Aeroengine Remaining Life Prediction Based on Advanced Health Index Construction and Gray Similarity Multiscale Matching

In this article, we address the challenge of predicting the remaining useful life (RUL) of aeroengines, which are critical components of aircraft that operate under increasingly extreme conditions as engine performance enhances. Ensuring the safety and reliability of these engines is paramount. To this end, we introduce a novel RUL prediction methodology that leverages gray similarity multiscale matching. This approach employs the robust capabilities of long short-term memory (LSTM) networks for processing time-series data. First, an LSTM stacked autoencoder (L-SAE) is designed to extract pivotal operational features of the engine, thereby delineating its degradation trajectory. Furthermore, the gray correlation analysis is utilized to assess the similarity between these degradation trajectories, which are complemented by a multitime scale sliding window technique for enhanced similarity matching. Subsequently, kernel density estimation (KDE) is applied to gauge the uncertainty associated with the prediction outcomes. The efficacy and superiority of our proposed method are demonstrated through the validation of the experiment study. Comparative analysis reveals that our method outperforms existing techniques in key evaluation metrics, underscoring its potential applicability to large-scale datasets. This validation confirms not only the method's effectiveness but also its advantage in predicting the RUL of aeroengines with greater accuracy and reliability.