Deep cluster neural network model construction method for pneumatic data processing

Abstract

The invention discloses a deep cluster neural network model construction method for aerodynamic data processing, and relates to the technical field of deep cluster neural network model construction in the aerodynamic data processing field. The method comprises the following steps: a, preparing and preprocessing a data set: firstly, obtaining an aerodynamic data set through a computational fluid dynamics method, and extracting main design parameters and response parameters in the aerodynamic data set; classifying the data, and dividing the data into a plurality of subsets; labelling each subset ; finally, dividing the pneumatic data set into a training set, a verification set and a test set; b, constructing a deep cluster neural network model; c, training a deep cluster neural network model; and d, verifying the deep cluster neural network model. When the cluster neural network obtained through training of the method is used for processing aerodynamic data, the defect of a traditional neural network model in the environment of insufficient sample quality caused by uneven sample sampling or uneven sample distribution can be overcome, and therefore the prediction precision of the model is improved.

Description

technical field [0001] The invention relates to the technical field of deep cluster neural network model construction in the field of aerodynamic data processing. Background technique [0002] With the continuous development of the country's economy and technology, the aerospace field is also advancing. The research of aerodynamics directly affects the development and advancement of the aerospace industry. In current aerodynamic research, there are mainly three sources of data: numerical calculations, wind tunnel experiments, and flight tests. [0003] The numerical calculation method is the computational fluid dynamics method, which can provide high-precision numerical simulation results of the flow field. However, the solution of aerodynamic partial differential equations is easily affected by turbulence and flow field grid density, which requires a lot of time and cost, and some complex partial differential equations do not have numerical solutions. [0004] A wind tun...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a method for constructing a deep cluster neural network model for aerodynamic data processing aimed at the defects and deficiencies in the above-mentioned prior art. When the cluster neural network trained by this method is used to process aerodynamic data, It can make up for the defects of the traditional neural network model in the environment of insufficient sample quality caused by uneven sample sampling or uneven sample distribution, thereby improving the prediction accuracy of the model

Images