Sensitivity analysis of artificial neural networks for just-suspension speed prediction in solid-liquid mixing systems: Performance comparison of MLPNN and RBFNN. (January 2019)

• Record Type: Journal Article
• Authors: Ibrahim, Shaliza; Choong, Choe Earn; El-Shafie, Ahmed
• Is Part Of: Advanced engineering informatics. Volume 39(2019)
• Page Start: 278
• Page End: 291
• Publication Date: 2019-01
• Subjects: Artificial neural network -- Just-suspension speed -- Sensitivity analysis -- Radial basis function -- Multilayer perceptron; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2019.02.004
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: Investigate the potential of different AI models to predict the just-suspension speed in solid-liquid mixing systems. Two different AI models have been developed: the RBFNN model and MLPNN. Comprehensive sensitivity analysis was carried out to evaluate the models and optimize the input pattern. RBFNN achieved better accuracy with the least number of input variables compared to MLPNN. The proposed ANN model is useful for predicting the just-suspension speed in solid-liquid mixing systems. Abstract: Just-suspension speed (Njs) is an important parameter for stirred tank design using a solid-liquid mixing system in the chemical process industry. However, current correlations for Njs suffer from uncertainty from limited experimental databases and limitations due to many parameters that play an important role in Njs determination. A comprehensive computation of the radial basis function neural network (RBFNN) was developed based on solid-liquid mixing experiments, which contain 935 datasets for the prediction of Njs. The Njs values were obtained experimentally using Zwietering correlation with different solid loading percentages, solid particle density, solid particle diameter, mixing solvent density, number of impeller blades, impeller diameter, impeller blade hub angle, impeller blade tip angle, the width of the impeller blade and the ratio of the clearance between the impeller and the bottom of the tank with the tank diameter. The RBFNN proved to have a much better ability to accurately predict the desired Njs compared to MLPNN even after decreasing the number of input variables from 11 to 8. Thus, the computational RBFNN model results will be useful for extending the application of a solid-liquid mixing system for estimating the just-suspension speed for stirred tank design.