arXiv (Cornell University) · 2017 · 13 citations · 1 references
ComputingComputational EngineeringComputer ScienceFluid DynamicsMachine LearningMultiphase FlowDeep LearningFlow Feature ExtractionFlow ModelingNeural NetworksPattern RecognitionFlow PatternFlow Pattern AnalysisFlow Pattern IdentificationFlow Pattern RecognitionFluid Flow PatternsMultilayer PerceptronMultiphase Flow ModelingPerceptron
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.
1