Abstract:

A deep-learning LSTM-based POD model （LSTM-POD） based on long short-term memory （LSTM） and proper orthogonal decomposition （POD） is developed for the turbulent wake of the square-back Ahmed automotive general model. A high time-resolution reconstruction is achieved by establishing the mapping relationship between the POD modal coefficients of the non-time-resolved planar velocity field and the time-resolved velocity signals at a number of discrete points， and the effect of different time-step configurations， i.e.， the single time step （LSTM-Sin） and multiple time steps （LSTM-Mul） on the reconstruction results is compared. The results show that the LSTM-POD model has strong learning and generalization ability in time series reconstruction， In addition， LSTM-Mul considers temporal continuity and correlation， the reconstructed mode coefficients （lower order） and velocity fields of which are more consistent with the POD reconstructed results compared with that of LSTM-Sin. The deep learning model proposed in this study can alleviate the problems of high resource consumption and low computational efficiency in obtaining high time resolution flow field data through experiments and high-precision numerical simulation.

Key words: turbulent wake of automobiles, deep learning, reconstruction of flow fields, POD, LSTM