Accurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional–convolutional neural network–long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics.

In prognostics, it is essential to accurately predict the Remaining Useful Life (RUL) of complex systems like turbofan engines. Most studies adopt data-driven methods and rely on piecewise linear (PwL) labeling, where a fixed initial RUL is assigned to all engines. To better reflect real-world degradation, this assumption is refined using change point detection to assign engine-specific initial RUL values, offering a more realistic problem formulation. In line with PwL-based labeling approaches, where mechanical systems shift from a normal to a degradation phase at a specific change point, distinct RUL prediction models are developed for each health stage. A classification model is proposed using a novel training methodology to identify the current health stage of an engine. This method segments the dataset into pre- and post-change intervals and applies data augmentation both to simulate the truncated nature of the test data—where engines are monitored up to unknown failure points—and to construct a balanced training set that fairly represents both healthy and degraded conditions, thereby improving the robustness and generalization of the classification model. Two deep learning models are used for RUL prediction in engines: an LSTM model for degraded engines, which captures long-term dependencies in deterioration data, and a feature-level fusion model for healthy engines with sparse sensor data, which enhances prediction accuracy by integrating CNN and LSTM, addressing unique problems in different engine health stages. Model interpretability is enhanced through post-hoc SHAP analysis, revealing stage-specific sensor importance and explaining predictions across different health stages.