AI-Driven Predictive Maintenance: Remaining Useful Life Estimation for Turbofan Engines via Ensemble Learning, LSTM, and Uncertainty Quantification

Unplanned industrial equipment failures cause significant financial losses andsafety hazards across aviation, energy, and manufacturing sectors. Predictive Maintenance(PdM) addresses this by estimating the Remaining Useful Life (RUL) — the numberof operational cycles before a machine requires intervention — enabling proactive, costoptimal scheduling. This paper presents a complete end-to-end machine learning pipelinefor RUL prediction on the NASA C-MAPSS turbofan engine degradation dataset [17]. Wecompare four models — Linear Regression, Random Forest, Gradient Boosting, and a twolayer Long Short-Term Memory (LSTM) network implemented in pure NumPy underrigorous Group K-Fold cross-validation to eliminate engine-level data leakage. Our featureengineering pipeline transforms 21 raw sensor channels into 37 temporal features includingrolling statistics, a composite health index, and degradation rate. Random Forestachieves the best performance: RMSE = 9.95 cycles, R2 = 0.9398, MAE = 5.77,and NASA PHM asymmetric score = 1.9. We further contribute bootstrap predictionintervals achieving 90.0% empirical coverage at the 95% nominal level, and a maintenancescheduling module projecting $430,000 in cost savings on a 20-engine fleet.