Monitoring data exception identification and processing method and system

A monitoring data and processing system technology, applied in the direction of electrical digital data processing, special data processing application, database update, etc. Effects of correlation, adding weights, and avoiding outlier data

Active Publication Date: 2020-12-29
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods do not consider the change of equipment in time, and the accuracy of recognition is not high

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
  • Monitoring data exception identification and processing method and system
  • Monitoring data exception identification and processing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] see figure 1 , a method for identifying and processing abnormal monitoring data, comprising the following steps:

[0043] Step 1: According to the number of data items in the monitoring data, confirm the identification position corresponding to each data item. For example: There are 5 data items, item 1~item 5. Then the assigned identification position is figure 2 As shown, the corresponding int data range is (0~31). In this step, the data of each monitoring instrument is a data item, for example, the data collected by the water pressure sensor is a data item.

[0044] Step 2: For each data item, arrange the data in ascending order of time (that is, sort according to the collection time from early to late), and perform mean filtering on the first few (preferably greater than 5) data to filter out obvious abnormal data.

[0045] Step 3: For each data item, use the data processed in step 2 to establish their respective Kalman filter models, and sequentially feed back...

Embodiment 2

[0058] A system for identifying and processing abnormal monitoring data, including a data abnormal identification field building module, a data prediction module, a suspected abnormal data judging module, an audit and correction module, a monitoring filter updating module, and a threshold filter updating module.

[0059] Data Exception Identification Field Building Blocks

[0060] Since there may be more than one data item collected by the sensor device, if an identification field is established for each field to identify the data, the entire data will be redundant. The present invention adopts the int data type to mark the abnormality of each data item, and the specific method is, each bit of the int data type under the binary data type identifies a collected data item, such as one 8-bit int data has 8 Binary data: 00000000~11111111, each bit of binary data has two data values ​​of 0 or 1, the present invention marks 1 as abnormal data, and 0 as normal data, so an 8-bit int d...

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 monitoring data exception identification and processing method and system, and the method comprises the steps: predicting to-be-analyzed and judged monitoring data through employing a Kalman filter data prediction principle, and preliminarily judging whether the monitoring data is exceptional or not through the comparison of a prediction value and a monitoring value; performing secondary correction on the preliminarily judged abnormal data through manual supervision, and performing updating processing of a filter and updating of a threshold model on a correction result. The method is different from general data model filtering, considers the change condition of equipment in time, increases the weight of a current normal monitoring value, has time correlation, meets the requirements of scenes such as environment change monitoring and instrument loss monitoring.

Description

technical field [0001] The invention relates to the technical field of abnormal data identification and data cleaning, in particular to a method and system for identifying and processing abnormal monitoring data. Background technique [0002] At present, with the continuous development of sensor technology, more and more data are collected, and the analysis and decision-making of data can provide strong support for related industries. However, the data collected by the equipment cannot be accurate for every item, and the data will be abnormal due to various reasons. When the abnormal data is used for analysis and decision-making, wrong judgments may be made. Therefore, it is necessary to make abnormal judgments on the collected data items. and processing is particularly important. For the processing of wrong data in abnormal data, the commonly used processing methods are: to eliminate outliers by means of clustering, regression, binning, etc.; it is also possible to elimina...

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 Applications(China)
IPC IPC(8): G06F16/215G06F16/23G06F16/248
CPCG06F16/215G06F16/23G06F16/248Y02P90/02
Inventor 罗小娅
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap