A predictive model for the identification of the volume fraction in two-phase flow

This work presents the use of artificial intelligence in multiphase flows, implementing a multilayer perceptron artificial neural network with back-propagation, and using the sigmoid tangent activation function, to generate a predictive model capable of obtaining the holdup of a two-phase flow composed of water and mineral oil in a horizontal pipe of 12 m. The artificial neural network is developed using an input layer, formed by the pressure differential in the line and the superficial velocities of the working fluids, also, it has two hidden layers and an outlet layer, which is made up of the volumetric fractions of the fluids. The best-performing predictive model shows a mean percentage absolute error of 3.07 % and a coefficient of determination R2 of 0.985 using 15 neurons in the two hidden layers of the neural network. The 56 experimental data used in the study were obtained in the laboratory LEMI EESC-USP (Brazil).

• Fecha de publicación: 2021
• Institución: Universidad Pedagógica y Tecnológica de Colombia
• Repositorio: RiUPTC: Repositorio Institucional UPTC
• Idioma: spa
• OAI Identifier: oai:repositorio.uptc.edu.co:001/15330
• Acceso en línea: https://revistas.uptc.edu.co/index.php/ciencia_en_desarrollo/article/view/13417; https://repositorio.uptc.edu.co/handle/001/15330
• Palabra clave: Flujo multifásico, Fracción volumétrica, Red Neuronal Artificial, Presión diferencial, Velocidad superficial; Multiphase flow, Volumetric fraction, Artificial Neural Network, Differential pressure, Surface speed
• License: http://purl.org/coar/access_right/c_abf2