Uncertainty-Aware Deep Learning Framework for Remaining Useful Life Prediction in Turbofan Engines with Learned Aleatoric Uncertainty

TL;DR

This paper presents a novel deep learning framework that predicts remaining useful life of turbofan engines while quantifying aleatoric uncertainty, leading to more reliable and safety-critical prognostics.

Contribution

It introduces a probabilistic, uncertainty-aware deep learning model with a hierarchical architecture and Bayesian output layer, a novel approach in CMAPSS-based RUL prediction.

Findings

Achieved competitive RMSE on NASA CMAPSS benchmarks.

Significantly improved critical zone RUL predictions by 25-40%.

Produced well-calibrated confidence intervals with over 93% coverage.

Abstract

Accurate Remaining Useful Life (RUL) prediction coupled with uncertainty quantification remains a critical challenge in aerospace prognostics. This research introduces a novel uncertainty-aware deep learning framework that learns aleatoric uncertainty directly through probabilistic modeling, an approach unexplored in existing CMAPSS-based literature. Our hierarchical architecture integrates multi-scale Inception blocks for temporal pattern extraction, bidirectional Long Short-Term Memory networks for sequential modeling, and a dual-level attention mechanism operating simultaneously on sensor and temporal dimensions. The innovation lies in the Bayesian output layer that predicts both mean RUL and variance, enabling the model to learn data-inherent uncertainty. Comprehensive preprocessing employs condition-aware clustering, wavelet denoising, and intelligent feature selection. Experimental validation on NASA CMAPSS benchmarks (FD001-FD004) demonstrates competitive overall performance with RMSE values of 16.22, 19.29, 16.84, and 19.98 respectively. Remarkably, our framework achieves breakthrough critical zone performance (RUL <= 30 cycles) with RMSE of 5.14, 6.89, 5.27, and 7.16, representing 25-40 percent improvements over conventional approaches and establishing new benchmarks for safety-critical predictions. The learned uncertainty provides well-calibrated 95 percent confidence intervals with coverage ranging from 93.5 percent to 95.2 percent, enabling risk-aware maintenance scheduling previously unattainable in CMAPSS literature.