Aircraft Engine Remaining Useful Life Prediction Using Attention-Based Convolutional Neural Network - Gated Recurrent Unit

As aircraft usage time increases, the state and performance of aircraft engines gradually deteriorate. In the context of rapid development in smart industries and aviation transport, accurate assessment of aircraft engine status and prediction of Remaining Useful Life (RUL) are crucial for flight safety and maintenance cost reduction. This study focuses on the multivariate time series features of historical data from aircraft engines. It develops an RUL prediction model based on the Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) model integrated with an attention mechanism to enhance the focus on key features. Through training and testing on real engine datasets, the effectiveness and accuracy of the proposed method in RUL prediction tasks were validated. Experimental findings demonstrate that the proposed method offers relatively precise predictions of engine RUL, furnishing vital decision support and optimization strategies for airlines and maintenance teams. This research holds significant implications for enhancing flight operational safety, refining maintenance schedules, and reducing operational costs, presenting extensive prospects within the aerospace engineering domain.