基于改进BP网络的航空发动机起动过程辨识

利用某型发动机地面试验数据作为学习样本，采用改进BP神经网络的方法，建立了航空发动机起动过程动态模型。利用所建立的模型对起动性能进行了估算，估算结果与试验数据基本相符。结果表明，将改进BP神经网络用于起动模型的辨识是可行的，该模型具有精度高，推广性好的优点。对于用BP神经网络对发动机进行起动性能计算具有一定的理论指导意义和应用价值。

An Identification Model of Aeroengine Starting Based on Improved BP Neural Network

A dynamic identification model based on improved BP neural network is presented in this paper. It makes use of ground test data as learning samples. The start performance of aeroengine is estimated. Application results in aeroengine compressor show that this presented method possesses much better precision, which proves that the method is feasible and effective. This method is contributive and instructional for starting performance calculation for areoengine via improved BP neural network.