新框架直接学习数据内在不确定性，提升航空发动机剩余寿命预测精度与可靠性。
Uncertainty-Aware Deep Learning Framework for Remaining Useful Life Prediction in Turbofan Engines with Learned Aleatoric Uncertainty
- 通过贝叶斯输出层联合预测寿命均值与方差，自动学习数据固有不确定性。
- 在关键阶段（剩余≤30周期）的预测误差降低25%-40%，显著优于传统方法。
- 提供校准良好的置信区间，适合高安全要求的智能维护决策场景。
准确的剩余使用寿命（RUL）预测结合不确定性量化，仍是航空航天预测领域的关键挑战。本文提出一种新型不确定性感知深度学习框架，首次在CMAPSS基准上通过概率建模直接学习数据固有不确定性（aleatoric uncertainty）。该框架采用分层结构，融合多尺度Inception模块提取时序特征、双向LSTM进行序列建模，并设计双层注意力机制同步关注传感器与时间维度。创新性地引入贝叶斯输出层，同时预测均值与方差，实现对数据内在不确定性的自适应学习。预处理环节结合条件感知聚类、小波去噪与智能特征选择。在NASA CMAPSS基准（FD001-FD004）上的实验表明，整体表现优异，均方根误差（RMSE）分别为16.22、19.29、16.84和19.98。尤为突出的是，在关键阶段（RUL ≤ 30周期）的RMSE达到5.14、6.89、5.27、7.16，相较传统方法提升25%-40%，树立了新基准。学习到的不确定性生成校准良好的95%置信区间，覆盖率达93.5%至95.2%，为此前在CMAPSS文献中未实现的风险感知维护调度提供了可能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。