In order to solve the real time application demand of the fuel flow control in aircraft engine's starting process

a new nonlinear predictive control method based on particle swarm optimization(PSO) algorithm is presented.The method established a predictive model with last suares support vector machines(LS-SVM)

and then carried out the receding horizon optimization with PSO algorithm.The example validated that the new control method can reduce the rotors' rotating speed fluctuation and the steady state can be attained 5～6 seconds earlier than that without optimization.The result of the emulation shows that the method is suitable for the fuel flow control

and it can achieve the best control pattern of fuel flow when the restriction is provided accurately.