Applying artificial neural network to predict the viscosity of microalgae slurry in hydrothermal hydrolysis process
Hao Chen, Qian Fu, Qiang Liao, Xun Zhu, A.A. Shah
Abstract
Estimation of the viscosity of microalgae slurry is the premise for the design of industrial reactors in microalgal biofuel production. To accurately predict the viscosity of microalgae slurry (Chlorella pyrenoidosa), an artificial neural network (ANN) model is designed in this study. In the ANN model, the mass fraction of microalgal cell, shear rate, temperature, and retention time during the hydrothermal hydrolysis process are used as the input variables, and the viscosity of microalgae slurry is obtained as the output variable. Comparisons show that the ANN model is in excellent agreement with the experimental data. The mean square error (MSE), Mean Absolute Error (MAE), and goodness of fit (R2) are 0.725, 0.484 and 0.991, respectively. The results provide a proof-of-concept for using ANN models to estimate the viscosity of microalgae slurry. In particular, the developed ANN model can accurately predict the viscosity of microalgae slurry in a hydrothermal hydrolysis process, which cannot be accurately predicted by a standard curve fitting method.