摘要
The accurate modeling and prediction of the rotating stall in a centrifugal pump is a significant challenge. One of the modeling techniques that can improve the accuracy of the flow predictions is the large eddy simulation （LES）. The quality of the LES predictions depends on the sub-grid-scale （SGS） model implemented in the LES. This paper assesses the influence of various SGS models that are suitable for predicting rotating stall in a low-specific speed centrifugal pump impeller. The SGS models considered in the present work include the Smagorinsky model （SM）, the dynamic Smagorinsky model （DSM）, the dynamic non-linear model （DNM）, the dynamic mixed model （DMM） and the dynamic mixed non-linear model （DMNM）. The results obtained from these models are compared with the PIV and LDV experimental data. The analysis of the results shows that the SGS models have significant influences on the flow field. Among the models, the DSM, the DMM and the DMNM can successfully predict the ＂two-channel＂ stall phenomenon, but not the SM and the DNM. According to the simulations, the DMNM gives the best prediction on the mean velocity flow field and also indicates improvements for the simulation of the turbulent flow. Moreover, the high turbulent kinetic energy predicted by the DMNM is in the best agreement with the experiment data.
The accurate modeling and prediction of the rotating stall in a centrifugal pump is a significant challenge. One of the modeling techniques that can improve the accuracy of the flow predictions is the large eddy simulation （LES）. The quality of the LES predictions depends on the sub-grid-scale （SGS） model implemented in the LES. This paper assesses the influence of various SGS models that are suitable for predicting rotating stall in a low-specific speed centrifugal pump impeller. The SGS models considered in the present work include the Smagorinsky model （SM）, the dynamic Smagorinsky model （DSM）, the dynamic non-linear model （DNM）, the dynamic mixed model （DMM） and the dynamic mixed non-linear model （DMNM）. The results obtained from these models are compared with the PIV and LDV experimental data. The analysis of the results shows that the SGS models have significant influences on the flow field. Among the models, the DSM, the DMM and the DMNM can successfully predict the ＂two-channel＂ stall phenomenon, but not the SM and the DNM. According to the simulations, the DMNM gives the best prediction on the mean velocity flow field and also indicates improvements for the simulation of the turbulent flow. Moreover, the high turbulent kinetic energy predicted by the DMNM is in the best agreement with the experiment data.
基金
Project supported by the National Nature Science Foun-dation of China(Grant Nos.51139007,51321001)
the Natural Science Foundation of Zhejiang Province(Grant No.LQ17E090005)
the National Science and Technology Support Program of China(Grant No.2015BAD20B01)
