Issue 65

A. Namdar et alii, Frattura ed Integrità Strutturale, 65 (2023) 112-134; DOI: 10.3221/IGF-ESIS.65.09

Number of layers in ANNs

-

Training

Validation

Test

R 2

0.78406 3.9838

0.78312 4.4124

0.71877 4.7717

3

MSE

3 Table 10: R 2 and MSE results ANNs for model 2 at node 12.

Training: R=0.78406 Data Fit Y = T

Validation: R=0.78312 Data Fit Y = T

5 10 15 20 25

20

15

10

5

5 10 15 20 25 Target Test: R=0.71877 Data Fit Y = T

5 10 15 20 Target

All: R=0.7741 Data Fit Y = T

5 10 15 20 25

20

15

10

5

5 10 15 20 Target

5 10 15 20 25 Target

Figure 16: Regression analysis in the Y direction of displacement prediction for model 2 at node 12.

Best Validation Performance is 4.4124 at epoch 21

10 3

Train Validation

Test Best

10 2

10 1

10 0

0

5

10

15

20

25

27 Epochs

Figure 17: Prediction of displacement in Y direction for model 2 at node 12.

129