Fault diagnosis method and system based on qualitative trend analysis and five-state Bayesian network, equipment and storage medium

Abstract

The invention discloses a fault diagnosis method and system based on qualitative trend analysis and a five-state Bayesian network, equipment and a storage medium, and aims to solve the defect technical problem that a fault diagnosis method in the prior art only has normal and abnormal conditions, and only two states cannot describe the variation trend of the variables and the influence relationship of positive and negative effects between the variables in detail. According to the method, fault reasoning diagnosis is carried out in a multivariable time sequence system, firstly, multivariable time window data and two linear segments are defined, an optimal segmentation point is obtained, the two linear segments are solved according to the optimal segmentation point, then the next linear segment is described by adopting five states of normal, rising, falling, positive step and negative step, a causal relationship network is constructed according to the causal relationship of the variables, the state of each variable is judged by using a qualitative trend analysis method in real time, reasoning diagnosis is performed by using a five-state Bayesian network, and the root cause and the fault propagation path of the fault of the current system are judged.

Description

technical field [0001] The invention belongs to the field of fault diagnosis and relates to a fault diagnosis method, system, equipment and storage medium based on qualitative trend analysis and five-state Bayesian network. Background technique [0002] When a multivariable sequential system fails, multiple variables often deviate abnormally, and it is difficult for staff to quickly determine the root cause of the failure based on experience. The purpose of fault inference diagnosis is to reason and diagnose the root cause of the system failure according to the change trend of abnormal variables, and to give the fault propagation path. The results of fault reasoning and diagnosis have important guiding significance for the staff to understand the system status and fault type, and can also assist the staff to manually adjust the operating variables according to the identification and diagnosis results, so that the system can be adjusted to its normal state as soon as possible...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the above-mentioned shortcoming of the prior art, the object of the present invention is to provide a kind of fault diagnosis method, system, equipment and storage medium based on qualitative trend analysis and five-state Bayesian network, aiming to solve the fault diagnosis method in the prior art There are only two states, normal and abnormal, and it is impossible to describe in detail the variable trend and the positive and negative influence relationship between variables with only two states.

Images