Two-phase flow regime prediction using LSTM based deep recurrent neural network
This work addresses flow regime prediction in fluid dynamics, but it is incremental as it applies existing LSTM methods to a specific dataset.
The authors tackled two-phase flow regime prediction by proposing an LSTM-based deep recurrent neural network, achieving accuracy dependent on network depth and layer cell count, with deeper networks increasing prediction time.
Long short-term memory (LSTM) and recurrent neural network (RNN) has achieved great successes on time-series prediction. In this paper, a methodology of using LSTM-based deep-RNN for two-phase flow regime prediction is proposed, motivated by previous research on constructing deep RNN. The method is featured with fast response and accuracy. The built RNN networks are trained and tested with time-series void fraction data collected using impedance void meter. The result shows that the prediction accuracy depends on the depth of network and the number of layer cells. However, deeper and larger network consumes more time in predicting.