Prediction of aero engine remaining service life using a bidirectional GRU model with self attention mechanism

The performance and operational lifespan of aircraft engines are critical factors influencing flight safety and economic viability. Traditional methods for predicting aircraft engine service life often overlook microstructural changes, resulting in inaccurate predictions. To address this, a deep learning approach combining the Bidirectional Gated Recurrent Unit (BiGRU) model and self-Attention Mechanism (AM) for more accurate and reliable predictions is proposed. The method constructs a Health Index (HI) curve using a stacked denoising autoencoder and Kernel Canonical Correlation Analysis (KCCA), integrating self-AM for improved pattern recognition. The results were compared with the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) methods, showing superior efficiency and accuracy. The integrated BiGRU method demonstrates rapid fitness reduction, superior computational speed, and consistent prediction accuracy across various prediction horizons. The overall findings suggest that this method holds significant promise for enhancing the prediction accuracy of aircraft engine combustion chambers' Remaining Useful Life (RUL), with potential applications in aviation engine maintenance and control protocols. Further optimization and testing under extreme conditions are warranted for future research.