Unlock instant, AI-driven research and patent intelligence for your innovation.

A time series bridge monitoring data analysis method based on mapreduce framework

A mapreduce framework and time series technology, applied in data mining, data processing applications, electrical digital data processing, etc.

Active Publication Date: 2021-01-08
LIAONING UNIVERSITY OF TECHNOLOGY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the research on bridge health status monitoring data has not played its true role, and has not yet been able to make full use of the information contained in monitoring data on various time scales to realize efficient mining of data evolution laws and different types of sensor collection from massive data. A long-term monitoring mechanism for the relationship between data

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
  • A time series bridge monitoring data analysis method based on mapreduce framework
  • A time series bridge monitoring data analysis method based on mapreduce framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0031] Such as Figure 1-2 As shown, the present invention provides a kind of time series bridge monitoring data analysis method based on MapReduce framework, comprises the following steps:

[0032] Step 1: The time series raw data about bridge health indicators is composed of historical data and daily real-time data collection, and the raw data is preprocessed by cleaning invalid data and filling missing values ​​by interpolation; the cleaning of invalid data The method is: for the univariate time series in the original data, use the clustering method to detect the outliers, that is, use the standard deviation change of the univariate time series to perform cluster analysis on any piece of data. Specifically include the following steps:

[0033] Step 1.1: Create a univaria...

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 MapReduce frame based time sequence bridge monitoring data analysis method. The method includes the following steps: a first step, performing pretreatment on time sequence original data about a bridge health indication, and acquiring valid data; a second step, improving an ARIMA time sequence analysis method in parallel, and performing ARIMA model construction on the pre-treated valid data set; a third step: predicting a future value according to the constructed ARIMA model in the second step; and a fourth step: showing the analysis result, forming bridge health evaluation, and providing a scientific basis for maintenance. The MapReduce frame based time sequence bridge monitoring data analysis method can achieve real-time monitoring of structure response and behaviors in a target operation stage in various environment conditions so as to acquire various types of information reflecting the structural condition and environmental factors, can analyze the health condition of a bridge, can evaluate the reliability of the bridge structure, and can provide a scientific basis for maintenance demands and measure-making.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a time series bridge monitoring data analysis method based on a MapReduce framework. Background technique [0002] As one of the key parts of national infrastructure construction, bridge engineering has become an extremely important transportation hydraulic hub. Especially in recent years, the number of high-speed railways and cross-sea bridges in China has been increasing. Due to the influence of local climate, oxidation, environmental corrosion and other unfavorable factors on various facilities, the bridge structure will inevitably produce natural aging under the action of static load or live load for a long time, and the damage will continue to accumulate. The performance of the structure will gradually deteriorate, and the safety of roads and bridges will be constantly threatened. Its safety is directly related to national property and people's lives. Ther...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/2458G06F16/2453G06F16/215G06Q10/04G06Q10/06G06Q50/08
CPCG06F2216/03G06Q10/04G06Q10/0639G06Q50/08G06F16/215G06F16/24532G06F16/2465G06F16/2474
Inventor 史伟颜飞李畅张兴李万杰李帅
Owner LIAONING UNIVERSITY OF TECHNOLOGY