Summary
Monitoring industrial processes is important for both safety and saving money, but current methods rely on many specific models that need a lot of labeled data and can struggle when conditions change. The authors designed a new approach called IPM-FM that first learns general patterns from unlabeled data, then fine-tunes itself with a small amount of labeled examples, and finally carefully estimates how confident it is in its predictions. This method uses special techniques for selecting important features and modeling time series, which helps it perform better at predicting measurements in a complex industrial setting. Tests on real industrial data showed that IPM-FM made more accurate and reliable predictions than previous methods, suggesting this approach can be useful for industry.
Industrial process monitoringFoundation modelSelf-supervised learningFeature selectionTime series forecastingUncertainty quantificationInformer modelRecursive lag featuresMonte Carlo dropoutSoft sensing
Authors
Liang Cao, Weide Liu, Yan Qin, Jun Cheng, Weisi Lin, Bhushan Gopaluni
Abstract
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.