Aircraft Bleed Air System Fault Prediction based on Encoder-Decoder with Attention Mechanism

The engine bleed air system (BAS) is one of the important systems for civil aircraft, and fault prediction BAS necessary to improve aircraft safety operator's profit. A dual-stage two-phase attention-based encoder-decoder (DSTP-ED) model proposed normal state estimation. Unlike traditional ED networks, DSTP-ED combines spatial temporal attention better capture spatiotemporal relationships achieve higher accuracy. Five data-driven algorithms, autoregressive integrated moving average (ARIMA), support vector regression (SVR), long short-term memory (LSTM), ED, DSTP-ED, are applied build models BAS. comparison experiments show that outperforms other four models. An exponentially weighted (EWMA) control chart used as evaluation criterion failure warning. empirical study based on Quick Access Recorder (QAR) data from Airbus A320 series demonstrates method can effectively predict failures.