PSI - Issue 68

6

Chahboub Yassine et al. / Procedia Structural Integrity 68 (2025) 310–317 CHAHBOUB Yassine/ Structural Integrity Procedia 00 (2025) 000–000

315

The time to generate the database was 300 minutes; each simulation took around five minutes. The mesh size in front of the pre-crack tip is 0.125 mm 0.0625 mm, as well as the mesh, is composed of axisymmetric quadratic elements with eight nodes. ANN and the creation of the database As already mentioned, 60 simulations for NT specimens with different GTN parameters were performed to generate the database essential to train the ANN. The trained ANN model for the NT test has 200 input neurons, 75 hidden neurons, and 5 output neurons (200-75-6). The values of the response force F refer to (neurons of the input layer), and the GTN parameters to be identified are represented by the neurons of the output layer (f 0 , f c , f f , f n , S n , and ε n ). We estimated the GTN parameters after training the neural network in a fraction of the time compared to the direct technique, which combines experimental and finite element data. f 0 =0, f c =0.0045, and f f =0.25, f n = 0.05, S n = 0,45 et ε n = 0.2 are the GTN parameters determined by utilizing the ANN. Prediction of Crack propagation for PIPELINE SPECIMEN We performed a FEM simulation using the GTN parameters obtained by the ANN; the results indicate that the simulation curve closely matches the actual curve and that they agree well in Fig. 5.

Fig. 5. Prediction failure using ANN

2.3. Quantitave Study for comparing direct method and ANN method It is noticeable that the curve found by ANN is not fully fitting the experimental data, especially at the end of the curve; this phenomenon is related to the database used to train the network. We decide to run a Statical comparison between the ANN and direct method for FP1. Four statistical measures were used, which are mean, median, standard deviation, and range, in comparing the performance between the two methods: Direct and ANN. The mean in the case of the Direct method is 50.82, the median is 51.29, and the standard deviation is 3.01. Therefore, the range will be 14.55. In the case of the ANN method, a mean of 50.50, a median of 50.44, a standard deviation of 3.19, and a range of 13.91 were found. Normality testing: We performed The Shapiro-Wilk test to check the normality of the data. The results indicate that the load force results obtained from both methods are normally distributed (p > 0.05). We first computed the load force results for the direct and ANN techniques before doing the Shapiro-Wilk test.