ARIMA-BP neutral network-based bridge monitoring data prediction method

A BP neural network and monitoring data technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of small prediction error, large prediction error, inability to analyze nonlinear information well, and achieve prediction error Small, efficient parsing of effects

Inactive Publication Date: 2017-03-22
ZHEJIANG UNIV OF TECH
View PDF2 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0027] In order to overcome the shortcomings of the existing bridge monitoring data prediction methods that cannot analyze nonlinear information well and have large prediction errors, the

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
  • ARIMA-BP neutral network-based bridge monitoring data prediction method
  • ARIMA-BP neutral network-based bridge monitoring data prediction method
  • ARIMA-BP neutral network-based bridge monitoring data prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with the accompanying drawings.

[0062] refer to Figure 3 ~ Figure 7 , a bridge monitoring data prediction method based on ARIMA-BP neural network, the prediction method comprises the following steps:

[0063] 1) ARIMA (p, d, q) model establishment of bridge monitoring data: Sequential stationarity test is carried out on bridge monitoring data, and the model is identified and ordered by AIC criterion, and the model parameters are fitted according to the least squares method. Complete the establishment of the ARIMA(p,d,q) model;

[0064] 2) Use the ARIMA(p,d,q) model to estimate the measured value of the monitoring period of the existing measured data, and obtain its estimated value Estimate the measured value of the expected forecast period without measured data to obtain its estimate

[0065] 3) Acquisition of the monitoring data residual: the actual value of the monitoring data and the predic...

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 ARIMA-BP neutral network-based bridge monitoring data prediction method. The method comprises the following steps of 1) building an ARIMA(p,d,q) model of bridge monitoring data; 2) performing monitoring value estimation on a monitoring cycle of existent actual measurement data through the ARIMA(p,d,q) model to obtain an estimated value Ypn; performing monitoring value estimation on an expected prediction cycle of inexistent actual measurement data to obtain an estimated value Ynm; 3) obtaining a residual error of the monitoring data: performing subtraction on an actual value of the monitoring data and the estimated value Ypn of the ARIMA(p,d,q) to obtain a residual error Epn of a prediction result; 4) performing a process for predicting a residual error by a BP neutral network; 5) predicting a residual error in a prediction cycle through the established network to obtain an estimated value Enm; and 6) performing superposition on linear trend information predicted by the ARIMA(p,d,q) and a prediction result of the residual error by the BP network to obtain a combined prediction model result. According to the method, nonlinear information is effectively analyzed and a prediction error is relatively small.

Description

technical field [0001] The invention relates to the field of long-span bridge monitoring data analysis and processing, in particular to a prediction method for long-span bridge monitoring data. Background technique [0002] my country's "Measures for the Safety Operation and Management of Highway Long Bridges and Tunnels (Draft for Comment)" proposes that the safety operation management of national highways and provincial highway super-large bridges should implement the work policy of "safety first, prevention first", and recommends that the management and maintenance units adopt modern information technology , Gradually establish a safety monitoring system for the long bridge and tunnel, grasp the overall technical status and operating conditions of the long bridge and tunnel in a timely manner, and provide a basis for the operation management, maintenance and repair, reliability assessment and related scientific research of the long bridge and tunnel. In order to monitor th...

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): G06F19/00
CPCG16Z99/00
Inventor 余佩琼吴丽丽杨立陆超伦梁圣浩周仁武
Owner ZHEJIANG UNIV OF TECH
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