The paper introduces a quantile‑led feature‑extraction framework for predictive maintenance that separates representation learning from downstream modeling. Using a dual‑stage MLP‑QRNN hierarchy, it learns a ten‑quantile distribution per sensor and refines a mid‑tail quantile set into compact, channel‑resolved features. Experiments on 72 machines across nine facilities show that increasing the retained mid‑tail quantiles improves short‑term F1 scores, and that horizon‑conditioned extractors outperform a fixed short‑horizon extractor, demonstrating that feature extraction should be horizon‑dependent rather than fixed preprocessing.
By David J Poland, Daniele Ravi, Na Helian
arXiv:2507. 14194v3 Announce Type: replace-cross Abstract: This paper presents an integrative prognostic framework that combines Spatiotemporal Permutation Entropy (STPE), Boosted Enhanced Quantile Regression Neural Networks (B-EQRNNs), Gated Temporal Attention, a Spiking Neural Network (SNN) refinement stage, and a Temporal Fusion Transformer (TFT) classifier.
By David J Poland
arXiv:2607. 12730v1 Announce Type: cross Abstract: Smart-building load forecasters are often trained offline on dense, multivariate, high-frequency data, but deployment may provide only hourly, feature-limited inputs.
By Sarah Al-Shareeda, Gulcihan Ozdemir, Heung Seok Jeon
arXiv:2607. 16493v1 Announce Type: new Abstract: Multi-task deep learning models that jointly perform fault classification and remaining useful life (RUL) regression are increasingly used in predictive maintenance, yet reported performance can be strongly affected by how sliding-window sequences are split into training and test sets.
By Md Mahamudur Rahaman Shamim, Md. Nuruzzaman, Zannatul Ferdus, Md Rajib Ahmed, Abieer Nwshad Anward, Mohammad Tooneer, Johir Uddin Khan, Khalid Hossen
The paper presents a predictive maintenance framework for semiconductor manufacturing that combines deep learning sequence models with simultaneous quantile regression to provide uncertainty‑aware remaining useful life (RUL) estimates. It evaluates several architectures—including state‑space models—on ion‑milling data from the 2018 PHM Data Challenge, showing that the Diagonal State Space (S4D) model delivers the most accurate RUL predictions across quantiles. Compared to preventive maintenance baselines, the S4D approach significantly reduces business costs by avoiding unnecessarily early interventions.
By Davide Frizzo, Francesco Borsatti, Gian Antonio Susto
arXiv:2606. 24173v1 Announce Type: cross Abstract: On-device fault detection enables real-time diagnostics without cloud dependency, but deploying machine learning models on resource-constrained hardware demands careful tradeoffs between accuracy, latency, and model size.
By Disha Patel
arXiv:2607. 02632v1 Announce Type: cross Abstract: Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring.
By Shah Nawaz Haider, Steve Austin, Arnab Barua, Sarowar Morshed Shawon, Hadaate Ullah
arXiv:2605. 30122v2 Announce Type: replace-cross Abstract: Deep-learning precipitation nowcasting models are often optimized using pointwise losses such as mean squared error or mean absolute error, which can lead to overly smooth forecasts and poor representation of heavy rainfall.
By Gijs van Nieuwkoop, Siamak Mehrkanoon
The study evaluates six deep learning architectures for predictive maintenance in Industry 4.0, focusing on Recurrent Neural Networks (RNNs) and Transformers. It finds that Transformers perform well on stable, slow-moving data but overreact to noisy, chaotic data, whereas a hybrid model combining an LSTM layer with a Transformer layer better filters noise and delivers more consistent predictions. The hybrid approach improves accuracy and reliability across varying levels of data volatility.
By Zhengyang (Cissy), Gu, Joseph E. Hernandez, Thomas Cook, John Burtenshaw, Sean Scott, Chris Couch
arXiv:2511. 09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics.
By Fulong Yao, Wanqing Zhao, Chao Zheng, Xiaofei Han
The paper introduces FreqCondNorm, a Transformer-based architecture that adds a frequency-conditioned normalization layer to unify heterogeneous time-series data for predictive maintenance. The model is pretrained on five public datasets using masked auto‑encoding and contrastive learning, achieving 99.2% accuracy on CWRU and 82.1% zero‑shot accuracy on MFPT, showing strong transfer across sampling frequencies. However, it does not improve remaining useful life prediction, indicating a mismatch between pretraining and RUL objectives that requires further study.
By Zaynab Raounak, Camille LHermine, Zhiguo Zeng
arXiv:2602. 15327v2 Announce Type: replace-cross Abstract: Machine learning model performance improvements tend to arise from competition and application.
By Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade