测控技术2025，Vol.44Issue(10)：37-47,11.DOI:10.19708/j.ckjs.2025.07.237
基于级联递进建模的涡扇发动机剩余使用寿命预测方法
Remaining Useful Life Prediction Method of Turbofan Engine Based on Cascade Progressive Modeling
摘要
Abstract
In order to improve the accuracy of the remaining useful life(RUL)prediction of turbofan engine,a hybrid prediction method based on cascade progressive modeling is proposed.Firstly,the important feature screening method is used to screen the key features to reduce the influence of redundant features.Then,a hy-brid prediction model based on cascade progression is constructed.The bidirectional long short-term memory network(BiLSTM)is used to capture the temporal features of the data,and the extracted features are input into the random forest(RF)model for modeling,and finally the prediction results are obtained.At the same time,in order to further improve the prediction accuracy,the particle swarm optimization(PSO)algorithm is used to op-timize the hyperparameters of the model.The experimental results show that the proposed method effectively combines the advantages of deep learning in extracting temporal features with the generalization ability and ro-bustness of machine learning regression model.The mean absolute error(MAE)and root mean squared error(RMSE)are reduced by 45.98％and 44.86％respectively,and the goodness of fit is also increased by 29.03％on average,which provides a scientific and feasible solution for the RUL prediction of turbofan engine.关键词
剩余使用寿命预测/级联递进建模/重要特征筛选/复杂时序特征Key words
RUL prediction/cascade progressive modeling/important feature screening/complex temporal features分类
航空航天引用本文复制引用
王艳慧,范瀚博..基于级联递进建模的涡扇发动机剩余使用寿命预测方法[J].测控技术,2025,44(10):37-47,11.基金项目
云南省重大科技专项计划(202302AD080001) （202302AD080001）
