Search

Recently, transformers have demonstrated notable improvements in natural advanced visual tasks. In the field of computer vision, transformer networks are beginning to supplant conventional convolutional neural networks (CNNs) due to their global receptive field and adaptability. Although transformers excel in capturing global features, they lag behind CNNs in handling fine local features, especially when dealing with underwater images containing complex and delicate structures. In order to tackle this challenge, we propose a refined transformer model by improving the feature blocks (dilated transformer block) to more accurately compute attention weights, enhancing the capture of both local and global features. Subsequently, a self-supervised method (a local and global blind-patch network) is embedded in the bottleneck layer, which can aggregate local and global information to enhance detail recovery and improve texture restoration quality. Additionally, we introduce a multi-scale convolutional block attention module (MSCBAM) to connect encoder and decoder features; this module enhances the feature representation of color channels, aiding in the restoration of color information in images. We plan to deploy this deep learning model onto the sensors of underwater robots for real-world underwater image-processing and ocean exploration tasks. Our model is named the refined transformer combined with convolutional block attention module (RT-CBAM). This study compares two traditional methods and six deep learning methods, and our approach achieved the best results in terms of detail processing and color restoration. [ABSTRACT FROM AUTHOR]

Aiming to address the multi-objective cooperative optimization problem of ship structure lightweight and crashed-resistance, this study proposed a concave reentrant honeycomb-based negative Poisson's ratio (NPR) sandwich structure to replace the stiffened plate. The feasibility of using the sandwich structure to improve ship crashworthiness is demonstrated through finite element analysis. An intelligent optimization method is established to address the issues of multiple parameters and complex effects associated with composite structures and optimize the crashworthiness of the sandwich structure. The effectiveness of the optimization method and the feasibility of the NPR sandwich structure in ship crashworthiness have been validated, providing a reference for the design of new multi-functional ship structures. [ABSTRACT FROM AUTHOR]

In this paper, the novel pendulum tuned mass damper model has been suggested as a potential practical engineering modification to an existing offshore crane setup. A number of potential numerical singularities have been circumvented and substantial numerical model accuracy has been reached. Main application of this study would be extreme value statistics, in case of e.g. extreme weather conditions causing collision between vessel and payload. Next, extreme statistics of random vibrations has been studied in this paper for a suggested pendulum tuned mass damper model under white noise excitation. Restoring force has been modelled as the elastic non-linear, and numerical comparison has been performed with the linearised restoring force model case to see the force non-linearity effect on the vessel payload response statistics. The statistics of non-linear case has been studied by applying the path integration method, based on the Markov property of the coupled dynamic system. [ABSTRACT FROM AUTHOR]

Robust prediction of extreme motions during wind farm support vessel (WFSV) operation is an important safety concern. In particular, it is important to study safety of operation in random sea conditions during WFSV docking against the wind tower, while workers are able to get on to the tower. Docking is performed by thrusting the vessel fender against the wind tower (the alternative docking maneuver by hinging is not studied here). In this paper, the finite element software AQWA has been used to analyse the vessel response due to hydrodynamic wave loads, acting on a specific maintenance ship under actual sea conditions. Excessive motions may occur during certain sea conditions, posing a risk to the crew transfer operation. This paper presents a novel method for estimating bivariate statistics, based on Monte Carlo simulations (or measurements if available). The bivariate average conditional exceedance rate (ACER2D) method is briefly outlined. [ABSTRACT FROM AUTHOR]

Accurate fatigue assessment of ship structures is an important part of the structural reliability. As a result of accumulated fatigue damage, fatigue cracks may occur earlier than expected in critical locations of ocean-crossing ships. In many practical cases, the data set needed for accurate fatigue damage estimation, can be obtained by either numerical simulation or direct measurement, but in practice the size of the above-mentioned data set is often limited and not large enough for accurate direct fatigue damage calculation. The objective of this paper is therefore to contribute to development of novel fatigue estimation techniques that utilise available limited data set more efficiently. The continuous stress time series covering nearly two years duration has been analysed in this paper. Rainflow counting method was subsequently used for the accumulated fatigue damage assessment. An efficient distribution tail extrapolation technique has been proposed to accurately predict fatigue damage. The proposed technique utilises available data more efficiently, than direct fatigue estimation. [ABSTRACT FROM AUTHOR]

To predict the anti-penetration performance of protective structures, the ballistic performance of sandwich plates with steel face-sheet and aluminum foam core, the quasi-static compressive experiments of four different aluminum foam are performed and analyzed. The failure mechanism, mechanical parameters, and modified constitutive model are obtained. The virtual tests using numerical simulation were carried out in different penetration velocities based on quasi-static experimental constitutive parameters. Influence of projectile shape, face-sheet thickness, core thickness, and core densities on the residual velocity and plastic deformation of sandwich plates are discussed, while typical penetration failure modes and deformation mechanism are presented and analyzed. The failure modes of sandwich plates are different for hemisphere- and blunted-nosed projectile and the projectile shape influence is significant for ballistic performance when the penetration velocity approaches ballistic limit. The ballistic limit increases with increase of face-sheet or core thickness, core density and which shows an approximate linear relationship. [ABSTRACT FROM AUTHOR]

A new kind of higher order analysis model is presented for sandwich plates with flexible core, especially “soft” core. The governing equations derived from equilibrium differential equations of motions are analytically solved for simply supported sandwich plate with a flexible core. The Navier-type solutions for free vibration analysis and static bending are presented for sinusoidal and uniformly distributed loads. The accuracy and convergence of the present theory and solution are ascertained by comparing with various available results, the author considered vary of length-to-width ratios, Young’s modulus ratios between skins and core, thickness ratios between skins and core, and span-to-thickness of sandwich plates. The results show that the present theory can achieve the great accuracy for sandwich plate with flexible core by comparing with existing classical plate theory, first-order shear deformation, higher order shear deformation theory, and finite element software ANSYS. [ABSTRACT FROM AUTHOR]

The three-dimensional vibration of a functionally graded sandwich rectangular plate on an elastic foundation with normal boundary conditions was analyzed using a semi-analytical method based on three-dimensional elasticity theory. The material properties of the sandwich plate varied with thickness according to the power law distribution. Two types of functionally graded material (FGM) sandwich plates were investigated in this paper: one with a homogeneous core and FGM facesheets, and another with homogeneous panels and an FGM core. Various displacements of the plates were created using an improved Fourier series consisting of a standard Fourier cosine series along with a certain number of closed-form auxiliary functions satisfying the essential boundary conditions. The vibration behavior of the FGM sandwich plate, including the natural frequencies and mode shapes, was obtained using the Ritz method. The effectiveness and accuracy of the suggested technique were fully verified by comparing the natural frequencies of sandwich plates with results from investigations of other functionally graded sandwich rectangular plates in the literature. A parametric study, including elastic parameters, foundation parameters, power law exponents, and layer thickness ratios, was performed, and some new results are presented. [ABSTRACT FROM AUTHOR]