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

2025-10-26

AI Summary

To address spike signal misclassification, lack of physical interpretability, and insufficient model robustness in Remaining Useful Life (RUL) prediction, this paper proposes SARNet: a unified framework integrating a spike-aware temporal convolutional network (ModernTCN) with an adaptive continuous validation mechanism. It incorporates physics-informed feature engineering—including spectral slope, energy ratio, and adaptive threshold-based spike detection—and employs an RF-LGBM stacked regressor for end-to-end RUL estimation. SARNet significantly enhances sensitivity to early fault onset and improves prediction robustness while preserving decision interpretability. Evaluated on multiple benchmark datasets under event-triggered communication protocols, it achieves an RMSE of 0.0365 and MAE of 0.0204, outperforming state-of-the-art methods. The framework is computationally lightweight and highly deployable in resource-constrained industrial settings.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: State Estimation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Predicting remaining useful life with spike-aware fault detection
• Addressing model fragility during fault onset transitions
• Providing physics-informed interpretability for degradation indicators

Innovation

• Spike-aware detection for physics-informed interpretability
• Adaptive consecutive threshold validates spikes and suppresses noise
• Stacked RF-LGBM regressor produces final remaining useful life