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

Method and system for predicting short-time wind speed overrun probability

A technology that transcends probability and forecasting methods, applied in forecasting, instruments, biological neural network models, etc., can solve problems such as measurement errors of pulsation sensors that do not consider wind, to avoid driving safety accidents, improve traffic efficiency, and improve traffic travel environment Effect

Pending Publication Date: 2021-01-05
CENT SOUTH UNIV +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a prediction method and system for short-term wind speed exceeding probability, which is used to solve the technical problem that the existing short-term wind speed prediction is a deterministic prediction and does not consider uncertain factors such as wind pulsation and sensor measurement error.

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 and system for predicting short-time wind speed overrun probability
  • Method and system for predicting short-time wind speed overrun probability
  • Method and system for predicting short-time wind speed overrun probability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] see figure 1 , the prediction method of the short-term wind speed exceeding probability of the present embodiment, comprises the following steps:

[0038] Real-time monitoring and collection of meteorological parameters including at least wind speed and wind direction in the area to be measured to obtain monitoring data sequences;

[0039] Extract a part of the monitoring data sequence as a sample, and train to obtain a short-term wind speed prediction model based on the LSTM network; use the short-term wind speed prediction model to predict the rest of the monitoring data in the monitoring data sequence except for the sample, and obtain a short-term predicted wind speed sequence;

[0040] Subtract the short-term predicted wind speed sequence from the corresponding monitoring data sequence to obtain the wind speed prediction error sequence;

[0041] The GMM method is used to statistically analyze the wind speed forecast error sequence, and the conditional probability ...

Embodiment 2

[0046] see figure 1 , the prediction method of the short-term wind speed exceeding probability of the present embodiment, the specific steps are as follows:

[0047] (1) Real-time monitoring and collection of wind speed in the area along a certain high-speed rail to obtain the monitoring wind speed sequence x.

[0048] (2) Feature selection is performed on the monitoring wind speed sequence x, and the features include mean value, root mean square value, extreme value and peak-to-peak value, etc. And use x part of the data as a sample to train the LSTM network wind speed prediction model; use the trained model to predict the rest of the monitoring data, assuming that the previous monitoring wind speed x is known t-1 Predict the next wind speed x t , and the short-term forecast wind speed sequence is defined as y.

[0049] The structure of the basic module of LSTM and the flow of information are as follows: figure 2As shown, each storage unit includes an input gate, a forge...

Embodiment 3

[0080] This embodiment provides a computer system, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps in any of the foregoing embodiments are implemented.

[0081] In summary, the present invention can be used for high wind early warning of high-speed railways, highways, wind farms and photovoltaic farms, can avoid driving safety accidents caused by cross winds, ensure the safety of life and property of travelers, and improve traffic efficiency. has great significance.

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 and system for predicting short-time wind speed overrun probability. The method comprises the steps: carrying out the real-time monitoring and collection of meteorological parameters of a to-be-detected region to obtain a monitoring data sequence; extracting a part of the monitoring data sequence as a sample, and training to obtain a wind speed short-time prediction model based on an LSTM network; predicting other monitoring data except the sample in the monitoring data sequence by adopting a wind speed short-time prediction model to obtain a short-time prediction wind speed sequence; subtracting the short-time prediction wind speed sequence from the corresponding monitoring data sequence to obtain a wind speed prediction error sequence; performing statistical analysis on the wind speed prediction error sequence by adopting a GMM method to obtain a conditional probability density function of the wind speed prediction error; taking the short-term prediction wind speed sequence as prediction expectation, and calculating the occurrence probability that the prediction wind speed exceeds a certain specific wind speed value in combination with a conditional probability density function of a prediction error. The method is used for strong wind early warning of high-speed railways, expressways, wind power plants and photovoltaic electric fields.

Description

technical field [0001] The invention relates to the field of real-time early warning of wind speed exceeding probability, in particular to a prediction method of short-term wind speed exceeding probability based on LSTM (Long Short-Term Memory, long-term short-term memory network) and GMM (Gaussian Mixture Model, Gaussian mixture model). Background technique [0002] In the past two decades, high-speed railways, expressways, wind farms, and photovoltaic farms have developed rapidly. With the further extension of high-speed railways and expressway networks, high-speed vehicles are facing threats from various harsh wind environments. Driving safety accidents caused by strong winds are not uncommon, such as: Xinjiang 30-mile wind area and hundred-mile wind area, Shenhai Expressway Rugao Section Lieshihe Bridge, Fuyin Expressway Hubei Suizhou Section, Guangzhou Humen Bridge, Zhengzhou City Yellow River Highway Bridge, Zhejiang Jintang There have been many driving safety accident...

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): G06Q10/04G06Q50/26G06N3/04G06F17/15
CPCG06Q10/04G06Q50/265G06F17/15G06N3/044G06N3/045
Inventor 敬海泉何旭辉罗谦刚
Owner CENT SOUTH 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