Method for predicting significant wave height of sea waves based on multi-sine function decomposition neural network

A technology of sine function and effective wave height, which is applied in the field of wave parameter calculation, can solve problems such as prediction of effective wave height without ocean waves, and achieve the effect of avoiding economic loss and strong fitting

Active Publication Date: 2020-10-23
GUANGDONG ZHANJIANG PROVINCIAL LAB OF SOUTHERN MARINE SCI & ENG
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art, there is no calculation method for predicting the significan

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for predicting significant wave height of sea waves based on multi-sine function decomposition neural network
  • Method for predicting significant wave height of sea waves based on multi-sine function decomposition neural network
  • Method for predicting significant wave height of sea waves based on multi-sine function decomposition neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0078] Example 1

[0079] The method of predicting the effective wave height of ocean waves based on the multi-sine function decomposition neural network of the present invention is used to predict the monthly average effective wave height:

[0080] (1) This example takes the significant wave height data of the Beibu Gulf region of the South China Sea from the ERA-Interim data set of the European Centre for Medium-RangeWeather Forecasts (ECMWF) as an example. The time resolution of the data is 6 hours. , The spatial resolution is 0.125°×0.125°, and the monthly average significant wave height data from 1979 to 2016 is used as the learning data; the monthly average significant wave height data for the two years of 2017 and 2018 are used as the verification data for prediction and decomposition The number of sine functions is selected as 10. The mean square error, mean absolute error and root mean square error of the final prediction result are as Figure 4 Shown (in Figure 4 Medium:...

Example Embodiment

[0082] Example 2

[0083] The method for predicting the effective wave height of ocean waves based on the multi-sine function decomposition neural network of the present invention is used to predict the seasonal average effective wave height:

[0084] (1) This example takes the significant wave height data of the Beibu Gulf region of the South China Sea from the ERA-Interim data set of the European Centre for Medium-RangeWeather Forecasts (ECMWF) as an example. The time resolution of the data is 6 hours. , The spatial resolution is 0.125°×0.125°, using the seasonal average data from 1979 to 2018 as the learning data, and the two-year seasonal average effective wave height data in 2017 and 2018 as the verification data for prediction, and the sine function for decomposition The number is selected as 10, and the mean square error, mean absolute error and root mean square error of the final prediction result are as Image 6 Shown (in Image 6 Medium: (a) mean square error, (b) mean ab...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for predicting the significant wave height of sea waves based on a multi-sine function decomposition neural network. The method comprises the following steps: S1, obtaining a time sequence L(tj) of sea wave fluctuation, and dividing the time sequence L(tj) into a learning data time length and a verification data time length; S2, carrying out decomposition learningon the extracted single-point time sequence by utilizing M sine functions according to the learning data time length; and S3, finally, accumulating the results of the learned sine functions, comparingthe accumulated results with verification data, calculating a mean square error, and predicting the effective wave height in future time to realize effective wave height prediction of the whole region after judging that a prediction result meets a threshold value set by an MSE. According to the method, decomposition learning is carried out on the effective wave height time sequence through multiple sine functions, and the effective wave height of sea waves is predicted; and tests prove that the method for predicting the significant wave height of sea waves can effectively predict the sea wavesignificant wave height, and has a remarkable effect on researching sea wave fluctuation and sea climate change rules.

Description

technical field [0001] The invention relates to the technical field of sea wave parameter calculation, in particular to a method for predicting the effective wave height of sea waves based on multiple sine functions decomposition neural network (MSFDNN for short). Background technique [0002] Ocean wave is a wave phenomenon in the ocean that is most directly and closely related to human life. It has a non-negligible impact on people's production and life. For example, sea navigation, fishery production, offshore oil platforms, and wave energy utilization are all related to ocean waves. Closely related; the effective wave height of the ocean refers to the arrangement of the wave heights in the wave train from large to small, and the average value of the wave height of the largest 1 / 3 part is an important parameter reflecting the characteristics of ocean waves; [0003] For the prediction of the significant wave height of the ocean, it can accurately reflect the wave fluctuat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01C5/00G01C13/00G06N3/04G06N3/08
CPCG01C5/00G01C13/002G06N3/08G06N3/045
Inventor 付东洋王焕黄浩恩刘贝余果肖秀春刘大召金龙
Owner GUANGDONG ZHANJIANG PROVINCIAL LAB OF SOUTHERN MARINE SCI & ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap