PSI - Issue 42

6

Author name / Structural Integrity Procedia 00 (2019) 000 – 000

Chahboub Yassine et al. / Procedia Structural Integrity 42 (2022) 1025–1032

1030

3000

Experiment

SIMULATION RESULTS GTN YASSINE

2500

Load [kN]

2000

1500

1000

500

COD [mm]

0

0

2

4

6

8

10

12

14

16

18

20

Fig. 4. Force vs. crack opening displacement for FP1

2.2. Prediction of failure of the pipeline using ANN approach The ANN was used in many fields to improve productivity and quality. Using the artificial neural network optimizes the time consumed while predicting the pipeline's failure. In the last section, we approved that the GTN tool is useful for predicting the pipeline's failure, but it took 30 days. It is important to highlight that we used just a quarter of the specimen in the last section to reduce the computing time. So we can conclude that for complicated and sophisticated equipment, the simulation period will be much longer than three days. Hence, it was necessary to find another alternative to cover the gap and reduce the time consumed in predicting equipment failure. NT Specimen modelling The simulation and geometry of the NT specimen are indicated in Fig.5; the reason behind choosing the NT specimen is the short time of computation, which leads us to generate a significant database to train the neural network. To find the GTN parameters using ANN, we decided to make 60 simulations of the NT specimen Fig. 5.

Fig. 5. Simulation of NT specimen