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

An outlier processing method for value filtering in sliding window box plots

A processing method and technology of abnormal points, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of unsmooth data waveforms, false filtering, missed or misjudged abnormal points, etc., and achieve time series waveforms Sleek, data quality-enhancing effects

Active Publication Date: 2022-02-01
CENT SOUTH UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides an outlier processing method for value filtering in a sliding window box graph, so as to overcome the missing or misjudgment of outliers and the median Filtering is easy to cause false filtering for non-abnormal points, and the data waveform after median filtering is not smooth enough, etc.

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
  • An outlier processing method for value filtering in sliding window box plots
  • An outlier processing method for value filtering in sliding window box plots
  • An outlier processing method for value filtering in sliding window box plots

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] like figure 1 As shown, this embodiment provides an abnormal point processing method of a variable filtering in a slide-shaped diagram, including the following steps:

[0025] A. Time series of process variables collected in real time during industrial processes, using a box type diagram method of a slide box to detect the sample sequence;

[0026] b, build an abnormal point detection count vector, statistically the number of abnormal points per initial judgment is detected in all slippers, if it is greater than the set anomaly point detection frequency threshold, it is identified as a formal abnormal point, otherwise, identification Reserved for misunderstanding;

[0027] c, the abnormal point data of the determination is used to remove and fill the neighboring medium value filtering method, forming normal continuous time series data;

[0028] Specifically, in step a, a specific method of detecting an abnormal point for a slide-shaped diagram for the process variable time ...

Embodiment example 2

[0081] like Figure 2-8 As shown, on the basis of the above embodiment, the present embodiment provides a method of hydrocracking process anomaly treatment method, which uses an abnormal point treatment method of the value filtering in the above-described slide box type diagram, including the following steps. :

[0082] A. Time series of process variables collected in real time during industrial processes, using a box type diagram method of a slide box to detect the sample sequence;

[0083] b, build an abnormal point detection count vector, statistically the number of abnormal points per initial judgment is detected in all slippers, if it is greater than the set anomaly point detection frequency threshold, it is identified as a formal abnormal point, otherwise, identification Reserved for misunderstanding;

[0084] c, the abnormal point data of the determination is used to remove and fill the neighboring medium value filtering method, forming normal continuous time series data;

...

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 method for processing abnormal points of value filtering in a sliding window box graph, which comprises the following steps: aiming at the time series of process variables collected in real time in industrial processes, using a sliding window box graph method to detect the abnormal points; Count the number of times each initial abnormal point is detected in all sliding window boxes. If it is greater than the set abnormal point detection frequency threshold, it will be considered as a formal abnormal point. Otherwise, it will be regarded as a false detection and retained; The data points that are abnormal points are processed by the neighborhood median filter method to form normal continuous time series data. The present invention uses the sliding window box diagram method to detect abnormal points, avoiding the problem of missed judgment caused by full-box processing or misjudgment caused by binning processing, and only performs neighborhood median filtering on detected abnormal points, so that the data The detailed structure is protected from damage, and the time series is as smooth as possible, which greatly reduces the impact of missed or misjudgment of abnormal points on the time series, and effectively improves the data quality.

Description

Technical field [0001] The present invention relates to the field of data-driven data pretreatment technology, and in particular, there is a abnormal point treatment method for the medium value filtering of the slide-type diagram of the complex industrial process. Background technique [0002] During the complex industrial process, there are many interference in the generation, acquisition, transmission, and conversion process of process variable data, mainly divided into internal interference and external interference. Internal interference mainly includes the basic nature or internal circuit caused by the inherent interference and data acquisition system of the industrial process equipment, etc.; external interference mainly includes artificial adjustment or weather such as interference and electromagnetic wave or power supply such as industrial process equipment to enter data collection. Interference caused by the internal system. Due to the presence of interference, the acqui...

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): G06F16/2458
Inventor 王雅琳张鹏程袁小锋夏海兵李灵曹跃阳春华
Owner CENT SOUTH UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com