🤖 AI Summary
This study addresses the challenges of inaccurate remaining useful life (RUL) prediction for aircraft engines under dynamic combat missions, which leads to excessive maintenance costs and reduced operational readiness. To overcome this, we propose a deep learning–based predictive maintenance model that constructs multivariate sensor time-series inputs via a sliding window approach to automatically extract degradation features. The model is evaluated on the NASA C-MAPSS FD001 and FD004 datasets, demonstrating strong generalization under complex operating conditions: it achieves an R² of 0.8901, RMSE of 13.28, and a NASA score of 320.34 on FD001; an RMSE of 15.71 on FD004; and an AUC of 0.9973 for early warning within a critical 30-cycle threshold. These results significantly outperform baseline methods such as Random Forest and CNN-LSTM.
📝 Abstract
To improve the operational readiness of combat aircraft engines and reduce unplanned maintenance costs, accurately estimating the remaining useful life (RUL) is critical. Traditional maintenance often proves insufficient under dynamic mission profiles. In this study, a deep learning-based predictive maintenance model capable of autonomously extracting features from multivariate sensor data was developed. Using the NASA C-MAPSS FD001 and FD004 datasets, data were converted into sequential blocks via 50- and 30-step sliding windows, respectively. The model's architectural superiority in autonomously extracting temporal degradation features was validated against RF, CNN-LSTM, and BiLSTM baselines. On FD001, it achieved an R-squared (R2) of 0.8901, a 13.28 RMSE, and a 320.34 NASA risk score, demonstrating generalizability on the multi-regime FD004 dataset with a 15.71 RMSE. The proposed maintenance protocol achieved a 0.9973 AUC at the critical 30-cycle threshold, ensuring high reliability. Additionally, a decision-support simulator has been developed to validate this protocol under aggressive combat flight profiles.