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

Dynamic grey Fehrhardt neural network landslide deformation prediction method

A technology of neural network and prediction method, applied in the field of dynamic gray Fairhurst neural network landslide deformation prediction, which can solve the problems of insufficient accuracy of prediction results and large errors of prediction results, etc.

Active Publication Date: 2019-03-19
GUILIN UNIV OF ELECTRONIC TECH
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There are still some problems in the above-mentioned prior art model, such as the gray Verhulst model of the prior art uses some outdated information, which makes the prediction result error larger; the BP neural network algorithm has problems in the selection of the initial weight and threshold of the network, resulting in insufficient accuracy of the prediction result high

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
  • Dynamic grey Fehrhardt neural network landslide deformation prediction method
  • Dynamic grey Fehrhardt neural network landslide deformation prediction method
  • Dynamic grey Fehrhardt neural network landslide deformation prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings, but the present invention is not limited.

[0066] figure 1 A dynamic gray Fairhurst neural network landslide deformation prediction method is shown, comprising the following steps:

[0067] (1) Establish the original data of the cumulative displacement of the landslide body, establish a GNSS monitoring network in the landslide area, and return the three-dimensional coordinate data to the server through the GPRS or 3G or 4G network, and store the data in the database;

[0068] (2) Data preprocessing, read the three-dimensional coordinate data from the database and perform preprocessing operations; the data preprocessing includes Kalman filter smoothing and use the 3σ criterion to remove outliers and outliers that cannot be filtered out by Kalman filter

[0069] (3) Fit the data through the gray Verhulst model, the specific steps are as follow...

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 dynamic grey Fehrhardt neural network landslide deformation prediction method, relating to that technical field of landslide monitor deformation prediction, and solving the technical problem that a method with high precision of landslide deformation prediction is provided, comprising the follow steps of: data preprocessing; the grey Verhulst model was used to fit the data; calculating residual error and constructing residual error sequence; training GA-BP neural network; obtaining a prediction residual series; calculating Combined Model Forecasts. The invention greatly improves the precision of the landslide deformation prediction.

Description

technical field [0001] The invention relates to the technical field of landslide monitoring deformation prediction, in particular to a dynamic gray Fairhurst neural network landslide deformation prediction method. Background technique [0002] Geological disasters are one of the main problems facing human society today. Geological disasters caused by nature and man-made in my country mainly include earthquakes, displacement of rock and soil on slopes, ground deformation and land degradation. According to statistics from the Department of Land and Resources, in 2015, there were 8,224 geological disasters of various types across the country, of which 5,616 were landslides, accounting for 68.3%. Landslide disasters have become one of the most important geological disasters in my country, and one of the important measures to actively and effectively prevent landslides and other geological disasters is to conduct long-term observation of hidden deformation points such as landslid...

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): G06Q10/04G06N3/04G06N3/08
CPCG06N3/086G06Q10/04G06N3/045
Inventor 邓洪高姚鹏远孙希延纪元法王守华符强严素清吴孙勇付文涛赵松克李有明
Owner GUILIN UNIV OF ELECTRONIC TECH
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