A Gaussian moment method and its augmentation via LSTM recurrent neural networks for the statistics of cavitating bubble populations. (June 2020)

• Record Type: Journal Article
• Authors: Bryngelson, Spencer H.; Charalampopoulos, Alexis; Sapsis, Themistoklis P.; Colonius, Tim
• Is Part Of: International journal of multiphase flow. Volume 127(2020)
• Publication Date: 2020-06
• Subjects: Bubbly flow -- Phase averaging -- Moment methods -- Recurrent neural networks; Multiphase flow -- Periodicals; Écoulement polyphasique -- Périodiques; Multiphase flow; Periodicals; 620.1064
• DOI: 10.1016/j.ijmultiphaseflow.2020.103262
• Languages: English
• ISSNs: 0301-9322

Abstract

Highlights: First moment method for statistics of cavitating bubble dynamics. Gaussian closures of unrepresented moments. Long short-term memory recurrent neural networks augment low-order moment closures and improve accuracy of high-order ones. Model reduces computational cost when compared to class-based methods. Abstract: Phase-averaged dilute bubbly flow models require high-order statistical moments of the bubble population. The method of classes, which directly evolve bins of bubbles in the probability space, are accurate but computationally expensive. Moment-based methods based upon a Gaussian closure present an opportunity to accelerate this approach, particularly when the bubble size distributions are broad (polydisperse). For linear bubble dynamics a Gaussian closure is exact, but for bubbles undergoing large and nonlinear oscillations, it results in a large error from misrepresented higher-order moments. Long short-term memory recurrent neural networks, trained on Monte Carlo truth data, are proposed to improve these model predictions. The networks are used to correct the low-order moment evolution equations and improve prediction of higher-order moments based upon the low-order ones. Results show that the networks can reduce model errors to less than 1% of their unaugmented values.