Artificial Neural Network Model with Parameter Tuning Assisted by Differential Evolution Technique: Study of Pressure Drop of Slurry Flow in Pipeline

摘要

This paper describes a robust hybrid artificial neural network (ANN) methodology, which cannoffer superior performance for important process engineering problems. The method incorporatesnhybrid artificial neural network and differential evolution technique (ANN-DE) for efficient tuningnof ANN meta parameters. The algorithm has been applied for the prediction of pressure drop ofnsolid liquid slurry flow. A comparison with selected correlations in the literature showed thatnthe developed ANN correlation noticeably improved the prediction of pressure drops over a widenrange of operating conditions, physical properties, and pipe diameters.