Deep Learning as a Tool to Predict Flow Patterns in Two-Phase Flow

Autor:	Ezzatabadipour, Mohammadmehdi, Singh, Parth, Robinson, Melvin D., Guillen-Rondon, Pablo, Torres, Carlos
Rok vydání:	2017
Předmět:	Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	In order to better model complex real-world data such as multiphase flow, one approach is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use deep learning methods, and in particular employ the multilayer perceptron, to build an algorithm that can predict flow pattern in twophase flow from fluid properties and pipe conditions. The preliminary results show excellent performance when compared with classical methods of flow pattern prediction. Comment: Part of DM4OG 2017 proceedings (arXiv:1705.03451)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1705.07117 Zobrazit plný text záznamu View this record from Arxiv