Bayesian network-based logic alarm root analysis method and system

A Bayesian network and analysis method technology, applied in the field of logic alarm root analysis method and system based on Bayesian network, can solve the problems of false alarm, missed alarm, incomplete root cause, etc., to eliminate negative effects and eliminate false alarms. Effects of alarms and missed alarms

Active Publication Date: 2019-08-27
SHANDONG UNIV OF SCI & TECH
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing methods require a certain number of alarm times to obtain a reliable estimate of the root cause of the alarm, and infer whethe

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
  • Bayesian network-based logic alarm root analysis method and system
  • Bayesian network-based logic alarm root analysis method and system
  • Bayesian network-based logic alarm root analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Aiming at the three main problems in the analysis of the root cause of the alarm described in the background technology, this embodiment provides a logical alarm root analysis method based on Bayesian networks. By applying the technology described in this embodiment, according to the alarm variable Variation detects root cause variables in all root cause variables, which may be one or multiple variables, and data samples can be obtained online to update the posterior probability parameters, overcoming random noise interference, incomplete analysis of root cause variables, and incomplete root cause variables The problem.

[0032] The logic alarm source analysis method based on Bayesian network in this embodiment specifically includes the following steps:

[0033] Step 1: Determine the update probability of the Bayesian network parameters.

[0034] Step 1.1: Use such as figure 1 The shown Bayesian network describes the alarm variable X a with root variable X 1 ,X 2 ,...

Embodiment 2

[0077] In one or more embodiments, a Bayesian network-based logical alarm root analysis system is disclosed, including:

[0078] A module used to represent alarm variables and source variables with binary 1 and 0, corresponding to alarm status and non-alarm status;

[0079] It is used to consider the prior conditional probability, complete the posterior estimation with the batch learning method and the maximum value function, and use the online update algorithm to complete the update of the probability parameters in the Bayesian network;

[0080] It is used to calculate the posterior probability based on the Bayesian formula. When an alarm occurs, the posterior conditional probability is expressed in the form of a vector and arranged in descending order, and the root cause is determined according to the position of the maximum posterior probability.

Embodiment 3

[0082] In one or more embodiments, a terminal device is disclosed, including a server, the server includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor executes the The program realizes the logic alarm root analysis method based on Bayesian network in the first embodiment. For the sake of brevity, details are not repeated here.

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 Bayesian network-based logic alarm root analysis method and system, wherein an alarm state and a non-alarm state are respectively represented by binary system 1 and binary system 0. The method comprises the following steps: when the root analysis is performed online, updating the Bayesian network probability parameter set from an observation sample in a recursive mode, and estimating the probability parameter set by adopting a maximum value function; and updating the posterior probability in an online manner according to a Bayesian calculation rule and a chain rule, expressing the posterior conditional probability in a vector form and arranging the posterior conditional probability in a descending order when an alarm occurs, and determining a root cause accordingto the position of the maximum posterior probability. According to the method, the influence of random noise is reduced by a Bayesian network logic analysis method, and the correctness of root analysis is ensured; and multiple coexisting root causes can be analyzed, and the concern only for the root cause that occurs initially is avoided.

Description

technical field [0001] The invention relates to the technical field of industrial alarms, in particular to a Bayesian network-based logical alarm source analysis method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Industrial alarm system is very important for modern factories, it can ensure the safe and efficient operation of factories and prevent accidents from worsening. Its primary function is to detect and communicate changes in alarm status and relay them to plant operators who will take corrective action to address the abnormal condition that caused the alarm. [0004] The inventors found that there are currently multiple methods to analyze the root cause of the alarm, including formulating standard rules or expert systems to analyze alarm failures, explaining alarms based on tables describing the relationship between...

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
IPC IPC(8): G08B29/18G08B29/20G06N7/00
CPCG08B29/185G08B29/20G06N7/01
Inventor 王建东王振杨子江周东华
Owner SHANDONG UNIV OF SCI & TECH
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