Elevator health diagnosis method based on bayesian network

Abstract

The invention discloses an elevator health diagnosis method based on a bayesian network. Different samples of elevator failures are used for carrying out bayesian network structure and parameter learning, the Monte carlo reasoning mechanism is adopted to build a bayesian network elevator failure diagnosis model meeting the elevator running mechanism, and compared with other diagnosis methods for predication according to the characteristic states, the bayesian network elevator fault diagnosis model considers the restrictive relation between state variables of a complex system, the method is more scientific and strict, through existing data samples, it is verified that the method can achieve the higher predication rate, the elevator health diagnosis method based on the bayesian network is quite effective in elevator health diagnosis and predication aspects, and the wide application prospect is achieved.

Description

technical field [0001] The invention relates to the technical fields of computers and elevators, in particular to an elevator health diagnosis method based on a Bayesian network. Background technique [0002] With the continuous development of science and technology in our country, the transportation of domestic cities has become very convenient, and most cities have begun to build subways. The normal order of the subway station is inseparable from the operation of the elevator, so the maintenance of the elevator is particularly important. The health diagnosis of the elevator in the subway station is an important content of the elevator maintenance. [0003] At present, the Bayesian Network (Bayesian Network-work) based on probabilistic reasoning is a technology developed in recent years to solve the problems of uncertainty and incompleteness. Faults caused by interconnectivity have great advantages. As a method of describing the directed graph of the probability relationsh...

AI Technical Summary

Problems solved by technology

[0003] At present, the Bayesian Network (Bayesian Network-work) based on probabilistic reasoning is a technology developed in recent years to solve the problems of uncertainty and incompleteness. Faults caused by interconnectivity have great advantages. As a method of describing the directed graph of the probability relationship, it combines prior information and uses the relevant theory of probability to solve the problems caused by different signals and signal correlations in the system. For deterministic problems, the posterior probability calculated by Bayesian theorem can be applied to decisions that depend on multiple control factors. At present, Bayesian networks have begun to be used in the field of fault diagnosis, but they have not yet been used in the diagnosis of elevator faults.

[0004] The structure of the elevator system is complex, consisting of seven subsystems, and the relationship between the system components is complicated. It is difficult to establish a corresponding mathematical model according to its operating state

In the field of elevator fault diagnosis, there are many signals that characterize the fault state of the elevator system, and because fault prediction is a research process on relevant important signals before the fault occurs, the diagnostic objects are complex, the testing methods are limited, and the knowledge is not accurate. There are many uncertainties in fault diagnosis, mainly including: there are many correlations and interconnections between index signals; the same fault may be caused by one or more abnormal signals, or an abnormal signal may cause single or multiple abnormal signals at the same time. Fault

At present, most of the literatures focus on the fault diagnosis of simple systems, and have achieved certain scientific research results. However, there are very few related reports on elevator system fault prediction in domestic and foreign literatures.

Images