This work presents a framework to predict near-optimal anisotropic spacing functions suitable to perform simulations with unseen operating conditions or geometric configurations. The strategy consists of utilising the vast amount of high-fidelity data available in industry to compute a target anisotropic spacing and train an artificial neural network to predict the spacing for unseen scenarios. The trained neural network outputs the metric tensor at the nodes of a coarse background mesh that is then used to generate meshes for unseen cases. Examples are used to demonstrate the effect of the network hyperparameters and the training dataset on the accuracy of the predictions. The potential of the method is demonstrated for examples involving up to 11 geometric parameters on CFD simulations involving a full aircraft configuration. • Artificial neural networks are designed to predict anisotropic mesh spacing for unseen simulations. • Neural network architecture exploits the mathematical properties of metric tensors. • A strategy to transfer anisotropic spacing to a background mesh, including mesh morphing. • Accuracy of the predictions is assessed and meshes are shown to be suitable to perform new simulations. • Demonstration for a complex problem involving a geometrically parametrised aircraft with 11 parameters.
Lock et al. (Mon,) studied this question.