关键词: 智能服务技术, 剩余使用寿命, 自编码神经网络, 双向长短期记忆神经网络, 深度学习, 故障诊断, 涡扇发动机

Abstract: Accurately predicting the Remaining Useful Life (RUL) of turbofan engines has important significance for developing maintenance strategies and reducing maintenance costs.Aiming at the characteristics of large sample size and high dimension of condition monitoring data,a hybrid health condition prediction model integrating the advantages of Autoencoder and Bidirectional Long Short-Term Memory (BLSTM) was proposed to improve the prediction accuracy of RUL.Autoencoder was used as a feature extractor to compress monitoring data,and BLSTM was designed to capture the bidirectional long-range dependencies of features,thus a hybrid deep learning prediction model of RUL was constructed.Through testing with a baseline dataset,the results demonstrated that the proposed Autoencoder-BLSTM hybrid model had a better prediction accuracy than existing methods,such as Multi-Layer Perceptron (MLP),Support Vector Regression (SVR),Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM).The proposed model could provide strong support for the health management and maintenance strategy development of turbofan engines.

Key words: intelligent service technology, remaining useful life, autoencoder, bidirectional long short-term memory neural networks, deep learning, fault diagnosis, turbofan engine