterized template, thereby speeding up the finite element modeling of the ship structure.

Taking the structural strength analysis of a 66000 DWT bulk carrier under typical loading conditions as an example, this approach can realize the automatic extraction, labeling and model reduction of the geometric model, boundary conditions and other information, and quickly complete the finite element modeling and analysis of the structure through the knowledge-based feature matching rules, effectively reducing data loss in the transmission process and realizing the reuse of knowledge.

The proposed fast finite element modeling method with embedded knowledge reuse rules improves the conversion efficiency of data, information and knowledge between the CAD and CAE systems, and has good universality and expansibility in practical engineering.

Low sampling rates on reconstruction surfaces cause high reconstruction error in near-field acoustic holography. Therefore, a deep learning-based approach which is applicable to planar sound sources and high-precision reconstruction with low sampling rates is put forward.

A three-dimensional N-shaped convolution neural network for near-field acoustic reconstruction is established to extract features in the frequency dimension in order to make up for sparse sampling in the spatial dimension. A frequency focal mechanism, namely an adaptive frequency weight focus mechanism, is put forward to improve reconstruction precision in the natural frequency and high frequency. Moreover, this paper also raises frequency-scaled focal loss and frequency-scaled focal Kirchhoff–Helmholtz(KH)loss, which are considered regularization. To validate the proposed methods, datasets are created with COMSOL Multiphysics and Matlab.

The mean error range of 100–2 000 Hz of the algorithm proposed in this paper is only 4.96%, higher than those of SRCNN and PV-NN.

The proposed method is verified as having the potential to reconstruct the accurate velocity fields of sound sources under low sampling rates.

This study aims to explore the law of the critical compression stress of stiffened panels under the influence of in-plane shear load, and whether in-plane shear load combined with lateral pressure will introduce a strong coupling effect.

To this end, nonlinear finite element (FE) software ABAQUS is used to perform numerical simulation analysis under combined loads on a group of FE models. A limit state equation/curve is then derived from the dimensionless calculation results based on the minimum square error method.

The results show that the influence law of in-plane shear load on the critical compression stress of stiffened panels is clarified, and a limit state equation of stiffened panels that considers the effect of shear load is obtained.

The limit state equation in this paper can provide references for modifying the ultimate strength of stiffened panels under the influence of in-plane shear load.

With the development of intelligent ships, it has been difficult for traditional crack damage detection methods to meet the detection requirements. This paper proposes a real-time crack damage detection method for box girders based on a gated recurrent unit (GRU) neural network.

Using the secondary development technology of Abaqus based on the Python language, a box girder crack damage model is built, and its acceleration response under dynamic Gaussian white noise excitation is calculated. A dataset is generated by expanding the original data using the data cropping method, and the influence of noise is considered. A box girder crack damage detection model based on GRU is established, the acceleration response dataset is directly used as input and the minimum loss function value is used as a target to train the model. This method is then compared to the wavelet packet transform-based multi-layer perceptron (WPT-MLP) model.

The comparison shows that the GRU model proposed in this paper has higher detection accuracy than the WPT-MLP model in damage location and extent detection. It is less sensitive to noise and has higher accuracy in approximate prediction.

The results of this study verify the applicability of GRU neural networks in the crack damage detection of box girders containing multiple plates.

In view of the incomplete evaluation of the ultimate strength of I-core sandwich panels in the past, a BP artificial neural network method is proposed to quantitatively determine the influence of relevant parameters on the ultimate strength of I-core sandwich panels.

First, the ultimate strength of I-core sandwich panels under axial compression are investigated using the nonlinear finite element method. Second, a BP neural network is constructed to predict the ultimate strength of I-core sandwich panels with different plate slenderness ratios between longitudinal webs, plate slenderness ratios of webs and column slenderness ratio of one longitudinal web. Finally, a formula for predicting the ultimate strength of I-core sandwich panels using the artificial neural network weight and bias method is proposed.

The mean square error MSE and correlation coefficient R of ultimate strength prediction using the BP neural network method are 0.001 2 and 0.981 8 respectively. The proposed neural network model has good prediction accuracy, and the maximum error is less than 10%.

This study can provide references for the application of I-core sandwich panels in hull structures.