... the same or better results with fewer parameters and less training time compared to conventional AE (Chen et al. 2018). deep learning anomaly score steel column asia government machine learning loading test damage evaluation neural network frequency response function evaluation deformation...

... of human operation. Currently, handheld laser 3D scanners are well-used for high-precision structural measurement and positional estimation of complex parts. asia government china government completion proceedings neural network cloud shaft system point cloud machine learning point cloud...

... of the bending beam at large spans after the actual structure has been installed. The photo of the site construction is shown in Fig. 1. deformation united states government asia government artificial intelligence neural network north america government displacement passenger transportation cruise...

... ABSTRACT This study proposes an artificial neural network (ANN) model to inversely estimate sea states from the motion signals of floating structures measured on board. A generic moored FPSO (floating production storage and offloading) is modeled and 6DOF-motion time-series data are generated...

... with the effects of proximity to submerged elements. Partial simulations of specific situations are used to generate reduced models of these dynamic behaviors to which artificial neural networks (ANN)-based learning systems are included to create more precise surrogate models that can be dynamically adapted from...

... the expedition. neural network machine learning united states government concentration artificial intelligence canada government ice condition ice concentration stereo camera floe lidar data henry larsen imagery information sensor water management classification lidar ccg henry larsen...

... on the Grand Banks of Newfoundland. This model approximated the draft of icebergs roughly 1.3 times more than the real values. rfr 7 united states government europe government neural network machine learning canada government rfr 9 iceberg draft rfr 8 rfr 12 decision tree learning artificial...

... and Soares (2016) conducted a feasibility study on the parametric method of directional wave spectrum estimation based on ship response measurements. The results were validated against numerical simulations and full scale trials of a patrol ship. neural network canada government wave buoy ship...

... surveillance well control neural network deep-water drilling gas data quality united states government drilling operation china government well logging production monitoring early warning side-bypass pipe riser production control early warning system engineering asia government information...

... neural network pto force power output lstm prediction model renewable energy engineering sigmoid function wec pto rmse 0 aggidis forecasting result wave energy converter lstm network Proceedings of the Thirty-third (2023) International Ocean and Polar Engineering Conference Ottawa, Canada...

... sampling frequency (once a month) and the sparsity of point-based sampling hinder a finer and continuous hydro-environment monitoring. asia government artificial intelligence neural network water management inversion model local model hong kong water weight vector neuron algorithm single...

... asia government sub-sea system hose artificial intelligence algorithm engineering sample point neural network hydrodynamic performance basis function multi-objective optimization radial basis function effective tension experimental design design method surrogate model calm buoy...

... velocity, model geometry, and system stiffness. Here we employ Physics-informed Neural Network (PINN) that embeds the physical equation to learn the VIV response under different stiffness. Several sets of VIV response data by adjusting the structural stiffness were used to train the model, and the learned...

... ABSTRACT In this study, nonlinear ship motions are investigated based on the LSTM-MLP integrated machine learning model proposed by Ahn et al. (2022). In this machine learning model, the classical multilayer perceptron (MLP) neural network and long short-term memory (LSTM) layer are combined...

... ABSTRACT We present a hybrid linear potential flow - machine learning (LPF-ML) model for simulating weakly nonlinear wave-body interaction problems. In this paper we focus on using hierarchical modelling for generating training data to be used with recurrent neural networks (RNNs) in order...

... of the pipeline installation. This analysis is time-consuming, especially if a considerable number of environmental conditions and several time-domain simulations for each environmental condition need to be evaluated. deep learning midstream oil & gas neural network north america government sea...

... ABSTRACT Wave prediction is of vital importance in offshore engineering. A phase-resolved wave prediction model based on recurrent neural networks is developed in this paper. Considering the fat-tailed distribution of the experimental waves, we introduce the Student's t-distribution...

... ABSTRACT The Power-activation Feed-forward Neural Network (PFN) is used to achieve real-time prediction of the ship's parametric roll motion. The theoretical rationality of real-time prediction based on the ship's rolling motion time series data is verified. Autoregressive and simplified...

... ABSTRACT The accuracy and generalization of the model for predicting ship maneuvering motion are significant to the navigation efficiency and safety. A nonparametric modeling method based on BP (Back Propagation) neural network combined with AdaBoost (Adaptive Boosting) algorithm is proposed...

... planning algorithm meeting the needs of navigation. asia government artificial intelligence algorithm neural network evolutionary algorithm great circle route marine transportation optimization problem machine learning coupling optimization consumption model fuel consumption model...