Fault Prediction and Condition Monitor of Turbojet Engine Ground Starting

摘要

In the UAV (Unmanned Aerial Vehicle) engine starting process, on account of its dynamic environment, mechanical complexity and other factors, it is difficult to avoid all potential faults. Therefore, it is need to find an appropriate forecast method to study and get the fault forecast model under a certain cost function, which can approximate the implied fault mapping mechanism of the system data, and then do the fault forecast for providing decision-making of system maintenance and real-time command. In this paper, firstly, use engine speed as study parameter, then establish a state-space model, which takes voltage (PWM signal) and the throttle opening as input, while engine speed as output. Secondly, making current analysis by using theoretical analysis to establish the system model and fit the current output. Compare it to the real value, if the difference exceeds the predetermined threshold, the alarm can be carried out. Combined with engine other parameters at this point, we can determine whether an error occurs. In this way, we realize the fault prediction of engine starting process.