Prediction of Remaining Useful Life of Aero-engines Based on CNN-LSTM-Attention

• DOI: 10.1007/s44196-024-00639-w
• Publication Date: 2024-09-03T13:02:05Z
• Authors: Sizhe Deng; Jian Zhou
• Keywords: Aero engine

Abstract Accurately predicting the remaining useful life (RUL) of aircraft engines is crucial for maintaining financial stability and aviation safety. To further enhance prediction accuracy engine RUL, a deep learning-based RUL method proposed. This possesses potential to strengthen recognition data features, thereby improving model. First, input features are normalized CMAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset utilized calculate engines. After extracting attributes from using convolutional neural network (CNN), extracted into long short-term memory (LSTM) model, with addition attention mechanisms predict Finally, proposed model evaluated compared through ablation studies comparative experiments. The results indicate that CNN-LSTM-Attention exhibits superior performance datasets FD001, FD002, FD003, FD004, RMSEs 15.977, 14.452, 13.907, 16.637, respectively. Compared CNN, LSTM, CNN-LSTM models, demonstrates better across datasets. In comparison other this achieves highest on dataset, showcasing strong reliability accuracy.