Remaining Useful Life Prediction for Aircraft Maintenance Using Machine Learning

ABSTRACT Ensuring regular equipment maintenance is critical for any business that relies on machinery. Predictive maintenance (PdM) is a strategy for scheduling maintenance tasks, with a primary focus on predicting the remaining useful life (RUL) of equipment in advance. This approach helps optimize maintenance schedules, reduce downtime, and detect unexpected faults. Predictions are based on analyzing data collected from the equipment, with machine learning (ML) facilitating these forecasts by training models on historical input data and corresponding outputs. The trained model can then estimate the RUL of the equipment before it reaches the end of its operational capacity. Various ML techniques have been employed for the accurate estimation of the RUL. In this paper, we aim to identify the most effective ML regression methods for PdM and RUL prediction for an auxiliary power unit (APU), focusing on performance indicators such as the root mean squared error (RMSE), the mean absolute error (MAE), and the correlation coefficient ( R ). The process begins with a dataset, followed by feature selection methods such as random forests and normalization during the preprocessing stage. Then, the ML models are trained and evaluated. To assess the effectiveness of the proposed approach, data from the NASA Ames Research Center, along with on‐wing sensor data from the Shenyang Maintenance Base of China Southern Airlines (SYMOB), are used. Six ML algorithms and a hybrid model are employed: Support Vector Machines (SVM), long short‐term memory (LSTM), gated recurrent unit (GRU), decision tree (DT), K‐nearest neighbors (KNNs), gradient boosting trees (GBTs), and a hybrid model (GBT + LSTM). The results for the regression techniques, based on the RMSE and R, are as follows: SVM (37.62, 0.84), LSTM (20.22, 0.91), GRU (31.29, 0.87), DT (17.89, 0.94), KNN (10.98, 0.98), GBT (22.62, 0.97), and (GBT + LSTM) (24.32, 0.96). The KNN method is the most effective approach for this study, as it demonstrates the lowest RMSE and the highest correlation coefficient ( R ) compared to other methods. Therefore, we highly recommend utilizing the KNN technique for PdM analysis of APUs.