Browsing by Author "Sureshbabu, Sanjeeth"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Deep-learning methods for non-linear transonic flow-field prediction
    (AIAA, 2023-05-08) Sureshbabu, Sanjeeth; Tejero, Fernando; Sánchez Moreno, Francisco; MacManus, David; Sheaf, Christopher
    It is envisaged that the next generation of ultra-high bypass ratio engines will use compact aero-engine nacelles. The design and optimisation process of these new configurations have been typically driven by numerical simulations, which can have a large computational cost. Few studies have considered the nacelle design process with low order models. Typically these low order methods are based on regression functions to predict the nacelle drag characteristics. However, it is also useful to develop methods for flow-field prediction that can be used at the preliminary design stages. This paper investigates an approach for the rapid assessment of transonic flow-fields based on convolutional neural networks (CNN) for 2D axisymmetric aeroengine nacelles. The process is coupled with a Sobel filter for edge detection to enhance the accuracy in the prediction of the shock wave location. Relative to a baseline CNN built with guidelines from the open literature, the proposed method has a 75% reduction in the mean square error for Mach number prediction. Overall, the presented method enables the fast prediction of the flow characteristics around civil aero-engine nacelles.
  • Thumbnail Image
    ItemOpen Access
    Point-enhanced convolutional neural network: a novel deep learning method for transonic wall-bounded flows
    (Elsevier, 2024-12) Tejero, Fernando; Sureshbabu, Sanjeeth; Boscagli, Luca; MacManus, David
    Low order models can be used to accelerate engineering design processes. Ideally, these surrogates should meet the conflicting requirements of large design space coverage, high accuracy and fast evaluation. Within the context of aerospace applications at transonic conditions, this can be challenging due to the associated non-linearity of the flow regime. Different methods have been investigated in the past to predict the flow-field around shapes such as airfoils or cylinders. However, they usually have reduced spatial resolution, limiting the prediction capabilities within the boundary layer which is of interest for transonic wall-bounded flows. This work proposes a novel Point-Enhanced Convolutional Neural Network (PCNN) method that combines the advantages of the well-established PointNet and convolutional neural network approaches. The PCNN model has relatively low memory requirements in the training process, preserves the spatial correlation in the domain and has the same resolution as a traditional computational method. The architecture is used for the flow-field prediction of civil aero-engine nacelles in which it is demonstrated that the flow features of peak isentropic Mach number (Mis), pre-shock isentropic Mach number and shock location (X/Lnac) are captured within ^Mis = 0.02, ^Mis=0.04, ^X/Lnac=0.007, respectively. The PCNN model successfully predicts the integral parameters of the boundary layer, in which the incompressible displacement thickness, momentum thickness and shape factor are typically within 5% of the CFD. Overall, the PCNN method is demonstrated for transonic wall-bounded flows for a range of flow physics that include shock waves and shock-induced separation.
  • Thumbnail Image
    ItemOpen Access
    Towards real-time CFD: novel deep learning architecture for transonic wall-bounded flows
    (2024-03-27) Tejero, Fernando; Sureshbabu, Sanjeeth; Boscagli, Luca; MacManus, David
    Low order models can be used to accelerate engineering design processes. These surrogates should meet the conflicting requirements of large design space coverage, high accuracy and fast evaluation. Within the context of aerospace applications at transonic conditions, this can be challenging due to the associated non-linearity of the flow regime. This work develops a deep learning based method for flow-field prediction. It preserves the spatial resolution of the underlying data, which enables the resolution of the boundary layer. This is an advance relative to current state-of-the-art for transonic flows. The architecture is demonstrated for a complex problem of aero-engine nacelles. The prediction of the primitive flow variables is within a root mean square error of 6×10−5. The model is used to extract the nacelle drag, and its accuracy is about 6.8% relative to CFD computations. The overall method is an enabling and fast preliminary design capability with self-consistent data for multidisciplinary design studies.