Extra-high arch dam deformation spatio-temporal series prediction method based on spatio-temporal integration

A technology for sequence prediction and high arch dam, applied in design optimization/simulation, special data processing applications, instruments, etc., it can solve the problem of not being able to comprehensively consider the spatiotemporal correlation of spatiotemporal sequence prediction, and achieve the effect of improving accuracy

Active Publication Date: 2018-11-20
HUANENG LANCANG RIVER HYDROPOWER +2
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: The time-space sequence prediction method for high arch dam deformation based on time-space integration...

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
  • Extra-high arch dam deformation spatio-temporal series prediction method based on spatio-temporal integration
  • Extra-high arch dam deformation spatio-temporal series prediction method based on spatio-temporal integration
  • Extra-high arch dam deformation spatio-temporal series prediction method based on spatio-temporal integration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0044] Such as figure 1 As shown, it is known that m displacement sensor measuring points are buried inside the dam body, and the displacement data obtained by each sensor can be regarded as a time series, so the collected monitoring data can be expressed as m time series. These data form a time series set S={s 1 ,s 2 ,...,s i} (i=1...m). in

[0045] the s i ={X 1 ,X 2 ,...,X j}(j=1...n) represents the monitoring data sequence of a single site i, and there are n time points in total in th...

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 an extra-high arch dam deformation spatio-temporal series prediction method based on spatio-temporal integration. The method comprises following steps: as measured data alwayshas a random error item, when a dam sensor is used for monitoring data, a spatio-temporal process of the dam sensor is assumed to be decomposed into two parts: determinacy spatio-temporal change and small-scale random error change after the deterministic trend is removed, wherein the small-scale random error change after the deterministic trend is expected to be zero. A simple BP neural network isused for fitting a whole spatio-temporal trend; the residual item is acquired after the whole spatio-temporal trend is removed, the residual item is subjected to linear unbiased estimation, and a spatio-temporal Kriging method is selected for fitting a local spatio-temporal trend; a threshold circulation neural network is introduced to predict a time sequence of each measure point of the dam, a deformation value of the related measure point is predicted, the deformation value predicted by the threshold circulation neural network is compared with the deformation value predicted by the BP neural network, and if the predicted value of the threshold network is more accurate, the river direction displacement data after prediction is used as training data for optimizing the BP network.

Description

technical field [0001] The invention relates to the technical field of high arch dam deformation time-space sequence prediction, in particular to a combination of BP network, GRU neural network and space-time kriging method to predict the time-space sequence of high arch dam deformation. Background technique [0002] With the rapid increase in the types and quantities of modern sensor data, how to reasonably and effectively use the massive information collected to predict the overall deformation value of the dam, and then grasp the overall deformation state of the high arch dam, has become an urgent problem to be solved by water conservancy workers. Only by understanding the overall state of the dam can we deal with the abnormal situations found in time and prevent problems before they happen. Only in this way can the dam always operate in a safe and efficient environment. [0003] The deformation value of the dam is measured by displacement sensors buried inside the dam bo...

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): G06F17/50
CPCG06F30/20
Inventor 艾永平毛莺池高建陈豪李承兵陈琨王晓刚丁玉江龚友龙沈凤群谭彬余记远
Owner HUANENG LANCANG RIVER HYDROPOWER
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap