Holdup prediction in inverse fluidization using non-Newtonian pseudoplastic liquids: Empirical correlation and ANN modeling

• Applicability of ANN has been examined.
• Bed height increases with the increase of liquid velocity.
• Bed height decreases increases of pseudoplasticity of the liquid.
• Empirical correlation for bed expansion is developed as a function of physical and dynamic variables of the system.

The bed expansion characteristics in inverse fluidization using non-Newtonian liquids are reported. Experiments have been carried out using single and binary systems of four different polymeric solids and four different non-Newtonian pseudoplastic liquids in two different columns. Empirical correlation has been developed to determine the bed expansion characteristics as a function of physical and dynamic variables of the system. A multilayer perceptron trained with backpropagation and Levenberg–Marquardt algorithm have been used for the Artificial Neural Network (ANN) analysis. Four different standard transfer functions in a single hidden layer are used. The ANN model with Levenberg–Marquardt algorithm with transfer function 2 having 12 processing elements in hidden layer gives good predictability of the bed height. Statistical analysis indicates that both the empirical correlation and the ANN prediction give acceptable results.

Figure optionsDownload as PowerPoint slide