Airfoil flow field rapid prediction method based on deep learning

Abstract

The invention provides an airfoil flow field rapid prediction method based on deep learning. The method comprises the steps of generating a sample data set; building a deep learning neural network model based on the data set; and applying the built deep neural network to rapid prediction of the airfoil flow field. According to the method, only the grids with obvious airfoil near-field flow parameter changes are intercepted to be used for training and testing the neural network model, and compared with the prior art, data points and time consumption can be reduced as much as possible while flow field feature extraction and flow field parameter prediction precision are guaranteed, and efficiency is improved; compared with the prior art, the multi-layer perceptron neural network model established by the invention can describe a more complex nonlinear relationship, improve the resolution of airfoil flow field features, and contribute to accurate identification of the flow field features. The method aims to construct and train the neural network for a series of airfoils derived from the same reference airfoil, and has high pertinence, so that the same series of airfoil flow fields can be quickly and accurately predicted.

Description

technical field [0001] The invention relates to the fields of computational fluid dynamics and artificial intelligence, in particular to a method for fast prediction of airfoil flow field based on deep learning. Background technique [0002] Airfoil optimization design is usually to optimize the same series of airfoils derived from a reference airfoil. The airfoil optimization design method has developed from early wind tunnel experiments to computational fluid dynamics (CFD), which greatly shortens the design cycle. However, there are a lot of flow field calculation problems in the airfoil optimization process based on CFD technology, which requires a lot of time Compute time and resources. As a system, the airfoil flow field must have its own characteristics, and repeated CFD calculations ignore this point and reduce the efficiency. Deep learning has a powerful learning ability for high-order complex functions, has unique advantages in feature extraction, and can make fa...

AI Technical Summary

Problems solved by technology

The airfoil optimization design method has developed from early wind tunnel experiments to computational fluid dynamics (CFD), which greatly shortens the design cycle. However, there are a lot of flow field calculation problems in the airfoil optimization process based on CFD technology, which requires a lot of time Computational Time and Resources

As a system, the airfoil flow field must have its own characteristics. Repeated CFD calculations ignore this point and reduce the efficiency

Images