Sea area wave data deduction method and system based on neural network model
The invention discloses a sea area wave data deduction method and system based on a neural network model, and the method comprises the steps: obtaining a wave image corresponding to a target sea area and historical wave time sequence data, and carrying out the time sequence decomposition of the hist...
Gespeichert in:
Hauptverfasser: | , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a sea area wave data deduction method and system based on a neural network model, and the method comprises the steps: obtaining a wave image corresponding to a target sea area and historical wave time sequence data, and carrying out the time sequence decomposition of the historical wave time sequence data, and obtaining corresponding periodic data, performing time sequence analysis on the historical wave time sequence data to construct a periodic prediction model; extracting periodical characteristics of the periodical data through the periodical prediction model, and performing modal decomposition on second historical wave time series data obtained after data fitting is performed on the periodical characteristics and the historical wave time series data to obtain corresponding subsequences, and inputting the sub-sequence and the second wave image into a pre-trained dual-channel neural network model, performing wave data deduction through the dual-channel neural network model, and outp |
---|