Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations
2026-06-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors present PC-MambaSDE, a new method to better predict when machines will stop working, even when sensor data is irregular or missing. Their approach uses a special encoder that understands which data is missing and a physics-based model that ensures the predicted machine wear always increases over time. They also introduce a way to guide predictions toward failure in a mathematically sound way, proving the method is stable and reliable. Their tests show improved accuracy compared to existing methods, especially when data is very irregular.
Remaining Useful Life (RUL)Predictive MaintenanceIrregular Time SeriesStochastic Differential Equations (SDE)Latent Variable ModelsMaskingMonotonic DegradationGirsanov's TheoremLyapunov StabilityBoundary Value Problem
Authors
Deyu Zhuang, Peiliang Gong, Yang Shao, Liyuan Shu, Qi Zhu, Xiaoli Li, Daoqiang Zhang
Abstract
Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance. However, real-world deployment is challenging due to the irregular nature of sensor observations, characterized by asynchronous sampling, burst missingness, and temporal jitter. Compounding this issue, purely data-driven models often generate physically implausible degradation trajectories that violate the irreversible nature of damage accumulation. To address this, we propose PC-MambaSDE, a unified continuous-time framework for robust RUL prediction under irregular observations. Specifically, we design a Mask-Aware Continuous Mamba Encoder that explicitly leverages observation masks to extract context-rich control signals. Furthermore, we introduce a Physics-Guided Latent SDE with parametrically rectified hybrid drift, superimposing a global physical bias to enforce monotonic degradation even amid severe observation gaps. Additionally, we formulate RUL prediction as a boundary value problem via a Terminal Degradation Penalty, which decouples a Health Index dimension and applies a penalty loss to guide trajectories toward the failure state. Theoretically, we prove that our variational objective is mathematically equivalent to minimizing the KL divergence via Girsanov's theorem, and we guarantee the global asymptotic stability of the learned dynamics through Lyapunov analysis. To enable rigorous evaluation, we develop a Hybrid Irregularity Generation Scheme that simulates realistic industrial imperfections. Extensive experiments on public benchmarks demonstrate that PC-MambaSDE significantly outperforms state-of-the-art methods, particularly under extreme observation scarcity, validating the efficacy of embedding physical priors into continuous-time latent dynamics.