The paper introduces TQRNN30d, a long‑horizon predictive maintenance model that uses a dual‑stage quantile regression neural network to transform hourly machine data into a 324‑dimensional quantile‑state representation, which is then classified with a multi‑stream temporal fusion architecture. Trained on data from 72 machines across nine facilities, the model achieves high performance at 30‑day horizons (F1 ≈ 80%, recall ≈ 80%, precision ≈ 82%, accuracy ≈ 82%, ROC‑AUC ≈ 0.82) and outperforms 18 baseline methods at 7‑, 14‑, and 30‑day thresholds. The study demonstrates that explicit conditional‑quantile representations can effectively distinguish gradual degradation from normal operation over multi‑day planning windows, though generalisation to unseen sites or equipment remains untested.
By David J Poland, Daniele Ravi, Na Helian
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: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. 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
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
By Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
arXiv:2609.13640v1 Announce Type: new
Abstract: Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the fin...
By Bahaeddine Abdessalem, Shifeng Xie, Zehao Xiao, Youssef Attia El Hili, Ambroise Odonnat, Jianfeng Zhang, Lujia Pan, Keli Zhang, Malik Tiomoko
arXiv:2601. 21293v3 Announce Type: replace-cross Abstract: Industrial Internet of Things (IIoT) systems increasingly rely on distributed vibration sensing to support predictive maintenance of rotating machinery.
By Changyu Li, Huabei Nie, Xiaoya Ni, Lu Wang, Lijuan Shen, Kaishun Wu, Fei Luo
arXiv:2607. 03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from heterogeneous and non-stationary time-series data.
By Quang Hung Pham, Ryad Zemouri, Martin Gagnon, Luc Vouligny
arXiv:2606. 11990v1 Announce Type: cross Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or large labeled datasets to train task-specific sequence models.
By Amir El-Ghoussani, Michele De Vita, Ronald Naumann, Valiseios Belagiannis
arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.
By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman
FedCMAPSS is a new benchmark for federated learning applied to remaining useful life (RUL) estimation, built on the NASA C‑MAPSS dataset. It defines five standardized tasks that mimic real‑world industrial scenarios, from ideal IID conditions to highly heterogeneous data distributions. The paper evaluates state‑of‑the‑art federated optimization algorithms across multiple neural architectures, providing reproducible baselines and publicly available code and data splits.
By Amelia Sorrenti, Matteo Pennisi, Concetto Spampinato, Simone Palazzo
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