A Method for Predicting Significant Wave Height of Ocean Waves Based on Multiple Sine Function Decomposition Neural Networks

A sine function and effective wave height technology, applied in the field of wave parameter calculation, can solve the problem of no effective wave height prediction of ocean waves, and achieve the effect of avoiding economic loss and strong fitting degree.

Active Publication Date: 2022-03-18
GUANGDONG ZHANJIANG PROVINCIAL LAB OF SOUTHERN MARINE SCI & ENG
View PDF0 Cites 0 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 significant wave height of ocean waves to effectively predict the significant wave height of ocean waves

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
  • A Method for Predicting Significant Wave Height of Ocean Waves Based on Multiple Sine Function Decomposition Neural Networks
  • A Method for Predicting Significant Wave Height of Ocean Waves Based on Multiple Sine Function Decomposition Neural Networks
  • A Method for Predicting Significant Wave Height of Ocean Waves Based on Multiple Sine Function Decomposition Neural Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] The method for predicting the effective wave of the waves based on multi-sine-based function decomposition neural network predicts the average effective wave high prediction:

[0080] (1) This example is an example of effective wave high data in the North China Sea Bay region of the Era-InterIum Dataset of European Center for Medium-RangeWeather Forecast, which is 6 hours. The spatial resolution is 0.125 ° × 0.125 °, with the average effective wave high data between 1979 and 2016 as learning data; 2017 and 2018 months average effective wave high data for verification data, for decomposition The sinusoidal function is selected from 10, and the mean square error of the final forecast results, the average absolute error and the root mean square error Figure 4 Indicated (in Figure 4 Middle: (a) average error, (b) average absolute error, (c) 均 root error), where: Figure 4 Point M in (a) 1 And point M 2 The minimum (0.0022) and maximum value (0.0675), respectively (0.0675), respe...

Embodiment 2

[0083] The seasonal effective wave high prediction is performed using the present invention based on multi-sine-based function decomposition neural networks.

[0084](1) This example is an example of effective wave high data in the North China Sea Bay region of the Era-InterIum Dataset of European Center for Medium-RangeWeather Forecast, which is 6 hours. The spatial resolution is 0.125 ° × 0.125 ° in 1979 to 2018 season average data for learning data, 2017 and 2018, two-year-average effective wave high data for verification data, for decomposition sine functions The number is selected from 10, and the mean square error of the final prediction result is, the average absolute error and the root mean square error are Image 6 Indicated (in Image 6 Middle: (a) average error, (b) average absolute error, (c) 均 root error), where: Image 6 Point M in (a) 3 And point M 4 The minimum (0.0013) and maximum value (0.0500), respectively (0.0500), respectively, and their latitude and longitude c...

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 ocean waves based on multi-sine function decomposition neural network, including S1. Obtaining the time series L(t of ocean wave fluctuations j ), and the time series L(t j ) is divided into learning data time length and verification data time length; S2. Utilizes M sine functions to decompose and study the single-point time series extracted by learning data time length; S3. Finally, accumulate the results of the learned sine functions, and Comparing with the verification data to calculate the mean square error, judging that the prediction results meet the threshold set by MSE, and then predicting the effective wave height in the future time to realize the effective wave height prediction of the entire area; this method decomposes and learns the effective wave height time series through multiple sine functions, Predict the significant wave height of ocean waves; it has been verified that the significant wave height of ocean waves can be effectively predicted by using the method for predicting significant wave height of ocean waves in the present invention, which has a significant effect on the study of ocean wave fluctuations and ocean climate change laws.

Description

Technical field [0001] The present invention relates to computing technology wave parameters, and in particular relates to a neural network based on multiple decomposition sine function (Multiple sine functions decomposition neural network, referred MSFDNN) wave high significant wave prediction method. Background technique [0002] Waves of human life is a relationship with the ocean in the most direct and most closely fluctuation, have a negligible impact on people's production and life, such as sea, fisheries, offshore oil platforms, etc wave energy use and the waves closely related; effective high ocean wave refers to a wave height of the wave train descending order of priority, wherein high maximum of 1 / 3 of the wave average value, is an important parameter of the reaction wave characteristics; [0003] For high significant wave ocean forecasts can accurately reflect the fluctuation ocean waves for ocean wave fluctuations and Variation of marine climate has a significant effe...

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
Patent Type & Authority Patents(China)
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