A novel adaptive soft sensing framework for label delay in industrial data streams

In industrial data stream environments, the acquisition of real quality variables is challenging and subject to delay, posing significant obstacles to effective updates of adaptive soft sensors. To this end, this paper proposes a novel framework, Adaptive Soft Sensor for Label Delay (ASSLD). An adaptive multilevel regression model, weighting and integrating outcomes from layers at different depths, is designed to enhance online adaptability. To efficiently reuse historical labeled data, a diverse database is maintained online, from which similar samples are selected and weighted. Moreover, unlabeled samples within the delay time are utilized to help accommodate recent data. The experimental results on the sulfur recovery unit dataset and polyester dataset show the effectiveness of ASSLD in handling label delay, with accuracy improvements of more than 12 % over baselines.