A non-intrusive reduced order model with transformer neural network and its application
| Autor: | Pin Wu, Feng Qiu, Weibing Feng, Fangxing Fang, Christopher Pain |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Physics of Fluids. 34:115130 |
| ISSN: | 1089-7666 1070-6631 |
| Popis: | In this paper, a novel method to construct non-intrusive reduced order model (ROM) is proposed. The method is based on proper orthogonal decomposition and transformer neural network. Proper orthogonal decomposition is used to generate the basis functions of the low-dimensional flow field, and the coefficients are taken as low-dimensional flow field features. Transformer network is used to extract temporal feature relationships from low-dimensional features. Compared with recurrent neural network and convolutional neural network, transformer network can better capture flow dynamics. At online stage, the input temporal flow sequences are calculated in parallel and can effectively reduce online calculation time. The model proposed in this paper has been verified in two scenarios: two-dimensional flow past a cylinder and two-dimensional flow past a building group. Experimental results show that our model can better capture the flowing change details and has higher accuracy. Compared with the ROM based on long short-term memory and temporal convolutional network, the prediction error is reduced by 35% and 60%, and the time cost is reduced by 65% and 60%. Finally, we apply the ROMs to a practical three-dimensional complicated scenario, flow past London South Bank University, and discuss future development of ROMs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|