Centrifugal Compressor Stage Efficiency and Rotor Stiffness Augmentation via Artificial Neural Networks

Centrifugal compressor stages with high rotor stiffness (i.e.impeller hub-to-outer-diameter ratio) may represent a crucial element  to  cope  with  tight  rotordynamic  requirements  and  constraints that are needed for certain applications.  On the otherhand, high stiffness has a detrimental effect on the aerodynamicperformance.   Thus,  an  accurate  design  and  optimization  arerequired to minimize the performance gap with respect to low-stiffness stages.  This paper shows a redesign and optimization procedure of a centrifugal compressor stage aimed at increasing the impeller stiffness while keeping high aerodynamic performance. Two different optimization steps are employed to consider a wide design space while keeping the computational costas low as possible.  At first the attention is focused on the impeller only,  then the diffuser and the return channel are takeninto account.  The multi-objective and multi-operating point op-timization makes use of artificial neural networks (ANNs) as asurrogate model to obtain the response surfaces.  RANS calculations are carried out using the TRAF code and are employedto create the training dataset.  Once the ANN has been trained,an optimization strategy is used to find the constrained optimum geometries for the impeller and the static components. The optimized high stiffness stage is finally compared to the low stiffnessone to assess its applicability