Abstract
The automation and intelligence of grid generation are still bottleneck problems in computational fluid dynamics. This problem can be solved by generating anisotropic quadrilateral by advancing layer method and isotropic triangular mesh by advancing front method. However, the advancing layer method needs to calculate the advancing direction, step size, a correction factor of the concave and convex area, so the automation level and efficiency of grid generation need to be improved. To solve the above problems, a hybrid grid generation method based on BP-ANN is proposed. The grid data generated by traditional methods are learned by a neural network, and the neural network can predict the above key parameters. Finally, a mesh generation example of 30P30N multi-element airfoil shows that the proposed algorithm can effectively improve the adaptability, efficiency and quality of hybrid mesh generation.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.