Reliability modeling method of aviation power system based on Bayesian network

Abstract

The invention discloses an aviation power supply system reliability modeling method based on Bayesian network, which comprises the following steps of: establishing an input-output relationship description table for each component of the aviation power supply system; Bayesian network node are constructed correspond to that data of each row of N sub-tables; determining a parent node of each node ofthe built Bayesian network; constructing a parent node with the same name for the element Ci in step 2, and determining the conditional probability distribution of each node on the basis of determining the state of each node of the constructed Bayesian network; determining a target node for the power supply bus bar and calculating the power supply reliability of the aviation power supply system. The corresponding target node is determined for each power supply bus bar, and the power supply reliability of the aviation power supply system is calculated. The invention improves the reliability calculation efficiency of the aviation power supply system.

Description

technical field [0001] The invention relates to the technical field of system engineering reliability evaluation, in particular to a Bayesian network-based aviation power system reliability modeling method. Background technique [0002] At present, with the development of aircraft towards more electrification and full electrification, traditional hydraulic energy, pneumatic energy and mechanical energy are gradually replaced by electric energy, and the number of onboard electrical and electronic equipment has increased sharply. The power supply objects (i.e. loads) include lifesaving, flight control, Deicing, navigation and other systems, these loads have made aviation power supply a key system related to aircraft flight safety. Therefore, it is of great significance to carry out reliability assessment of large-scale aviation power supply system to ensure flight safety. [0003] At present, the aviation power system integrates the power generation link and the power distrib...

AI Technical Summary

Problems solved by technology

[0004] However, with the increase of the number of components in the minimum diameter set of each bus bar, if the minimum diameter set is directly converted into an equivalent Bayesian network, there will be problems of low computational efficiency or even combinatorial explosion. Without the help of network structure optimization algorithms, Bayesian network Accurate reasoning algorithms will not be implemented; secondly, since the design of the aviation power system directly faces the structural diagram of the aviation power system, the traditional reliable The reliability modeling process is reduced to "Aviation Power System Structural Diagram - Equivalent Bayesian Network Reliability Model", which will undoubtedly improve the efficiency of aviation power system design

Images