Showing papers in "Ocean Engineering in 2021"
••
TL;DR: An enhanced convolutional neural network (CNN) is proposed to improve ship detection under different weather conditions by redesigning the sizes of anchor boxes, predicting the localization uncertainties of bounding boxes, introducing the soft non-maximum suppression, and reconstructing a mixed loss function.
118 citations
••
TL;DR: A novel deterministic algorithm named multiple sub-target artificial potential field (MTAPF) based on an improved APF is presented to make the generated path compliant with USV's dynamics and orientation restrictions and is validated on simulations and proven to work effectively in different environments.
111 citations
••
TL;DR: An AHP-FMEA methodology is proposed to analyse the floating offshore wind turbines failure causes and introduces the expert opinions to generate a risk index through the Analytical Hierarchy Process criteria weighting technique.
92 citations
••
TL;DR: Sun et al. as mentioned in this paper combined the multi-resolution δ + -SPH scheme and a total Lagrangian SPH method for more complex three-dimensional (3D) Fluid Structure Interaction (FSI) problems.
90 citations
••
TL;DR: The findings show that the modified optimizer and the designed classifier using mWOA significantly outperform the other benchmark classifiers.
86 citations
••
TL;DR: The rapid development of artificial intelligence significantly promotes collision avoidance navigation of maritime autonomous surface ships (MASS), which in turn provides prominent services in maritime environments and enlarges the opportunity for coordinated and interconnected operations.
83 citations
••
TL;DR: These path planning algorithms that deal with constraints and characteristics of AUV and the influence of marine environments are described and some potential future research directions that are worthy to investigate in this field are proposed.
78 citations
••
TL;DR: In this paper, a SPH (Smoothed Particle Hydrodynamics)-based multi-resolution fully Lagrangian mesh-free hydroelastic FSI (Fluid-Structure Interaction) solver is developed for accurate and adaptive reproductions of ocean engineering problems.
68 citations
••
TL;DR: In this paper, the authors presented a direct analysis methodology that makes use of Automatic Identification System (AIS) data to estimate collision probability and generate scenarios for use in ship damage stability assessment.
64 citations
••
TL;DR: In this article, a new strategy for finding tensile strength retention (TSR) using empirical models based on the strong non-linear ability of artificial intelligence techniques, i.e., artificial neuro-networking (ANN), gene expression programming (GEP), and adaptive neuro-fuzzy inference system (ANFIS), was presented.
62 citations
••
TL;DR: In this article, the authors investigated the cavity dynamics and trajectories of twin spheres vertically entering water side-by-side for different time intervals and several lateral distances at initial velocities from 14.1 to 15.2m/s, with the diameter (D) based Froude number varying from 37.0 to 40.0.
••
TL;DR: The advantages of TPNet and LSTM are combined in the proposed method and four parts are involved: the AIS data preprocessing method, the solutions of destination point and support point, and the uncertainty analysis, which indicates the validity of the method.
••
TL;DR: Wang et al. as mentioned in this paper proposed an unsupervised learning method which automatically extracts low-dimensional features through a convolutional auto-encoder (CAE), which can learn the lowdimensional representations of informative trajectory images.
••
TL;DR: The proposed Bayesian Network method is applied for the risk modelling of ship collision in narrow waters and is expected to help safety researchers validate their results.
••
TL;DR: Through Lyapunov stability analysis, it is verified that the proposed method is capable of ensuring asymptotic stability for tracking errors, and numerical simulation results reveal the advantage and effectiveness of this work.
••
TL;DR: A machine learning model based on Long Short-Term Memory neural networks for reconstruction and short- and long-term prediction of nearshore significant wave height (SWH), integrating bathymetric data for the first time is developed.
••
TL;DR: In this article, a single input Bi-LSTMC ship roll prediction method is proposed, which takes the advantage of LSTM time series prediction and combines convolution kernel to extract cross time features.
••
TL;DR: In the model, the dynamic and uncertainty features of the ship action dynamics in real operating conditions are considered, which could benefit on reducing ship collision accidents and improving the development of technologies on intelligent collision avoidance decision makings.
••
TL;DR: It follows from the theoretical analysis that finite-time convergence is achievable under the proposed two controllers and numerical simulations are exhibited to illustrate the effectiveness of the proposed formation control schemes.
••
TL;DR: In this article, a series of numerical pile penetration tests have been conducted by considering the influence of soil density, pile geometry and installation method, and the plug effect is more prevalent for jacked piles than dynamic installed piles.
••
TL;DR: A solution to existing challenging issues is proposed by introducing the digital twin (DT) technology into the OWT support structures and this new DT framework will enable real-time monitoring, fault diagnosis and operation optimization of the O WT support structures, which may provide a useful application prospect in the reliability analysis in the future.
••
TL;DR: An adaptive radial basis function (RBF) neural network controller is incorporated with a conditional integrator to deal with the uncertain model parameters, approximation errors and environmental disturbances in practical multi-AUV systems and results demonstrate the effectiveness of the proposed formation controller.
••
TL;DR: Both the DLSITs and PSTs suffer obvious high frequency interference arisen from the 3D effect of piles and the radius angle between the impact force location and the axial line of receiving sensors is advised to set as 90°.
••
TL;DR: Dynamic response and power output of this hybrid concept are evaluated and it is found the optimal control design for point-absorber WEC attached to fixed structures is no longer optimal for the combined floating wind and wave energy production platform, which needs further investigations in the future.
••
TL;DR: This paper proposes using optimised deep learning neural networks to forecast the wave energy flux, and other wave parameters, using moth-flame optimisation as the central decision-making unit to configure the deep neural network structure and the proper input data selection.
••
TL;DR: A novel method named as multiscale attention-based LSTM is presented, which achieves better performance compared with other popular methods in ship motion prediction and to avoid being trapped in local optimization.
••
TL;DR: A new leader-following consensus control protocol with time-varying delay for discrete-time multi-AUV recovery systems is proposed by modeling directed fixed communication topology.
••
TL;DR: A collision avoidance method that quantitatively assesses the collision risk and then generates an avoidance path that reliably avoided collisions through flexible paths for complex and unexpected changes in situations compared to the A* algorithm.
••
TL;DR: The significance and challenge of DSMV are presented, the existing deep-sea mining system in sea trial is reviewed and some existing issues and future study priorities are proposed.
••
TL;DR: A variety of bionic amphibious robots that have been designed over the past few decades are reviewed and some of the key technologies for their effective implementation are comprehensively analysed.