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

Chemical abnormal causality analysis and graphic display method based on time sequence fluctuation association

A causal analysis and graphic display technology, applied in the direction of instruments, electrical digital data processing, hardware monitoring, etc., can solve the problems of alarm flooding, low accuracy rate, and large calculation amount, and achieve high accuracy rate, less calculation amount, and calculation amount small effect

Active Publication Date: 2019-11-15
CHINA PETROLEUM & CHEM CORP +2
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is the problem of flooding of alarms, low accuracy and large amount of calculation in the prior art, and it provides a new method based on timing fluctuation correlation The chemical abnormality causal analysis and graphic display method has the advantages of precise alarm, high accuracy rate and small calculation amount

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
  • Chemical abnormal causality analysis and graphic display method based on time sequence fluctuation association
  • Chemical abnormal causality analysis and graphic display method based on time sequence fluctuation association
  • Chemical abnormal causality analysis and graphic display method based on time sequence fluctuation association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] Depend on figure 1 As shown, a chemical abnormality causal analysis and graphic display method based on time series fluctuation correlation, including real-time collection platform construction of device data, data preprocessing, univariate volatility analysis and fluctuation time series calculation, causality based on fluctuation correlation degree Links such as network construction, root cause mining of abnormal working conditions, and image interface display and output.

[0021] Real-time data acquisition platform construction: According to the data acquisition interface provided by the enterprise (the sampling frequency in the real-time database can reach 1 time / minute or 2 times / minute, and the data frequency collected from the DCS system using the OPC DA specification can reach 1 time / second ), using VC++ programming to implement an OPC DA server framework, collect real-time data from the control system of the device or enterprise real-time database, refresh the r...

Embodiment 2

[0028]Graphical interface display output: Alarm points are displayed in the form of nodes, and their root cause paths are also displayed, fluctuation variables are displayed in the form of nodes, and causal relationships are displayed in the form of arrows. If there are multiple fluctuations in the root cause of an alarm in the current period node, then merge different root cause paths at this alarm node, and finally form a tree structure display.

[0029] exist figure 2 Among them, after the variable TI2703A (the temperature of the discharge path A of the vacuum furnace F102 in an atmospheric and vacuum device) alarmed, according to the correlation analysis of time series fluctuations, there are three causes of this variable: F102XL (thermal efficiency of the vacuum furnace F102), AIC3908 ( Oxygen content in convection chamber of decompression furnace F102), PI2601 (feed pressure of decompression furnace F102); there are two root causes of variable F102XL: TI3913 (temperatur...

Embodiment 3

[0031] By analyzing the actual device operation data, the root cause alarm results are obtained (see Table 1). The source of the data is the operation data of the atmospheric and vacuum equipment of a refining and chemical company from November 1 to November 4, 2016, and the sampling frequency is 2 times / minute. For example, in the first alarm bit number "FIC2601A" in Table 1, the variable generates a high alarm at time 4714, that is, its operating value exceeds the high alarm line, and then record its alarm time. In order to find the root cause of the alarm, according to the method introduced in this patent, find the fluctuation moments of all variables in the device, take "FIC2601A" as the result variable, and other variables as the cause variable, and calculate the membership of "FIC2601A" and other variables When both the membership degree and the confidence degree exceed the threshold, it is considered that the variable has a causal relationship with "FIC2601A", so two ro...

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 relates to a chemical abnormal causality analysis and graphic display method based on time sequence fluctuation association, and mainly solves the problems of alarm flooding, low accuracy and large calculated amount in the prior art. According to the technical scheme of the invention, the chemical abnormal causality analysis and graphic display method based on the time sequence fluctuation association is adopted, and the method comprises the steps of real-time acquisition platform construction of chemical device data, data preprocessing, univariate volatility analysis and fluctuation time sequence calculation, causal relationship network construction based on fluctuation correlation degree, abnormal working condition root cause mining and image interface display output. Basedon a time sequence fluctuation correlation analysis method, the correlation between variables is described by utilizing operation data, and alarm and operation guidance are provided in time; according to the technical scheme that the current alarm point information is displayed in the graphic display interface, the problems are well solved; and the method can be used for chemical abnormal cause and effect analysis and graphic display.

Description

technical field [0001] The invention relates to a chemical abnormality causal analysis and graphic display method based on timing fluctuation correlation. Background technique [0002] In the alarm system, alarm redundancy often occurs. Too many alarm times and too frequent frequencies make the operator face too much alarm information, and cannot effectively find the key points of abnormal operation conditions. How to control the alarm frequency, reduce the number of alarms, eliminate redundant alarms, and improve the accuracy of alarms are important issues in alarm management. [0003] During the operation of the petrochemical plant, due to the strong coupling and correlation of the system, the fluctuation of a certain parameter often causes the fluctuation of related parameters, and the related parameters will cause the fluctuation of more parameters, thus generating a large number of Call the police. If the initial cause of the alarm is found in these large amounts of a...

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): G06F11/32G06F11/34
CPCG06F11/327G06F11/322G06F11/3476
Inventor 韩华伟王春利李传坤高新江
Owner CHINA PETROLEUM & CHEM CORP
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