Fault Diagnosis of RAT Actuator Based on Bayesian Network

The RAT (ram air turbine) system is the last barrier to ensure the safety of the aircraft. The actuator needs to be released correctly to perform the function of the device. However, it is difficult to identify the cause of the failure because of its concealment and the lack of monitoring data. To solve the above problems, fault diagnosis method of RAT actuator based on Bayesian network is proposed. Firstly, a fault tree model of the RAT actuator is established. Secondly, on the basis of mapping relationship between fault tree and Bayesian network, a Bayesian network model of the failures in actuator deployment process is established. Finally, a model based on Bayesian network is constructed using the Netica tool, which is verified by case analysis, providing technical support for the fault diagnosis of the RAT actuator.