Table 4 The correlation coefficient (R), mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the three parts with different mesh number.

From: Rapid thickness distribution prediction of superplastic formed parts based on geometry adapted PSO-BP neural network surrogate model

mesh number

R

MSE (mm2)

MAE (mm)

MAPE

3455

0.9996

5.527 × 10− 5

0.0057

0.62%

6091

0.9997

4.947 × 10− 5

0.0054

0.59%

9470

0.9994

8.151 × 10− 5

0.0055

0.59%

Back to article page