3-5-1 Neural Network results
3-5-1 Neural Network results
-
The first NN configuration had structure 3-3-1:
- input layer with 3 nodes for ε, ε’ and T- hidden layer with 5 nodes- output layer with 1 node for flow stress s prediction
Desired and predicted flow stress vs. strain for test 28
3-component input vectors including strain, constant strain-rate and constant temperature ε,ε', T were used for training and testing the 3-5-1 NN. Desired flow stress σ and predicted flow stress pred, yielded by the learned 3-5-1 NN were plotted vs. strain (see Fig. 3 for test 28). Curve reconstruction is very poor in curve geometry (the reconstructed curve is a straight line) and flow stress values (predicted flow stress << desired flow stress)
Who's online
There are currently 0 users and 208 guests online.