基于PCA BP的航空发动机大修周期预测方法

Method of PCA BP based Aero Engine Overhaul Makespan Prediction

航空发动机大修具有影响因素多、因素之间耦合关系复杂等特点,针对数据驱动的航空发动机大修周期预测,提出基于主成分分析和反向传播神经网络(PCA BP)的航空发动机大修周期预测方法。在分析影响航空发动机大修周期主要因素的基础上,采用PCA方法得到影响航空发动机大修周期的主成分因素,并将其作为BP神经网络的输入。基于某型航空发动机大修数据对PCA BP模型进行训练和测试,并与BP神经网络模型进行比较,结果表明PCA BP模型预测精度更高,验证了方法的有效性。

Aero engine overhaul has complicated influencing factors and complex coupling relationship between factors.Aiming at data driven aero engine overhaul makespan prediction,an aero engine overhaul makespan prediction method and model based on principal component analysis and back propagation neural network(PCA BP)is proposed.Firstly,the key factors affecting aero engine overhaul makespan are analyzed,and the dimension of the influencing factors for aero engine overhaul makespan is reduced by PCA.Then the obtained principal component is taken as the input vectors for BP neural network.Finally,a PCA BP model is trained and tested using a set of aero engine overhaul data and further compared with the BP neural network model.The results show that the PCA BP neural network model has higher prediction accuracy,and the effectiveness of the proposed method is verified.