Purpose Multidisciplinary design frameworks elaborated for aeronautical applications require considerable computational power that grows enormously with the utilization of higher fidelity tools to model aeronautical disciplines like aerodynamics, loads, flight dynamics, performance, structural analysis and others. Surrogate models are a good alternative to address properly and elegantly this issue. With regard to this issue, the purpose of this paper is the design and application of an artificial neural network to predict aerodynamic coefficients of transport airplanes. The neural network must be fed with calculations from computational fluid dynamic codes. The artificial neural network system that was then developed can predict lift and drag coefficients for wing-fuselage configurations with high accuracy. The input parameters for the neural network are the wing planform, airfoil geometry and flight condition. An aerodynamic database consisting of approximately 100,000 cases calculated with a full-potential code with computation of viscous effects was used for the neural network training, which is carried out with the back-propagation algorithm, the scaled gradient algorithm and the Nguyen–Wridow weight initialization. Networks with different numbers of neurons were evaluated to minimize the regression error. The neural network featuring the lowest regression error is able to reduce the computation time of the aerodynamic coefficients 4,000 times when compared with the computing time required by the full potential code. Regarding the drag coefficient, the average error of the neural network is of five drag counts only. The computation of the gradients of the neural network outputs in a scalable manner is possible by an adaptation of back-propagation algorithm. This enabled its use in an adjoint method, elaborated by the authors and used for an airplane optimization task. The results from that optimization were compared with similar tasks performed by calling the full potential code in another optimization application. The resulting geometry obtained with the aerodynamic coefficient predicted by the neural network is practically the same of that designed directly by the call of the full potential code. Design/methodology/approach The aerodynamic database required for the neural network training was generated with a full-potential multiblock-structured code. The training process used the back-propagation algorithm, the scaled-conjugate gradient algorithm and the Nguyen–Wridow weight initialization. Networks with different numbers of neurons were evaluated to minimize the regression error. Findings A suitable and efficient methodology to model aerodynamic coefficients based on artificial neural networks was obtained. This work also suggests appropriate sizes of artificial neural networks for this specific application. We demonstrated that these metamodels for airplane optimization tasks can be used without loss of fidelity and with great accuracy, as their local minima might be relatively close to the minima of the original design space defined by the call of computational fluid dynamics codes. Research limitations/implications The present work demonstrated the ability of a metamodel with artificial neural networks to capture the physics of transonic and subsonic flow over a wing-fuselage combination. The formulation that was used was the full potential equation. However, the present methodology can be extended to model more complex formulations such as the Euler and Navier–Stokes ones. Practical implications Optimum networks reduced the computation time for aerodynamic coefficient calculations by 4,000 times when compared with the full-potential code. The average absolute errors obtained were of 0.004 and 0.0005 for lift and drag coefficient prediction, respectively. Airplane configurations can be evaluated more quickly. Social implications If multidisciplinary optimization tasks for airplane design become more efficient, this means that more efficient airplanes (for instance less polluting airplanes) can be designed. This leads to a more sustainable aviation. Originality/value This research started in 2005 with a master thesis. It was steadily improved with more efficient artificial neural networks able to handle more complex airplane geometries. There is a single work using similar techniques found in a conference paper published in 2007. However, that paper focused on the application, i.e. providing very few details of the methodology to model aerodynamic coefficients.

Structured mesh computational fluid dynamic solvers are inherently faster than unstructured solvers, which is particularly advantageous for aerodynamic design optimization, where hundreds of flow solutions are required. However, generating body-fitted multiblock meshes for complex geometries is challenging and is a time consuming task. The overset mesh technique greatly reduces the manual effort required to generate meshes over complex geometries by overlapping a series of simpler meshes. However, generating the necessary connectivity information between meshes in a robust and computationally efficient manner remains a challenge. We address this challenge by developing an efficient parallel overset grid assembly technique based on implicit hole cutting that is fully automatic. The method is fully parallel and scales to hundreds of processors. Several optimizations of the Common Research Model wing-body-tail configuration are performed using the meshes generated by our technique. We compare the best drag reduction obtained from multiblock and overset meshes using two different artificial dissipation schemes. The smooth, highly orthogonal overset meshes produce better results than the multiblock meshes, by up to 3 drag counts. An application to rotorcraft design is also presented. The demonstrated meshing flexibility and accurate transonic solutions make the overset mesh technique ideally suited for aerodynamic shape optimization.

The strut-braced wing aircraft configuration promises to reduce fuel burn by enabling higher spans that reduce lift-induced drag. A successful design for this configuration depends on a careful trade-off between the various sources of drag and structural weight. When using CFD-based aerodynamic shape optimization, generating high-quality structured meshes for the strut-braced wing configuration becomes challenging, especially near junctions. Furthermore, mesh deformation procedures frequently generate negative volume cells when applied to these structured meshes during optimization. We address this issue by using overset meshes and a component-based parametrization technique to achieve a flexible design optimization cycle capable of handling changing junctions. We use this approach to minimize drag of the PADRI 2017 strut-braced wing benchmark for a fixed lift constraint at transonic flight conditions. The drag of the optimized configuration is 15% lower than the baseline due to the reduction of shocks and separation in the wing-strut junction region. This result represents an example in which high-fidelity modeling is required to quantify the benefits of a new aircraft configuration and address potential issues during the conceptual design.

Mesh generation for high-fidelity CFD simulation and aerodynamic shape optimization is a timeconsuming task. We can model complex geometries accurately using overset meshes where multiple high-quality structured meshes corresponding to different aircraft components overlap to model the full aircraft configuration. Nevertheless, from the geometry manipulation standpoint, most methods operate on the entire geometry rather than on each component, which diminishes the advantages of overset meshes. To address this issue, we introduce a geometry module that operates on individual components and automatically computes their intersections to automate the overset mesh updates during optimization. This method is also differentiated to compute derivatives with respect to component-based design variables and is integrated within an optimization framework. Using these automatically updated meshes and the corresponding derivatives, we perform aerodynamic shape optimization including the wing-body intersection for the DLR-F6 geometry and achieve a reduction of 15 drag counts (5%) compared to the baseline design.

No abstract