Semi-supervised soft sensor and feature ranking based on co-regularised least squares regression applied to a polymerization batch process

In this paper a semi-supervised regression model based on co-training is applied on the soft sensor context, together with a feature ranking approach which has the purpose of removing irrelevant features. The description of both the methods of semi-supervised regression and feature ranking, as well as the theorethical foundation of the proposed feature ranking approach are also given. To evaluate the proposed methodology, a real-world polymerization industrial process was used as example. The results demonstrate that the devised feature ranking and selection improves the semi-supervised regression model.