... ABSTRACT Coastal concrete components are susceptible to structural damage in acid deposition environments, and the characterization of the interfacial transition zone (ITZ) is critical to the macroscopic performance of the material, making accurate identification of this region of great...

... falling into the water is to extract the characteristic information in the process of movement, so as to complete the identification of personnel falling into the water. If only acceleration is used as the feature, some information extraction is not obvious and the detection is wrong. Euler Angle can...

... ode solver machine learning modeling prediction result artificial intelligence prediction ocean engineering training dataset neural network ship maneuvering motion neural ode identification Proceedings of the Thirty-fifth (2025) International Ocean and Polar Engineering Conference Seoul...

... dynamically changes due to the factors such as ship conditions (e.g., draft and loading) and environmental conditions (e.g., wind, waves, and currents) when sailing at sea (Zhang et al., 2012). Traditional offline identification models, which remain unchanged during navigation, are insufficient for updating...

... identification utilizing the data collected from ship sensors during practical navigations. The system identification is capable to learn the manoeuvring mechanism included in the motion data and can be updated flexibly according to the flowing data collected in real time. The system identification methods...

... intelligence ship prime system constraint regression linear regression simulation reliability coefficient trajectory alexandersson maneuver maneuvering model prediction identification matrix engineering Proceedings of the Thirty-fifth (2025) International Ocean and Polar Engineering...

.... By separately identifying the RK4 data and the computational fluid dynamics (CFD) data of the damaged ship DTMB-5415 in regular waves, the respective hydrodynamic coefficients are obtained. The coefficients obtained through identification are used to predict the roll motion, which is then compared...

... ABSTRACT This paper presents a hybrid model based on Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM), which is applied to the non-parametric identification of ship motion and takes into account the factor of wind. The model extracts the local...

... ABSTRACT For the problem of unmanned ships trajectory tracking with unknown parameters. Firstly, this article establishes a three degree of freedom ship kinematics and dynamics model. Secondly, an offline parameter identification algorithm is proposed based on the least squares method...

... dynamic positioning system denote uhlmann identification subsea system kalman filter experiment society Proceedings of the Thirty-fourth (2024) International Ocean and Polar Engineering Conference Rhodes, Greece, June 16 21, 2024 Copyright © 2024 by the International Society of Offshore...

.... machine learning exploration maneuver reinforcement learning ship marine science maneuvering simulation model-based reinforcement trajectory artificial intelligence dataset simulation ann journal identification algorithm technology denote ocean engineering threshold disturbance...

... ABSTRACT The paper addresses the problem of thrusters interactions and thrusters identification for the purpose of dynamic positioning (DP) operations and DP capability prognosis. Carried out analyses are based on numerical and experimental methods. The computations show satisfactory...

... ABSTRACT This paper proposes a system identification scheme to obtain a multi-input multi-output (MIMO) model of ship motion. The scheme is based on Long Short-Term Memory (LSTM) deep neural network, which can utilize the temporal correlation in the training data of ship maneuvering motion...

... is constructed to generate virtual data for the offline identification. An online model is established with reference to the offline model. The online model is trained by two state-of-the-art online algorithms, kernel adaptive projection and projection support vector machine. It has been verified...

... condensation instability production control dimension circulation interface two-phase flow instability experiment pipeline offshore passive heat removal system accuracy 0 mode recognition identification Proceedings of the Thirty-fourth (2024) International Ocean and Polar Engineering Conference...

... for the varying operational environments of different turbines, making it challenging to achieve precise risk identification. To handle the massive amount of data, Statistical Time Series methods for Structural Health Monitoring (STS-SHM) have been developed. These methods utilize (a) random excitation...

... phase of a project. In this article, we present a new method of identification based on big data analysis and genetic algorithm to identify parametric manoeuvring model based from few standard manoeuvres used as reference trajectories. A very large database, with several millions of manoeuvring models...

... project on the same point of P , one are not able to find out which is the true point. With the help of q point provided by another camera, the real point of Q point can be identified. Fig.4 Location identification by two cameras With the use of the already known matrix of image coordinate...

... at the riser's top. identification dissipation lms pimento tab contribution measurement carcass experiment riser vibration damping coefficient engineering curvature frequency modal identification procedure dissected riser sample Proceedings of the Thirty-fourth (2024) International...

... ABSTRACT A novel method for black-box modeling of ship maneuvering motion is proposed. The identification method is based on Gaussian progress regression (GPR), and the particle swarm optimization (PSO) is used for optimization of the hyperparameters in the kernel function to improve...