一种航空发动机性能衰退预测的优化算法

Research on an Algorithm for Prediction of Aeroengine Performance Deterioration

针对航空发动机性能衰退预测问题,采用基于过程神经网络的优化算法来对发动机的燃气温度裕度(EGTM)进行预测。为克服过程神经网络学习速度慢的缺点,提出一种基于Tent映射的混沌粒子群优化算法对网络进行训练,建立预测模型。采用某航空公司的EGTM监测数据进行验证,分析结果表明,基于Tent映射的混沌粒子群优化算法具有较高的收敛速度和预测精度,可为航空发动机视情维修决策提供支持。

Process neural networks were adopted to predict the engine gas temperature margin,which could reflect the performance deterioration of the civil aviation aircraft engine.In order to overcome the problem that the learning speed of existing learning algorithms for process neural network was slow,a chaotic particle swarm optimization based on Tent map was developed,which could improve the convergence speed and prediction accuracy.Simulation results demonstrate the validity and feasibility of the proposed algorithm.