Multi-network collaborative lift-drag ratio prediction and airfoil optimization based on residual network and generative adversarial network

Abstract

As compared with the computational fluid dynamics(CFD), the airfoil optimization based on deep learning significantly reduces the computational cost. In the airfoil optimization based on deep learning, due to the uncertainty in the neural network, the optimization results deviate from the true value. In this work, a multi-network collaborative lift-to-drag ratio prediction model is constructed based on ResNet and penalty functions. Latin supersampling is used to select four angles of attack in the range of 2°-10° with significant uncertainty to limit the prediction error. Moreover, the random drift particle swarm optimization (RDPSO) algorithm is used to control the prediction error. The experimental results show that multi-network collaboration significantly reduces the error in the optimization results. As compared with the optimization based on a single network, the maximum error of multi-network coordination in single angle of attack optimization reduces by 16.0%. Consequently, this improves the reliability of airfoil optimization based on deep learning.

Keywords: airfoil; deep learning; parameter optimizatioin; particle swam optimisation; random.

FIGURE 1

Flow chart of optimization of lift-drag ratio.

FIGURE 2

ResBlock structure.

FIGURE 3

CNN Block structure (A) Based on ResBlock and Shortcut bypass deletion (B) Typical CNN structure.

FIGURE 4

CNN and ResNet structure (when two blocks with the same output channel overlap, Only mark once, such as c = 64. When two blocks with different output channels overlap, mark in order, such as c = 64, 48 means that the output channel of the previous block is 64, and the output channel of the next block is 48)

FIGURE 5

WGAN structure diagram.

FIGURE 6

Some airfoil geometry samples in the database.

FIGURE 7

Loss function curve of network training (A) CNN Ⅲ (B) ResNet Ⅱ (C) ResNet Ⅲ (D) Validation set of all networks Loss function curve.

FIGURE 8

Geometry and lift-to-drag ratio prediction of the determined airfoil and the uncertain airfoil (A) solid line: the determined airfoil from the data set; dashed line: the uncertain airfoil generated by WGAN (B) different network pairs Determine the lift-to-drag ratio prediction of the airfoil, showing consistency (C) The lift-to-drag ratio predictions of the uncertain airfoil of different networks are significantly different.

FIGURE 9

The IPG parameter distribution of the WGAN generated airfoil and the data set airfoil.

FIGURE 10

The optimization result of ion number M = 50 (A) The lift-drag ratio prediction of the five optimization results by Adjective and CNN Ⅲ (B) The airfoil geometry of the five optimization results and the initial airfoil optimized at one time (C) 5 times The change curve of the weighted value of the lift-to-drag ratio during the optimization process.

FIGURE 11

The optimization result of the number of ions M = 100 (A) The prediction of the lift-to-drag ratio of the fifth optimization result by Adjective and CNN Ⅲ (B) The airfoil geometry of the fifth optimization result And the initial airfoil of one of the optimizations (C) The weighted value change curve of the lift-drag ratio during the fifth optimization process.

FIGURE 12

The optimization results are in the network participating in the optimization (ResNet Ⅲ or Adjective) and the network not participating in the optimization (CNN Ⅲ) The lift-to-drag ratio prediction curve in (A) is based on the optimization result of ResNet Ⅲ for single target angle of attack (B) is based on the optimization result of Adjective for single target angle of attack (C) is based on the optimization result of ResNet Ⅲ for multi-target angle of attack (D) Optimization results based on Adjective for multi-target angles of attack.

FIGURE 13

Comparison of optimization results with the best airfoil under the corresponding target in the data set (A) Airfoil geometry with 6° single angle of attack lift-to-drag ratio as the optimization target (B) The multi-angle of attack lift-drag ratio is the airfoil geometry under the target (C) The lift-drag ratio curve under the target with 6° single angle of attack lift-drag ratio (D) The lift-drag ratio curve under the target with multiple angles of attack lift-drag ratio.

FIGURE 14

Verification of lift-drag ratio based on CFD optimization results. (A) Calculation results of lift drag ratio of the best airfoil in the database at 0° angle of attack with different grid numbers (B) lift drag ratio curves of the best airfoil, initial airfoil and optimized airfoil in the database.

FIGURE 15

Stall characteristics of optimization results. (A) Calculation results of lift drag ratio of different grid numbers for the best airfoil in the database at 10° angle of attack (B) change curve of lift coefficient of the best airfoil, initial airfoil and optimized airfoil in the database with angle of attack (C) change curve of drag coefficient of the best airfoil, initial airfoil and optimized airfoil in the database with angle of attack.