Predicting Kappa Number in a Kraft Pulp Continuous Digester: A Comparison of Forecasting Methods

Abstract

This paper discusses kappa number prediction models using Single Exponential Smoothing, Multiple Linear Regression Analysis, the Time Series Method of Box-Jenkins (ARIMA) and Artificial Neural Networks. Applying a database of an industrial eucalyptus Kraft pulp continuous digester, these four different methods were evaluated according to different statistical decision criteria. After fitting the parameters of the models, validations were performed using a new dataset. Results, advantages and limitations of the four methods were compared. Some statistical forecasting indexes indicate that the ARIMA model showed more accurate estimation results, achieving a MAPE lower than 3 % and over 90% of the prediction data deviations lower than one kappa unit.

Multiscale Physics-Informed Neural Network Framework to Capture Stochastic Thin-Film Deposition

“…BC4b 2 (42) where R BC1a (t τ , T σ ), R BC2a (t τ , T σ ), R BC3a (t τ , T σ ), and R BC4a (t τ , T σ ) denote the residual terms for h̅ and its first, second, and third derivatives, respectively; and R BC1b (t τ ), R BC2b (t τ ), R BC3b (t τ ), and R BC4b (t τ ) denote the residual terms for h i and its first, second, and third derivatives, respectively. In addition to the above loss function terms, the DO decomposition process applied to the thin-film model necessitates that the SPDE outputs have specific properties, as discussed within the literature.…”

Characterization of Pulp and Paper Properties Produced from Okra (Abelmoschus esculentus) Stalks

“…Kappa numbers of the okra stalk pulps show similar characteristics as stated in previous studies (Jahan et al, 2012), and similar to other species such as wheat, cotton, and rice stalks (Tutuş and Çiçekler, 2016;Tutuş et al, 2010). A low kappa number indicates that the lignin content of the pulp is low and is easier to bleach (Correia et al, 2018;Przybysz Buzała et al, 2019;Birinci et al, 2020). Since okra stalk pulps have low kappa numbers (ranging from 25 to 33), they are easy to bleach, but considering the viscosity and DP values presented in Table 4, the strength properties of the papers produced after pulp bleaching will be low, since the chemicals used during bleaching will also damage carbohydrates.…”

A study on the effects of potassium borohydride in pulp and paper production from black locust (Robinia pseudoacacia L.) wood

“…Since KBH 4 stops the peeling and increases the yield, the cellulose content of the pulp increases. The kappa number is generally used to estimate the lignin content in the pulp and to determine its bleachability (Correia et al, 2018). Considering the increase in the cellulose content decreased the lignin content compared to the whole pulp, the kappa numbers of the KBH 4 -added pulps were found to be lower (Fig.…”