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

Alarm root cause diagnosis method based on chemical process knowledge automation

A technology of chemical process and diagnosis method, which is applied in the direction of program control, comprehensive factory control, instrument, etc., can solve the problems of heavy workload in topology model establishment, over-reliance on manual decision-making, low accuracy of alarm root cause diagnosis, etc., and achieve good application Effectiveness, strong decision-making ability, and high accuracy

Active Publication Date: 2020-12-29
CHINA UNIV OF PETROLEUM (EAST CHINA) +1
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the above-mentioned problems in the prior art, such as low accuracy rate of alarm root cause diagnosis, excessive reliance on manual decision-making and heavy workload of topology model establishment, and proposes an automatic alarm root cause diagnosis method based on chemical process knowledge

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
  • Alarm root cause diagnosis method based on chemical process knowledge automation
  • Alarm root cause diagnosis method based on chemical process knowledge automation
  • Alarm root cause diagnosis method based on chemical process knowledge automation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] see Figure 1-3 , an automatic alarm root cause diagnosis method based on chemical process knowledge, including the following steps:

[0032] Step 1: Based on the analysis of deviation causal time series transfer, use chemical process knowledge to establish process topology, collect chemical process alarm data and time information; Step 2: judge the causal relationship between variables through path search, and automatically deduce the root cause of the alarm; Step 3: Automatically retrieve alarm root cause keywords through instant search engine, retrieve relevant operation information from database, and assist operators in decision-making.

[0033] Establishment of deviation causal transfer process topology: using the improved HAZOP analysis method, optimize the HAZOP analysis table through initial cause-intermediate cause-deviation-intermediate consequence-final consequence, and establish a process that can be recognized by the computer through the causal correlation ...

Embodiment 2

[0043] see Figure 4 , the difference from the first embodiment is that the second embodiment has a decision output, the decision interface output: the root cause of the alarm is the initial node, and the causal transfer path is presented in the form of a symbolic directed graph. Among them, the alarm bit number with the highest alarm priority is highlighted.

[0044] exist Figure 4 In , the auxiliary decision-making information intelligently retrieved through the instant search system is displayed on the far left of the image. When the low EDC flow alarm, the high temperature alarm of the VCM cracking furnace and the high pressure alarm of the VCM cracking furnace tube occur at the same time, according to the established deviation causal transmission path, the associated alarm identification is automatically carried out. There are 3 reasons for the low EDC flow rate, and 2 reasons The initial reason is the low pressure of the EDC reactor and the other is the intermediate r...

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 an alarm root cause diagnosis method based on chemical process knowledge automation. The method comprises the steps of process topology establishment of deviation causal transmission, real-time collection of alarm data, associated alarm identification, alarm root cause diagnosis and an auxiliary decision-making system. According to the method, based on deviation causal timesequence transmission analysis, a process topology model is established by fully utilizing chemical process knowledge, chemical process alarm data and time information thereof are collected, causal association among variables is judged through path search, an alarm root cause is automatically reasoned, an alarm root cause keyword is automatically retrieved through an instant search engine, related operation information is retrieved from a database, an operator is assisted in making a decision, and the problems that in the prior art, the alarm root cause diagnosis accuracy is low, manual decision making is excessively relied on, and the workload of topology model establishment is large are solved.

Description

technical field [0001] The invention relates to a method for diagnosing the root cause of an alarm in a chemical enterprise, in particular to a method for diagnosing the root cause of an alarm based on the automation of chemical process knowledge. Background technique [0002] The phenomenon of "alarm flooding" that often occurs in the field of alarm management in chemical enterprises brings great interference to process safety, and the inability to accurately and quickly determine the root cause of alarms becomes a common phenomenon during "alarm flooding". At present, enterprises mainly rely on manual decision-making to diagnose the root cause of alarms, which has obvious subjectivity and inconsistency. Especially when there are many alarms in a short period of time, it is difficult to deal with large process fluctuations simply by relying on manual decision-making. [0003] There is a strong correlation between the alarm variables in the chemical process. If the causal r...

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): G05B23/02
CPCG05B23/0262G05B2219/24065Y02P90/02
Inventor 孟亦飞刘庆龙刘尚志赵东风宋肖苗酒江波王效天
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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