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

Alarm system optimization method based on bayesian network

A Bayesian network and optimization method technology, applied in the field of alarm system optimization based on Bayesian network, can solve problems such as disturbing the normal judgment and reasonable disposal of operators, unreasonable alarm settings, and failure to serve as an early warning.

Active Publication Date: 2015-10-28
BC P INC CHINA NAT PETROLEUM CORP +1
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Especially when a fault occurs, due to the internal interaction of the system and the unreasonable alarm settings, a large number of alarm information will appear. Interfering with the operator's normal judgment and reasonable handling, so that the operator cannot determine the real source of the fault (Root Cause), this situation is called alarm flooding (Alarm Flooding)

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 system optimization method based on bayesian network
  • Alarm system optimization method based on bayesian network
  • Alarm system optimization method based on bayesian network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0074] The following are two specific implementation cases: the former is used to illustrate the specific implementation steps; the latter is used to show the scale of the problem that can be solved.

[0075] Case study one:

[0076] 1.1. Prepare alarm data

[0077] figure 2 It is a schematic diagram of a water tank alarm system according to an embodiment of the present invention (wherein, Figure 2-Figure 23 Among them, L stands for Level (water level), I stands for Inlet (inlet), O stands for Outlet (outlet)); the alarm data synthesized by the water tank alarm system is shown in the table below, where NR means return to normal, HI means high alarm (alarm higher than the upper limit), LO means low report (alarm lower than the lower limit).

[0078] Table 1. Synthesized water tank DCS system alarm data

[0079]

[0080]

[0081] 1.2. Preprocessing alarm data

[0082] The preprocessing alarm data is shown in the table below.

[0083] Table 2. Expand the status of a...

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 system optimization method based on a bayesian network. The optimization method comprises the following steps: firstly, alarm data is collected, and the alarm data comprises alarm variables and alarm kinds; secondly, pretreatment of the alarm data is carried out, a data set used for bayesian network learning is generated according to states of the alarm variables; thirdly, correlation relations among the alarm variables are monitored from the alarm data learning, and qualitative and quantitative characterization of the correlation relations is carried out by utilization of the bayesian network ; fourthly, the obtained bayesian network is employed to adjust an alarm network, the root reason causing alarm is positioned rapidly and alarm flooding is reduced. The purpose is that an alarm system management method based on the bayesian network is employed to optimize alarm network performances, alarm flooding is reduced as possible, and therefore the method helps people to position the root reason causing alarm rapidly and take steps.

Description

technical field [0001] The invention relates to the field of alarm systems, in particular to a method for optimizing an alarm system based on a Bayesian network. Background technique [0002] In the early industrial enterprises, the control system was relatively simple, and each alarm signal was directly connected to the central control room through a hard line, but this method was expensive and complicated to maintain, and could not achieve good results. In the modern process industry, control methods such as single closed-loop control and cascade control have been maturely used, and the production scale is becoming increasingly complex and large-scale. Programmable logic controller (PLC), fieldbus control system (FCS) and distributed control system (DCS) has been widely used, which makes the generation and collection of alarms very easy. The expansion of the system scale and the simplicity of alarm signal setting inevitably produce a large number of false or redundant alar...

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): G08B29/18
CPCG08B29/185
Inventor 王杭州徐文浩丁泉会王雪梅陈红捷
Owner BC P INC CHINA NAT PETROLEUM 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