Study on Artificial Neural Network for Predicting Gas-Liquid Two-Phase Pressure Drop in Pipeline-Riser System

The pressure drop for air-water two-phase flow in pipeline systems with S-shaped and vertical risers at various inclinations (-1 degrees, -2 degrees, -4 degrees, -5 degrees and -7 degrees from horizontal) was predicted using an artificial neural network (ANN). In the designing of the ANN model, the superficial velocity of gas and liquid as well as the inclination of the downcomer were used as input variables, while pressure drop values of two-phase flows were determined as the output. An ANN network with a hidden layer containing 14 neurons was developed based on a trial-and-error method. A sigmoid function was chosen as the transfer function for the hidden layer, while a linear function was used in the output layer. The Levenberg-Marquardt algorithm was used for the training of the model. A total of 415 experimental data points reported in the literature were collected and used for the creation of the networks. The statistical results showed that the proposed network is capable of calculating the experimental pressure drop dataset with low average absolute percent error (AAPE) of 3.35% and high determination coefficient (R-2) of 0.995.

Automated summary

An artificial neural network (ANN) was used to predict the pressure drop for air-water two-phase flow in pipeline systems with S-shaped and vertical risers at different inclinations. The ANN model was designed with input variables including the superficial velocity of gas and liquid as well as the inclination of the downcomer, and the output was the pressure drop values of two-phase flows. The developed ANN network with a hidden layer containing 14 neurons showed high accuracy in calculating the experimental pressure drop dataset, with a low average absolute percent error (AAPE) of 3.35% and a high determination coefficient (R-2) of 0.995.