Bridge strain data abnormal value identification method based on data relevance

A data anomaly and data association technology, applied in character and pattern recognition, complex mathematical operations, instruments, etc., can solve the problems of data anomalies that are difficult to distinguish from a single signal source, signal fluctuations, and strain data fluctuations, etc., to achieve a wide range of The value of engineering application and the effect of less misjudgment

Pending Publication Date: 2019-09-27
上海深物控智能科技有限公司
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the strain data itself fluctuates greatly, and when a vehicle passes by, it will cause large signal fl

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
  • Bridge strain data abnormal value identification method based on data relevance
  • Bridge strain data abnormal value identification method based on data relevance
  • Bridge strain data abnormal value identification method based on data relevance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The following is based on Figure 1 to Figure 7 The specific embodiment of the present invention is further described:

[0048] A method for identifying outliers in bridge strain data based on data correlation, comprising the following steps:

[0049] 1) Obtain raw data from sensors installed at the same location.

[0050] The specific steps are:

[0051] Get the raw strain data collected by the strain sensor at the same position of the health monitoring system {x i},i=1,2,...,n and the original acceleration data collected by the acceleration sensor {y i}, i=1,2,...,n, where n represents the number of data.

[0052] 2) Extract the long-period trend data from the original strain data through wavelet decomposition, and obtain the difference between the original strain data and the long-period trend data.

[0053] The specific steps are:

[0054] a) Using wavelet decomposition to extract the long-period trend data {s of the original strain data i},i=1,2,...,n;

[0...

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 bridge strain data abnormal value identification method based on data relevance. The bridge strain data abnormal value identification method comprises the steps of obtaining the sensor original data installed at the same position; extracting the long-period trend data from the original strain data through the wavelet decomposition to obtain a difference value between the original strain data and the long-period trend data; according to the mean value and the standard deviation of the strain difference value data, obtaining a change range of the potential abnormal values in the original strain data; extracting the long-period trend data from the original acceleration data through wavelet decomposition to obtain a difference value between the original acceleration data and the long-period trend data; obtaining a change range of a potential abnormal value in the original acceleration data according to a mean value and a standard deviation of the acceleration difference data; comparing the occurrence position of the potential abnormal value in the original strain data with the occurrence position of the potential abnormal value in the original acceleration data, and judging and identifying the true abnormal value of the original strain data. According to the method, the problem of the strain data abnormal values in the bridge health monitoring can be accurately and efficiently solved.

Description

technical field [0001] The invention belongs to the field of analysis and research of bridge health monitoring data, in particular to a method for identifying abnormal values ​​of bridge strain data based on data correlation. Background technique [0002] The application of bridge health monitoring technology at home and abroad has gradually matured, and the functions of large-scale bridge structure health monitoring systems have gradually improved. However, due to the increasing number of its components and influencing factors, the potential for failures has gradually increased. The contradiction between the reliability and the limited life of the monitoring system equipment is more prominent. For example, the failure of individual components will often cause a chain reaction, resulting in the failure of the entire system to operate or even paralysis. In particular, if the monitoring data distortion caused by the monitoring system's own failure cannot be detected in time, i...

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): G06K9/00G06F17/18
CPCG06F17/18G06F2218/00
Inventor 任普
Owner 上海深物控智能科技有限公司
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