Skip to content
Open access

Risk-Aware Predictive Maintenance for Aero-Engines via CVaR-Guided Reinforcement Learning and LLM-Based Risk Abstraction

Oct 2026 · Italian National Conference on Sensors · Vol 26 · 0 citations · 51 references
Medicine

TL;DR

The Risk-Aware Predictive Maintenance framework, consisting of four integrated components, achieves a 96.0% optimal stopping rate with no late interventions or failure events compared with 90.2% for the strongest independent maintenance baseline and demonstrates that the decision benefit of RAPM extends across independently trained prognostic models.

Abstract

A fundamental limitation of current predictive maintenance is the inability to transform prognostic uncertainty into actionable decisions, which often leads to either wasteful early interventions or catastrophic failures in aero-engines. To address this, we propose the Risk-Aware Predictive Maintenance (RAPM) framework consisting of four integrated components: a probabilistic stacked sparse autoencoder that extracts degradation features while providing distributional remaining useful life (RUL) predictions; a Monte Carlo Dropout module with Conditional Value at Risk (CVaR) that summarizes lower-tail predictive risk and produces a conservative RUL estimate for decision making; a locally deployed large language model (Qwen2.5-3B) that abstracts numerical uncertainty into discrete semantic risk levels, enabling interpretable reward shaping; and a Proximal Policy Optimization agent trained with curriculum learning to handle long-horizon sparse-reward maintenance optimization. On the NASA C-MAPSS FD001 benchmark, RAPM achieves a 96.0% optimal stopping rate with no late interventions or failure events compared with 90.2% for the strongest independent maintenance baseline. Under controlled substitution with LSTM-MCD, Transformer-MCD, CNN-MCD, and Deep Ensemble prognostic backbones, the same CVaR-LLM-PPO decision architecture maintains optimal stopping rates of 92.4–95.2% with no late interventions or failure events. Within the matched Rule-PPO ablation, CVaR increases the mean optimal stopping rate from 92.0% to 95.0% under unperturbed conditions, which is a gain of 3.0 percentage points. Under Gaussian sensor noise (σ=0.05), the gain reaches 9.0 percentage points, from 73.0% to 82.0%. These results demonstrate that the decision benefit of RAPM extends across independently trained prognostic models.

Read PDF

Similar papers

Conference Open access Sep 2026

AI-Based Predictive Maintenance Model for Industrial Systems

This paper proposes an end-to-end explainable predictive maintenance framework consisting of a contextual probabilistic prognosticator based on convolutional and self-attention networks and a SHAP-based attribution and a risk-sensitive decision layer that is formulated as either a mixed-integer linear programming or di...

K. Selvi · 0 citations
Open access Oct 2026

Remaining useful life prediction with uncertainty quantification for risk-aware maintenance decision-making

Remaining useful life (RUL) prediction is a key task in predictive maintenance; however, most existing methods emphasize point estimation accuracy, limiting their ability to characterize predictive uncertainty and support maintenance decision-making. To address this issue, this paper proposes RQDNet, an integrated fram...

Yu Wang, Wei Zhang, Zhen Li et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling

This work formalizes failure modes, derives lagged-risk decompositions that expose the resulting temporal bias, and recasts risk prediction as an in-context sequence modeling problem, and yields more reliable difficulty estimates and consistent performance gains across robust Meta-RL, DR, and prompt curriculum RL post-...

Jia-Rong Wen, Qing-Chao Tao, Kai-Yu Zhang et al. · 1 citation

Sequential Estimation of Remaining Useful Life Through VAE-Based Deep Reinforcement Learning With Reward Shaping

A novel framework that integrates Variational Autoencoders (VAE) as surrogate environments with actor-critic Deep Reinforcement Learning (DRL) to provide a modular and efficient sequential RUL estimation method for challenging industrial scenarios is introduced.

Hima Soni, Vibha Patel, Arnav Modanwal et al. · 0 citations
Sep 2026

Evidence-Bounded Edge Reinforcement Learning for Adaptive Fuel Optimization

An evidence-bounded and fully reproducible evaluation of a continuous-action Proximal Policy Optimization (PPO) controller for adaptive fuel management, together with a heterogeneity-aware federated extension is developed, yielding a defensible benchmark and a concrete evidence protocol for subsequent automotive valida...

T. Manjunath · 1 citation
Open access Oct 2026

Stochastic Operator Residual Learning with Conformal Calibration for Risk-Aware Wind Turbine Maintenance

Wind turbine maintenance decisions are frequently made under uncertainty, yet conventional degrada‐ tion models often provide deterministic predictions that ignore the tail risks associated with unexpected component failure. We propose a stochastic operator residual learning framework with conformal calibration for ris...

Pankaj Sharma · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.