针对设备寿命预测中突发异常信号易被忽略的问题，提出可感知尖峰的精准预测框架。
SARNet: A Spike-Aware consecutive validation Framework for Accurate Remaining Useful Life Prediction
- 引入尖峰感知机制，结合自适应连续阈值识别真实故障信号
- 在多个基准数据集上实现RMSE 0.0365、MAE 0.0204的低误差表现
- 模型轻量且可解释，适合工程部署与故障机理分析
准确预测剩余使用寿命（RUL）对提升系统可靠性、降低维护风险至关重要。然而，许多先进模型在故障初期表现脆弱且缺乏可解释性：短时高能尖峰常被平滑或误读，固定阈值敏感度不足，物理机理解释匮乏。为此，我们提出SARNet（尖峰感知连续验证框架），基于现代时间卷积网络（ModernTCN），加入尖峰感知检测，提供物理启发式可解释性。ModernTCN预测退化敏感指标；自适应连续阈值验证真实尖峰并抑制噪声。故障高危段进行针对性特征工程（频谱斜率、统计导数、能量比），最终由堆叠的随机森林-梯度提升机回归器输出RUL。在事件触发协议下，多个基准数据集上的实验表明，SARNet持续优于近期基线（RMSE 0.0365，MAE 0.0204），同时保持轻量、鲁棒且易于部署。
原文摘要 · Abstract (English)
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.
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。