Health Status Estimation of Aircraft Engines Based on Clustering and Bi-LSTM with Attention Mechanism

Accurate health status estimation is one of the key technologies to ensure the safe operation of aircraft engines. To improve the accuracy of estimating the health status of aircraft engines, a health status estimation model based on clustering and bidirectional long short-term memory (Bi-LSTM) network with attention mechanism is proposed. On the one hand, attention mechanism is incorporated into the Bi-LSTM network to allow the model to dynamically focus on important information at different positions in the sequence when processing it, thereby improving the model’s understanding ability of the sequence. On the other hand, fuzzy C-means (FCM) clustering algorithm is used to automatically partition the health status of multi-dimensional sensor signals in aircraft engines, to reduce the burden of manual labeling. Finally, the effectiveness and superiority of the proposed model are validated on the C-MAPSS public dataset.