Neural networks adaptive control of aircraft engine based on genetic algorithm

In this paper, a method of neural network adaptive control was proposed based on genetic algorithm (GA). At first, genetic algorithm is applied to determine initial weights of neural networks (NNs), and then NNs identifier is applied to real-time identify the model of engine. Moreover, the sensitivity information of the system is fed back to the NNs controller, which ensures the accuracy of the controller for the controlled object. For an aircraft turbojet engine, the control system is designed on the selected design point. The simulation results show that the control system not only has good quickness and less overshoot but also has strong anti-interference ability.