A Recognition Method of Correlation Alarm Based on Data Extraction

A recognition method and data extraction technology, applied to alarms, instruments, etc., can solve problems such as not paying attention to the degree of correlation of alarm signals
CN103440730BActive Publication Date: 2016-04-06TSINGHUA UNIV
8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TSINGHUA UNIV
Publication Date
2016-04-06

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a relevant alarm identification method based on data extraction, and belongs to the technical field of industrial inspection and alarm technologies. The method comprises the steps that the number of alarm variables in a detected system is determined, and alarm time of each alarm variable is monitored and recorded; a causal relationship topology graph with an independent alarm variable as the node is drawn, namely, a period of time is firstly selected, whether two alarm variables are mutually related or not is determined according to the alarm time of the two alarm variables; regarding to all alarm variable pairs which are not calculated in the detected system, association degree and causal strength between each alarm variable pair are acquired, and the causal graph is supplemented to be complete according to the calculation result. The alarm causal graph, within a period of time, of a system can be acquired through the causal strength, between every two alarm variables, given by the bidirectional association degree, if the causal strength exceeds a contain threshold value, a user can determine that two alarm signals are related, and therefore operation efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of industrial detection and alarm, in particular to a method for identifying associated alarms based on data extraction. Background technique

[0002] With the increasing size and complexity of industrial enterprises, more and more failures not only affect the benefits of enterprises, but also bring a lot of safety problems. In industrial applications, the application of classic control methods such as single loop and cascade has been very mature, and single point alarm and fault diagnosis of local systems have also been widely used. However, as the scale of the system continues to increase, the large number and disorder of the alarms gradually reduce the operating efficiency of the operator. How to scientifically manage the numerous alarm signals to achieve the purpose of filtering invalid alarm signals and highlighting key alarm signals, thereby Improving operational efficiency and reducing the probabilit...

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