Using RBF neural networks and a fuzzy logic controller to stabilize wood pulp freeness

Data‐driven ALS‐SVR‐ARMA 2K modelling with AMPSO parameter optimisation for a high consistency refining system in papermaking

“…As for the data‐driven modelling of CSF, two kinds of models can be found in the existing literatures. One is the widely used NN based model [18], and the other is the recently proposed case‐based reasoning based model [19]. However, these methods usually suffer from poor generalisation, and overfitting problems.…”

Soft Sensors for Pulp Freeness and Outlet Consistency Estimation in the Alkaline Peroxide Mechanical Pulping (APMP) High-Consistency Refining Process

“…Artificial neural networks (ANN) and fuzzy logic models act as soft sensors that enable the operators to control and optimize the refining process (Bard et al 1999;Runkler et al 2003). When studying the impact of refining operations on pulp quality, multivariate analysis (MVA) methods such as principal component analysis (PCA) and partial least squares (PLS) are popular modeling techniques applied to data-driven soft sensors (Broderick et al 1996;Harrison et al 2004Harrison et al , 2007.…”