Data-driven soft sensor for continuous production monitoring: an application to paper strength

This paper presents a set of modeling procedures which are substantial for developing a data-driven soft sensor for paper strength parameters in production environment. Special focus is put on describing methods for efficient data aggregation, data cleaning and feature selection, which were employed to appropriately model the inherently complex process of papermaking and handle the challenging nature of collected data. The resulting soft sensor for tensile index deployed at a paper machine shows solid performance. Moreover, good quality of calculated real-time predictions is also confirmed by means of experiment-based validation.