Pressure drop is the most important factor affecting the dust collection efficiency in venturi scrubbers. The model described by Viswanathan et a]. IS. Viswanathan, A.W. Gnyp, C.C. St. Pierre, Annular flow pressure drop model for Pease-Anthony type venturi scrubbers, AIChE J. 31 (1985) 1947-1958] predicts pressure drop according to an annular two-phase flow model, but there is a parameter lacking in order to implement this model. In this work, some correlations are suggested for use in Viswanathan's model. The results are compared with experimental data extracted from two different venturi scrubbers with different conditions. In these ranges of conditions, good agreement between the results of this modified model and experimental data shows the ability of the model to predict pressure drop. In the next step, artificial neural network was used to predict pressure drop in venturi scrubbers and acceptable results were obtained. For increasing the efficiency of neural networks. genetic algorithm was used to optimize parameters of the neural network such as the number of neurons in the hidden layer, the momentum rate and the learning rate. Finally, the model of neural network optimized by genetic algorithm was selected as the best model due to its agreement with experimental data and greater flexibility compared to mathematical models. (C) 2008 Elsevier B.V. All rights reserved.