<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Accurate tide height is crucial for the safe navigation of large deep-draft ships when they enter and leave the port. We have proposed an accurate forecasting method for the tide heights from the observation data and neural networks, which can easily calculate the tidal window period of large deep-draft ships’ navigation through long channels at high tide. Moreover, an artificial neural network is established for the tide height from the observation of tide heights before their current time node. For an ideal forecast, the neural network was optimized for one year with the tide height data of Huanghua Port. In case of large ships, their tidal characteristics of channels for are complex. A new method is proposed for the observation of multiple stations and artificial neural networks of each observation station. When ships are navigating through the port, the tide height is predicted from the observed data and forecast tide heights of multiple observation stations. Thus, a valid tidal window period is secured when the ships enter the port. Comparative analysis of the ship’s tidal window period with that of the measured one can lead us to conclude that the forecasted data has a strong correlation with the measurement. So, our proposed algorithm can accurately predict the tide height and calculate the node timing when the ship enters and depart the port. Finally, these results can be applied for the safe navigation of large deep-draft ships when the port is at high tide.</p></abstract>

Accurate tide height is crucial for the safe navigation of large deep-draft ships when they enter and leave the port. We have proposed an accurate forecasting method for the tide heights from the observation data and neural networks, which can easily calculate the tidal window period of large deep-draft ships’ navigation through long channels at high tide. Moreover, an artificial neural network is established for the tide height from the observation of tide heights before their current time node. For an ideal forecast, the neural network was optimized for one year with the tide height data of Huanghua Port. In case of large ships, their tidal characteristics of channels for are complex. A new method is proposed for the observation of multiple stations and artificial neural networks of each observation station. When ships are navigating through the port, the tide height is predicted from the observed data and forecast tide heights of multiple observation stations. Thus, a valid tidal window period is secured when the ships enter the port. Comparative analysis of the ship’s tidal window period with that of the measured one can lead us to conclude that the forecasted data has a strong correlation with the measurement. So, our proposed algorithm can accurately predict the tide height and calculate the node timing when the ship enters and depart the port. Finally, these results can be applied for the safe navigation of large deep-draft ships when the port is at high tide.

Calculation and Measurement of Tide Height for the Navigation of Ship at High Tide Using Artificial Neural Network

Polish Maritime Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Accurate tide height is crucial for the safe navigation of large deep-draft ships when they enter and leave the port. We have proposed an accurate forecasting...

Calculation and Measurement of Tide Height for the Navigation of Ship at High Tide Using Artificial Neural Network

Online veröffentlicht: 11. Jan. 2019

Seitenbereich: 99 - 110

DOI: https://doi.org/10.2478/pomr-2018-0118

Schlüsselwörter
Deep-draft ships, neural network, intelligent navigation, multi-observation stations

© 2019 Li Qiang, et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Calculation and Measurement of Tide Height for the Navigation of Ship at High Tide Using Artificial Neural Network

Online veröffentlicht: 11. Jan. 2019

Seitenbereich: 99 - 110

DOI: https://doi.org/10.2478/pomr-2018-0118

SchlüsselwörterDeep-draft ships, neural network, intelligent navigation, multi-observation stations

© 2019 Li Qiang, et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Schlüsselwörter
Deep-draft ships, neural network, intelligent navigation, multi-observation stations