针对航空发动机在起动过程中各截面气流处于亚临界状态 ,难以利用传统的气动热力学方法进行建模的问题 ,本文利用发动机地面试验数据作为学习样本 ,采用动态径向基 (RBF)神经网络的方法 ,建立了航空发动机起动过程动态模型。仿真结果表明 ,利用该方法建立的发动机模型具有动态性好 ,精度高的优点 ,开辟了发动机中小转速建模的新途径 Aeroengine in the starting process of the cross-sectional airflow in the subcritical state, it is difficult to use the traditional aerodynamic modeling method of the problem, the use of the engine ground test data as a learning sample, the use of dynamic radial basis (RBF) neural network method , Established a dynamic model of aeroengine starting process. The simulation results show that the engine model established by the method has the advantages of good dynamics and high precision, and opens up a new way of modeling the mid-small engine speed