A Bayesian Network Fault Diagnosis Method for Satellite Attitude System
The attitude control system is an important component of satellite systems,and due to its high cost,mal-functions can cause adverse effects.With the development of aerospace science and technology,the satellite attitude control system has become more and more complex,and the probability of its failure has also increased.Considering the lacking of confidence,poor robustness and easy overfitting in fault diagnosis of traditional neural networks,this pa-per proposes a new Bayesian LeNet network model which composed of a Bayesian linear layers and a Bayesian convo-lutional layers.After analyzing and processing of the fault data of the flywheel components of the satellite attitude con-trol system,the Bayesian network model was used to conduct the fault simulation experiment and compared with the Bayesian fully connected neural network and the traditional LeNet.The results show that under the premise of three possible failures of the flywheel,the Bayesian neural network has better accuracy and less overfitting.The Bayesian neural network is verified.
Satellite attitude control systemFault diagnosisBayesian neural networkDeep learning
NETL
NSTL
万方数据
维普
