System Identification Technique and Neural Networks for Material Lifetime Assessment Application - Complex System Modelling and Control Through Intelligent Soft Computations - page 774

Fig. 6 S-N curves obtained
by the NN-NARX model and
the experimental data for
R = 0.9 of Material I
Fig. 7 S-N curves obtained
by the NN-NARX model and
the experimental data for
R = 0.8 of Material I
Fig. 8 S-N curves obtained
by the NN-NARX model and
the experimental data for
R = 0.7 of Material I
It can be seen that the NN-NARX model prediction results were consistent with
the experimental data showing the NN applicability and capability to model the
problem considered. The NN model also showed its ability to dynamically predict
the fatigue lives sliding over each stress level in a fashion of spectrum loading made
up by several R values. Looking at the fatigue life prediction results for Material I
produced by the NN architecture, it may be worth to also note that the results