A remaining useful life prediction method based on LSTM-DCGAN for aero-engines

Abstract Turbofan engine is a key component in aerospace. Its health condition determines whether an aircraft can operate reliably. However, it difficult to predict the remaining useful life (RUL) precisely because of characteristics complex operating conditions and various failure modes. To RUL more accurately make full use advantages neural networks, prediction model based on long short-term memory network (LSTM) deep convolutional generative adversarial (DCGAN) proposed called LSTM-DCGAN this paper. In LSTM-DCGAN, DCGAN used obtain knowledge training dataset, then generator after pretraining attached LSTM for further feature extraction. The effectiveness validated C-MAPSS aero-engine degradation dataset compared with other methods.