As the key part of the aero engine, the controller is the core component to ensure the normal operation of the engine.With the development of aero engine, it requires higher and higher accuracy and timeliness of the control of aero engine, which promotes to increase the effectiveness of PID controller. In this work, two online and offline parameter self-tuning methods for fractional order PID are proposed to control the thrust of aero engine. Firstly, a fractional PID model is established based on the Caputo fractional calculus definition.Secondly,by introducing the lognormal distribution,an improved cuckoo optimization algorithm is provided to achieve offline parameter tuning.Then,combining with RBF network, the parameter online setting problem for fractional order PID is solved. Finally, the results show that the improved cuckoo optimization algorithm exhibits high performance on offline parameters tuning of fractional order PID. The online parameter tuning based on RBF neural network also works stably.We find that the control effect of fractional order PID is much better than the traditional PID,which greatly improves the thrust control effectiveness.