Scale effects in AR model real-time ship motion prediction

Jiang, Hua; Duan, Shiliang; Huang, Li‐Min; Han, Yang; Yang, Heng; Ma, Qingwei

doi:10.1016/j.oceaneng.2020.107202

Cited by 47 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, has long been investigated, and non-NN methods are well developed in this context. Typically, there are two kinds of non-NN methods: one kind based on parameterized models, such as Kalman filters [19] and model identification [20], and the other kind based on linear models, such as Autoregressive method (AR) [21]. These methods are based on specific assumptions, e.g., non-linear terms can be omitted for linearization [22], and a priori knowledge, such as simplified models of ship dynamics [23].…”

Section: ) Non-nn Prediction Modelsmentioning

confidence: 99%

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Zhang¹,

Hu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.<div><br></div><div>A major revision is done, compared to the previous version.</div><div><br></div><div>Abstract: Neural networks (NNs) have been applied to predict complex ship motions for stable ship maneuvering and operations at sea, but the coupling effects of different DoFs are still not effectively modeled in black-box NNs. To this end, we propose a novel deep NN framework that explicitly models the coupling effects through factorization machines, and significantly improves the prediction accuracy without introducing much extra complexity. The proposed framework is also lightweight and frequency-aware, which serves real-time and high-frequency prediction with high accuracy. We experimentally demonstrated that the framework is not only friendly to real-time prediction and online learning, but also interpretable and with great potential to be complemented by common machine learning tricks and go deeper.<br></div><div><br></div>

show abstract

Section: ) Non-nn Prediction Modelsmentioning

confidence: 99%

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Zhang¹,

Hu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Increasing literature proposes multistep prediction approaches to forecast freight rates using time series models, mainly including the Auto-Regressive model (AR), the Auto-Regressive Integrated Moving Average model (ARIMA), and their variants . These time series models have a small calculation amount and low cost, but they are not suitable for nonlinear problems under complex shipping market supply/demand conditions . Various artificial intelligent methods models such as Artificial Neural Networks (ANN), Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), and Radial Basis Function (RBF) network, are proposed to deal with this strong nonlinearity in the shipping market model, to forecast freight rates.…”

Section: Introductionmentioning

confidence: 99%

Practicality of Green H₂ Economy for Industry and Maritime Sector Decarbonization through Multiobjective Optimization and RNN-LSTM Model Analysis

Kazi

Eljack

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

A green H 2 economy's practicality depends highly on multisector decarbonization and cost−benefit analyses of the supply chain, including production routes, techno-economic performance, storage, and transportation. In this work, a strategic methodology is used to formulate the multiobjective optimization problem as a mixed-integer linear programming (MILP) to optimize green H 2 economy scenarios for decarbonizing the industrial and marine sectors concurrently. GAMS/IBM ILOG CPLEX 30.3.0 solver was used to solve the MILP, and an RNN-LSTM prediction model was used to identify the future H 2 demand from the maritime sector. Capital budgeting and sensitivity analysis were conducted for a constant 5% industrial sector decarbonization target and variable scenario-based maritime sector decarbonization. The results provide the detailed cost−benefit and trade-offs analysis for the optimal supply chain elements. The findings of this study can help define the essential legislative changes required to promote green H 2 as a marine fuel.

show abstract

“…For example, the spectral estimation method can analyse and forecast the ship motion by using the perspective of energy superposition 5 , which is too complex and abstract for using. The time-series method forecasts the ship motion by using the linear autoregressive sequence (AR) or autoregressive moving average model (ARMA) [6][7][8] , which needs complex models and the forecasting results are not very good. The Kalman filter method considers the wave excitation as white noise, and the accuracy of the prediction results will be reduced with time growing 9,10 .…”

Section: Introductionmentioning

confidence: 99%

A ship-motion prediction algorithm based on modified covariance method and neural networks

Ding¹

2022

International Conference on Computer Application and Information Security (ICCAIS 2021)

View full text Add to dashboard Cite

In order to provide accurate ship-motion prediction for safe seaboard operations, this paper presents a new ship-motion prediction algorithm based on modified covariance (MCOV) method and neural networks. This algorithm firstly uses the MCOV method to analysis spectrums of the ship motion. And then, major spectrums of the ship motion are used to find the ship motion model by using the Neural Network (NN). Simulation results show that this method can present a confidence performs on ship-motion prediction.

show abstract

Scale effects in AR model real-time ship motion prediction

Cited by 47 publications

References 11 publications

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Practicality of Green H₂ Economy for Industry and Maritime Sector Decarbonization through Multiobjective Optimization and RNN-LSTM Model Analysis

A ship-motion prediction algorithm based on modified covariance method and neural networks

Contact Info

Product

Resources

About

Scale effects in AR model real-time ship motion prediction

Cited by 47 publications

References 11 publications

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Modeling of Coupling Effects in Neural Networks for Ship Motion Prediction

Practicality of Green H2 Economy for Industry and Maritime Sector Decarbonization through Multiobjective Optimization and RNN-LSTM Model Analysis

A ship-motion prediction algorithm based on modified covariance method and neural networks

Contact Info

Product

Resources

About

Practicality of Green H₂ Economy for Industry and Maritime Sector Decarbonization through Multiobjective Optimization and RNN-LSTM Model Analysis