发表机构
University of British Columbia; Jiangxi University of Finance and Economics; Chongqing University; Institute for Infocomm Research; Nanyang Technological University（不列颠哥伦比亚大学; 江西财经大学; 重庆大学; 信息通信研究院; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
IPM-FM是一种工业过程监测基础模型，通过自监督预训练和共识特征选择适应多任务，在柴油闪点软测量中RMSE达2.99，优于现有基线。
AI 中文摘要
工业过程监测对于现代过程工厂的安全性和经济性能至关重要。当前实践仍采用“一任务一模型”范式，该范式标签效率低下，且在运行漂移下容易退化。基础模型已重塑了语言、视觉和通用时间序列预测领域，但尚未被应用于工业过程监测。这一应用场景带来了领域特定的挑战，包括安全关键决策以及过程变量与实验室测量之间的非对称采样。我们提出了工业过程监测基础模型（IPM-FM）。它首先通过自监督预训练从未标记的工业过程数据中学习通用表示，然后利用少量任务标记数据适应特定监测任务，最后通过不确定性感知预测头产生校准的预测。IPM-FM集成了自监督的Informer骨干网络与多准则共识特征选择器、递归滞后特征回归头以及校准的蒙特卡洛丢弃不确定性模块。在用于柴油闪点软测量的七年加氢处理装置数据集上，IPM-FM实现了2.99的均方根误差（RMSE）、0.50的$R^2$以及其95%预测区间的97%覆盖率，在RMSE上分别比最强的经典基线和从头训练的序列基线提升了8.3%和14.6%，支持了统一预训练-适应框架在工业过程监测中的可行性。
英文摘要
Industrial process monitoring is fundamental to the safety and economic performance of modern process plants. Current practice remains a one-task-one-model paradigm that is label-inefficient and prone to degradation under operating drift. Foundation models have reshaped language, vision, and generic time-series forecasting, but it has not been adapted to industrial process monitoring. This setting poses domain-specific challenges, including safety-critical decisions and asymmetric sampling between process variables and laboratory measurements. We propose the industrial process monitoring foundation model (IPM-FM). It first learns general-purpose representations from unlabeled industrial process data through self-supervised pretraining, then adapts to specific monitoring tasks using a small amount of task-labeled data, and finally produces calibrated predictions through an uncertainty-aware prediction head. IPM-FM integrates a self-supervised Informer backbone with a multi-criteria consensus feature selector, a recursive lag-feature regression head, and a calibrated Monte Carlo dropout uncertainty module. On a seven-year hydrotreater dataset for diesel flash-point soft sensing, IPM-FM attains an RMSE of 2.99, $R^2$ of 0.50, and 97\% coverage of its 95\% predictive interval, outperforming the strongest classical and from-scratch sequence baselines by 8.3\% and 14.6\% in RMSE respectively, supporting the viability of a unified pretraining--adaptation framework for industrial process monitoring.
