163 Modeling of Organosolv Pulping Process Using Wavelet Neural Networks

Optimization of the pulping process without laborious modeling is crucial for efficient and economical designs purposes. In this study, wavelet neural networks (WNNs) were utilized in investigating the influence of the pulping variables (viz cooking temperature and time, ethanol and NaOH concentration) on the properties of the resulting pulp (pulp yield and kappa number) and paper sheets (tensile index and tear index) during the organosolv pulping of the oil palm fronds. The experimental results and the statistical estimators indicated that the WNNs fitted the underlying relationship between the dependent and independent variables well, where the prediction error less than 0.0965 (in terms of mean squared error) was obtained.