基于实验数据的航空发动机稳态模型建模

Aeroengine Steady State Modeling Based on Test Data

针对基于部件级航空发动机稳态建模过程中完整、准确的航空发动机部件特性数据往往难以获取,建模时间长等现象,提出使用实验数据进行辨识建模的方法;为了建立航空发动机的稳态模型,通过对某轻型飞机实验台的飞行实验数据进行分析整理,提出使用BP神经网络对发动机重要参数进行建模,同时使用粒子群优化算法(Particle swarm optimization,PSO)对BP神经网络的权值和阈值进行优化。最后,使用改进粒子群优化算法(Improved particle swarm optimization algorithm,IPSO)对传统粒子群优化算法进行改进,仿真结果表明IPSO-BP网络建立的发动机模型精度更高,稳定性更好。

For the complete and accurate aeroengine component characteristic data in the steady state modeling process of component-based aeroengines,it was often difficult to obtain,and the modeling time was long.The method of using experimental data for identification modeling was proposed.In order to establish the steady state model of the aeroengine,by analyzing and collating the flight experimental data of a light aircraft test bench,it was proposed to use BP neural network to model the important parameters of the engine,At the same time,Particle Swarm Optimization(PSO)was used to optimize the weight and threshold of BP neural network.Finally,the improved particle swarm optimization algorithm(IPSO)was used to improve the traditional particle swarm optimization algorithm.The simulation results show that the engine model established by IPSO-BP network has higher precision and better stability.