Unmanned aerial vehicle engine rapid diagnosis method based on grey optimization Bayesian network

Abstract

The invention discloses an unmanned aerial vehicle engine rapid diagnosis method based on a grey optimization Bayesian network. The method comprises the following specific steps: step 1, constructing a fault tree model of an unmanned aerial vehicle engine; 2, qualitative and quantitative analysis based on the fault tree; 3, screening important intermediate events by using a grey correlation analysis optimization model; 4, converting the fault tree model into a Bayesian model; and step 5, rapid diagnosis and result utilization. The invention provides a fault tree and Bayesian network fusion diagnosis framework based on grey correlation analysis optimization aiming at the fault characteristics of a remote control engine of an unmanned aerial vehicle, and in the process of converting a diagnosis model from a fault tree to a Bayesian model, important intermediate events are extracted by grey correlation analysis optimization; therefore, the directivity of the Bayesian network nodes is enhanced, the problems that an original model cannot display and express important information and the diagnosis efficiency is low are solved, the diagnosis method has faster and more accurate diagnosis positioning capacity, and support is provided for equipment maintenance.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to a rapid diagnosis method for an unmanned aerial vehicle engine based on a gray-optimized Bayesian network. Background technique [0002] The reliable and stable operation of the remote control engine of the UAV is an important guarantee for the UAV to complete the flight mission. The failure of the remote control engine during the flight mission will cause the UAV to fail to start in the air, resulting in the failure of the flight mission and the loss of air superiority on the battlefield. Therefore, early detection of the weak links of the remote control engine, rapid and accurate detection and location of faults is an important guarantee for the stable operation of the remote control engine of the UAV in combat training. [0003] At present, fault diagnosis methods are mainly divided into data-driven, model-driven and hybrid-driven methods. Since the failure mode of t...

AI Technical Summary

Problems solved by technology

The transformed Bayesian network model still cannot fully and directly display the important information hidden in the diagnostic object, which is not conducive to effectively and directly mining the fundamental problems of the system

As a result, this method cannot highlight the key points of troubleshooting for fault location, and the diagnosis efficiency is low

Images