发表机构
University of Hertfordshire（赫特福德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出TQRNN30d框架，结合双阶段QRNN特征提取器与多流时间融合分类器，在9个制造设施72台机器的测试中，其长程故障预测性能优于18个基线，验证了同构集群内的泛化能力。
AI 中文摘要
长程预测性维护需要模型在以天而非小时计的规划窗口内，区分缓慢演变的退化过程与正常运行状态的变化。本文评估显式条件分位数表示是否可为该问题提供信息丰富的分类器接口。所提出的TQRNN30d框架结合了双阶段分位数回归神经网络（QRNN）特征提取器与多流时间融合分类器。81通道机器行为的每小时“词”被映射为324维分位数状态表示，720个有序小时“词”构成长程模型所需的30天“文档”。分类器采用门控残差处理、因果循环编码及元数据条件跨模态注意力，融合分位数状态、动态协变量、通道级静态元数据与168小时隐历史流。源自持续单步预测误差发散的有界不稳定感知信号，为最长规划窗口提供辅助记忆调制。评估采用9个制造设施中72台机器的机器不相交划分，训练/验证/测试集比例为43/14/15。在30天时，TQRNN30d的F1值达79.97%、召回率80.18%、精确率81.82%、准确率82.39%、ROC-AUC为0.820；在7、14、30天固定阈值对比中，其性能领先所有18个评估基线，且在14天的F1优势最大。结果验证了其在观测到的同构9设施集群内的留用机器性能，但未确立其在未见过的站点、跨设备或跨行业的泛化能力。
英文摘要
Long-horizon predictive maintenance requires models to distinguish slowly evolving degradation from normal operating-regime variation over planning windows measured in days rather than hours. This paper evaluates whether an explicit conditional-quantile representation provides an informative classifier interface for this problem. The proposed TQRNN30d framework combines a dual-stage quantile regression neural network (QRNN) feature extractor with a multi-stream temporal fusion classifier. Each hourly word of 81-channel machine behaviour is mapped to a 324-dimensional quantile-state representation, and 720 ordered hourly words form the 30-day document supplied to the long-horizon model. The classifier fuses quantile states with dynamic covariates, channel-level static metadata, and a 168-hour latent-history stream using gated residual processing, causal recurrent encoding, and metadata-conditioned cross-modal attention. A bounded instability-aware signal derived from sustained one-word-ahead prediction-error divergence provides auxiliary memory modulation at the longest horizon. Evaluation uses a machine-disjoint 43/14/15 train/validation/test allocation across 72 machines in nine manufacturing facilities. At 30 days, TQRNN30d achieves 79.97% F1, 80.18% recall, 81.82% precision, 82.39% accuracy, and 0.820 ROC-AUC. It leads all 18 evaluated baselines at the 7-, 14-, and 30-day fixed-threshold comparisons, with the largest F1 advantage at 14 days. The results support held-out-machine performance within the observed homogeneous nine-facility fleet, but do not establish unseen-site, cross-equipment, or cross-sector generalisation.
