Long-span steel structure building micro-strain short-term prediction method

A short-term forecasting and steel structure technology, applied in special data processing applications, geometric CAD, design optimization/simulation, etc., can solve the problem of lack of effective methods for short-term forecasting

Pending Publication Date: 2021-07-06
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems existing in the prior art, the present invention provides a short-term prediction method for the micro-strain of a long-span steel structure building, which solves the problem that the existing short-term prediction of the micro-strain of a long-span steel structure building lacks an effective method, and can be more Grasp the characteristics of the micro-strain time series of steel structure buildings in detail, which greatly improves the accuracy of short-term prediction of the micro-strain of steel structures

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
  • Long-span steel structure building micro-strain short-term prediction method
  • Long-span steel structure building micro-strain short-term prediction method
  • Long-span steel structure building micro-strain short-term prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] see figure 1 , the short-term prediction method of a kind of long-span steel structure building micro-strain of the present invention, comprises the following steps:

[0061] Step 1. Obtain the historical data of micro-strain of long-span steel structure buildings, and divide them into training set and test set according to the relevant ratio. The ratio here is 9:1.

[0062] Step 2, using the variational mode decomposition (VMD) method to adaptively decompose the training set and test set in step 1, effectively extracting the decomposed modal component data in the historical data, reducing the instability of the historical data, and improving Prediction accuracy; then use phase space reconstruction to process and optimize the decomposed modal component data, and obtain the subsequences of each modal component in the training set and the subsequences of each modal component in the test set, so that the reconstructed samples are better Reflect changes in the micro-strain...

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 long-span steel structure building micro-strain short-term prediction method. The method comprises: obtaining historical data of the micro-strain of the large-span steel structure building, and dividing the historical data into a training set and a test set; performing adaptive decomposition on the training set and the test set by using a variational mode decomposition method to obtain each mode component sub-sequence of the training set and the test set; training each modal component sub-sequence in the gating circulation unit by using each modal component sub-sequence of the training set as a training sample, and establishing a short-term prediction sub-model of the gating circulation unit steel structure building micro-strain of each modal component sub-sequence of the training set; predicting each modal component sub-sequence of the test set by using the short-term prediction sub-model of the gated circulation unit steel structure building micro-strain of each modal component sub-sequence of the training set, and accumulating each predicted modal component sub-sequence of the test set to obtain a prediction set; and performing comparative analysis by using the prediction set and a test set in historical data. According to the invention, the short-term prediction precision of the micro-strain of the steel structure building is improved.

Description

technical field [0001] The invention belongs to the technical field of short-term prediction of micro-strain of steel structure building in the research of long-span steel structure, and specifically relates to a short-term prediction method of micro-strain of long-span steel structure building. Background technique [0002] The construction of national infrastructure has greatly promoted the rapid rise of the construction industry. A large number of long-span steel structure buildings have sprung up all over the country. They have novel appearance, exquisite workmanship, complex structure, strong sense of technology, light weight, strong rigidity, high seismic performance and uniform stress distribution. They are usually widely used It is applied in various fields and becomes a landmark building in the city or region. However, since these buildings are exposed to the natural environment for a long time, under the comprehensive action of various factors such as wind, frost,...

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): G06F30/13G06F30/27
CPCG06F30/13G06F30/27
Inventor 段中兴刘瑞兴焦晨琳陈亚州
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
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