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

EEMD-neural network based real-time data abnormal value detection method

A real-time data and neural network technology, applied in the field of data analysis, can solve problems such as unreliable real-time monitoring data

Active Publication Date: 2017-12-12
中国航天系统科学与工程研究院 +2
View PDF6 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical solution problem of the present invention is: overcome the deficiency of prior art, provide a kind of real-time data outlier detection method based on EEMD-neural network, be used for solving the problem that there is unreliable data in real-time monitoring 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
  • EEMD-neural network based real-time data abnormal value detection method
  • EEMD-neural network based real-time data abnormal value detection method
  • EEMD-neural network based real-time data abnormal value detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0102] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0103] Step 1: Identify research subjects and obtain data

[0104] Taking the daily water intake data of a waterworks B1 in North China as the research object. The daily water intake monitoring data comes from the national water resource management system database. The selected time range is two years from January 1, 2015 to December 31, 2016, a total of 731 days. The data of 365 days in 2015 is used as historical data, and the data of 366 days in 2016 is used as real-time data.

[0105] Step 2: Historical data outlier detection and correction

[0106] (2.1) Visualization of historical time ser...

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

An EEMD neural network based real-time data abnormal value detection method is provided, and the problem that the existing real-time data abnormal value detection method does not consider the historical data abnormal value is taken into account. The method comprises: obtaining historical time series data, and sorting the historical data according to a chronological order; using a median method to carry out preliminary detection on the historical data; finely detecting the historical data by using an EEMD method, and replacing the detected abnormal value with a zero value; then using the curve fitting method to fill the zero value, that is, correcting the abnormal value, and obtaining historical data closer to the objective reality after carrying out abnormal value detection and correction; and finally, by learning the historical data, using the neural network method so that the to-be-reported real-time data can be more accurately predicted, comparing the predicted value with the real-time reported monitored value so that whether there is abnormality can be determined, and correcting the abnormality. The method can be used to detect the real-time data abnormal value in one-dimensional time series, and is applicable to a wide range of fields such as water resources, traffic, weather, thermal power generation and other real-time monitoring data abnormal value detection.

Description

technical field [0001] The invention relates to a real-time data abnormal value detection method based on EEMD-neural network, which belongs to the field of data analysis. Background technique [0002] For the research on outlier detection methods of real-time data, predecessors have proposed methods such as neural network and support vector machine, but did not consider the outlier processing of historical data, because accurate prediction of real-time data needs to be based on reliable historical data . For historical data outlier detection, commonly used methods include outlier detection methods based on statistics, clustering, distance, density, etc., but these methods do not consider the time series change characteristics of time series data, but consider the complete set of data, hidden in the local outliers are difficult to detect. The present invention adopts the median-EEMD method for historical data to effectively detect local abnormal values ​​of time series, an...

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): G06F17/30G06N3/02
Inventor 方海泉蒋云钟周铁军万毅冶运涛薛惠锋王海宁郭姣姣罗婷
Owner 中国航天系统科学与工程研究院
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