Advances in Aerodynamics

Table 8 Comparison of accuracy metrics for aerodynamic coefficient predictions of the baseline wing by MLP and CNN at different Mach numbers and angles of attack

From: High-dimensional aerodynamic data modeling using a machine learning method based on a convolutional neural network

Object	Model	Relative error ε	R²	RRMSE	RMAE
\({C}_{L}\)	MLP	7.10%	0.9855	0.1198	0.3143
\({C}_{L}\)	CNN	1.55%	0.9993	0.0262	0.0699
\({C}_{D}\)	MLP	4.61%	0.9745	0.1591	0.4046
\({C}_{D}\)	CNN	1.16%	0.9984	0.0402	0.0798
\({C}_{M}\)	MLP	5.74%	0.9893	0.1029	0.2550
\({C}_{M}\)	CNN	2.23%	0.9984	0.0399	0.0913

Back to article page