SARNet: A Spike-Aware consecutive validation Framework for Accurate Remaining Useful Life Prediction

TL;DR

SARNet is a novel framework that improves remaining useful life prediction by incorporating spike-aware detection, physics-informed interpretability, and targeted feature engineering, outperforming recent baselines.

Contribution

Introduces SARNet, combining spike-aware detection with a ModernTCN and ensemble regressors for accurate, interpretable RUL prediction.

Findings

SARNet reduces prediction error on benchmark datasets.

It maintains robustness and ease of deployment.

Outperforms recent baseline models in accuracy.

Abstract

Accurate prediction of remaining useful life (RUL) is essential to enhance system reliability and reduce maintenance risk. Yet many strong contemporary models are fragile around fault onset and opaque to engineers: short, high-energy spikes are smoothed away or misread, fixed thresholds blunt sensitivity, and physics-based explanations are scarce. To remedy this, we introduce SARNet (Spike-Aware Consecutive Validation Framework), which builds on a Modern Temporal Convolutional Network (ModernTCN) and adds spike-aware detection to provide physics-informed interpretability. ModernTCN forecasts degradation-sensitive indicators; an adaptive consecutive threshold validates true spikes while suppressing noise. Failure-prone segments then receive targeted feature engineering (spectral slopes, statistical derivatives, energy ratios), and the final RUL is produced by a stacked RF--LGBM regressor. Across benchmark-ported datasets under an event-triggered protocol, SARNet consistently lowers error compared to recent baselines (RMSE 0.0365, MAE 0.0204) while remaining lightweight, robust, and easy to deploy.