Surrogate Estimations of Complete Flow Fields of Fan Stage Designs via Deep Neural Networks

Abstract

Abstract This paper presents a first step to adapt deep neural networks (DNN) to turbomachinery designs. It is demonstrated that DNNs can predict complete flow solutions, using xyzcoordinates of the CFD mesh, rotational speed and boundary conditions as input to predict the velocities, pressure and density in the flow field. The presented DNN is trained by only twenty random 3D fan stage designs (training members). These designs were part of the initialization process of a previous optimization. The approximation quality of the DNN is validated on a random and a Pareto optimal design. The random design is a statistical outlier with low efficiency while the Pareto optimal design dominates the training members in terms of efficiency. So both test members require some extrapolation quality of the DNN. The DNN reproduces characteristics of the flow of both designs, showing its capability of generalization and potential for future applications. The paper begins with an explanation of the DNN concept, which is based on convolutional layers. Based on the working principal of these layers a conversion of a CFD mesh to a suitable DNN input is derived. This conversion ensures that the DNNs can work in a similar way as in image recognition, where DNNs show superior results in comparison to other models.