A Data-Driven Reduced Order Modeling for Fluid Flow Analysis Based on Series Forecasting Intelligent Algorithm

Abstract

In this work, we propose a data-driven reduced-order model (ROM) for high dimensional flow fields by combining flow modal decomposition and multiple regression. Singular value decomposition-based (SVD-based) proper orthogonal decomposition (POD) is employed to extract principal spatial modes representing energy and dynamics level of flow field. The temporal coefficient regression for flow modal series is realized through intelligent algorithms: light gradient boosting machine (LGBM), long short-term memory (LSTM), and temporal convolutional neural network (TCN). The performance of the ROMs is assessed by predicting and analyzing low Reynolds number flow around a circular cylinder and transonic flow around a airfoil. The experiments show that vortex flow and shock flow are both well predicted with the POD-LGBM, POD-LSTM and POD-TCN, whereas the prediction result of POD-TCN is the closest to the numerical solution, with the minimum root mean squared error. Also, it should be noted that the prediction accuracy depends on the reduced-order results of flow field.

Keywords

• Reduced order modeling
• series forecasting
• proper orthogonal decomposition
• deep learning
• neural network