... algorithm eigenvalue sample data navigation recognition accuracy university identification yangtze river fusion Proceedings of the Thirty-second (2022) International Ocean and Polar Engineering Conference Shanghai, China, June 5 10, 2022 Copyright © 2022 by the International Society of Offshore...

... respectively. The amount of computation resulting from multi-disciplinary optimization can be substantially reduced by the application of Kriging model. Thirdly, a multi-objective genetic algorithm, NSGA-II, is adopted to produce Pareto-optimal front. Eventually, the optimal design schemes with obvious stealth...

... interest, and we focus on the analysis of wind waves and surface currents. We applied several ML models to reproduce observed time series and produced short- and long-term forecasts. LSTM model and XGBoost algorithms showed better results in fitting the observed curve. At the current stage of our research...

.... Subsequent experiments will use observers of real-time real-world waves as target waves for further learning. machine learning simulation algorithm reinforcement learning observation point target wave artificial intelligence irregular wave openfoam solitary wave superposition wave...

... decision-making of underwater vehicles, and achieved some results, mainly including grey prediction model, neural network method, fuzzy logic algorithm, sliding mode algorithm and so on. Neural network method is widely used in system prediction and fault diagnosis because of its adaptive learning ability...

... romberg quadrature method calculation time panel method water depth free surface green function algorithm engineering newman velocity potential reservoir simulation wave-structure interaction problem program fluhan software wadam element method integration method ABSTRACT...

... artificial intelligence real time system upstream oil & gas experiment control system subsea system ship software node module comprehensive simulation experiment platform propeller shuttle tanker diagram shuttle tanker model model experiment dp control system algorithm...

... proposes an algorithm for calculating the circumferential crack parameters by using YOLACT network, which is a kind of computer vision method. Ice blocks shown in images are identified through the YOLACT network to generate mask. Then Gaussian blur and Canny operator are applied to detect the edge...

... the approximate model and the multi-objective particle swarm optimization algorithm to achieve the multi-objective optimization of the taut polyester mooring system. The polyester rope volume and strength utilization ratio are defined as the optimization objectives, then the parameters of mooring radius...

...-diagonal elements of the MAC matrix to be relatively small, a set of sensors which will be a good design for vector correspondence can be determined. In addition, genetic algorithms(GA) have been successfully applied to sensor optimization arrangement. Yan(2002) defined the sum of the eigenvalue...

... hypoc-ppo auv path planning path length direction angle artificial intelligence algorithm obstacle steering angle objective function mdp machine learning path segment policy model reinforcement learning denote objective drl-based policy hybrid policy model ABSTRACT...

... ABSTRACT This study considers the hydrodynamic characteristics of an AUV near uneven seabed. An improved hydrodynamic algorithm based on conformal mapping and boundary element method is proposed in this paper to improve the accuracy and efficiency of numerical computation. The proposed...

... information actuation trajectory neural network machine learning ray deflection reinforcement learning curet complexity artificial intelligence fin algorithm amplitude operation international ocean control policy application patankar tracking controller kalman filter Proceedings...

... ABSTRACT Breaking waves interactions with vertical seawall attached with recurved parapet is investigated by a three-dimensional parallel CIP-based model, which is accelerated by high-performance computing based on Message Passing Interface algorithm and Open Multi-Processing algorithm...

... with the Kelvin wake produced by the mast is investigated by using the computation electromagnetic method based on the shooting and bouncing rays algorithm. It is shown that the wave surrounding the mast has an impact on the radar scattering feature of the mast. On one hand, the wave plays a role as stealth...

... algorithm capturable vibration frequency hao tian Proceedings of the Thirty-second (2022) International Ocean and Polar Engineering Conference Shanghai, China, June 5 10, 2022 Copyright © 2022 by the International Society of Offshore and Polar Engineers (ISOPE) ISBN 978-1-880653-81-4; ISSN 1098-6189...

... ABSTRACT Fitting parameters in the failure envelope expression are influenced by the complex boundary conditions. This paper carried out a comparative study on the performance of five machine learning (ML) algorithms, including decision tree (DT), support vector machine (SVM), random forest...

..., trim angle, and resistance) related to the bulk carrier in the data set were selected as the training data set and three machine learning algorithms were utilized to predict the optimum trim angle at which minimum resistance occurs. Then, the performance of machine learning algorithms in forecasting...

... structure characteristic signals in complex marine environments. The feasibility of signal recognition algorithm is proved by the monitored signal from a model test. The autonomous recognition of structural composite signals at different monitored positions is then realized. In addition, the influence...

..., China ABSTRACT This paper proposes a machine learning based ship speed over ground prediction model, driven by the eXtreme Gradient Boosting (XGBoost) algorithm. The dataset is acquired from a world-sailing chemical tanker with five years of full-scale measurements. The model is trained using...