Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for forecasting wind speed of high speed railway line

A wind speed prediction, high-speed railway technology, applied in neural learning methods, biological neural network models, etc., can solve problems such as difficulty in meeting the requirements of high-speed railway safety traffic management, and achieve the effect of ensuring accuracy

Inactive Publication Date: 2011-05-18
PEKING UNIV
View PDF0 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is difficult to meet the requirements of high-speed railway safety traffic management by using the existing single prediction method

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 forecasting wind speed of high speed railway line
  • Method for forecasting wind speed of high speed railway line
  • Method for forecasting wind speed of high speed railway line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Taking the measured wind speed sequence (one sampling point per second) of No. JJ005 anemometer station of the Beijing-Tianjin intercity high-speed railway as an example, the present invention will be further described in conjunction with the accompanying drawings. attached figure 1 It represents the flow of the high-speed railway wind speed prediction method combined with wavelet analysis and BP neural network.

[0039] The first 2678400 data of the measured wind speed sequence are taken as the training set to establish the prediction model, and the last 960 data are used to test the model.

[0040] First, the Mallat tower algorithm of the wavelet analysis method is used to perform multi-layer decomposition and reconstruction calculation on the wind speed sequence of the training set and the wind speed sequence of the prediction set, and the number of decomposition layers is 4. The subsequence of partial prediction set after decomposing is as follows figure 2 as sho...

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 forecasting wind speed of a high speed railway line by combining a wavelet analysis method and a BP (Back Propagation) neural network. In the invention, actually measured wind speed data is subjected to multilayered decomposition and reconfigurable computing through the decomposition of wavelet analysis and a reconfiguration algorithm so as to decompose an original wind speed sequence into wind speed sequences of different scales. The method comprises the following steps of: normalizing all layers of decomposed wind speed sequences; training the neural network by utilizing an error BP (Back Propagation) learning algorithm until converging; respectively establishing corresponding forecasting models for the wind speed sequences of all the layers for forecasting; and finally, carrying out reconfigurable computing on wind speed forecasting values of all the layers to obtain a forecasting value of the original wind speed sequence. The invention overcomes the defects of low forecasting precision, too large time interval, and the like of a traditional method, realizes the wind speed forecasting of a high speed railway line under various climate types, has the advantages of short computing time and high forecasting precision and provides a scientific reference for formulating operation control regulations of the high speed railway.

Description

technical field [0001] The invention belongs to the technical field of monitoring and control for safe driving of high-speed railways in windy weather, and relates to a method for wind speed prediction along high-speed railways, in particular to a high-precision wind speed prediction method combining wavelet analysis and BP neural network. The time is short, and high-precision wind speed prediction can be carried out 2 to 5 minutes ahead with a time interval of no more than 10 seconds. Background technique [0002] Due to the characteristics of strong transportation capacity, fast speed, high punctuality rate, all-weather operation and high economic efficiency, high-speed railway plays an increasingly prominent role in the transportation system. In order to alleviate the tense situation of railway transportation and meet the needs of national economic and social development, my country is currently vigorously building high-speed railways. Due to the light body and fast spee...

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 Applications(China)
IPC IPC(8): G06N3/08
Inventor 李振山薛安温闲云曾秋兰马淑红李建群殷和宜
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com