Investigations into the use of the finite element method and artificial neural networks in the non-destructive analysis of metallic tubes

Presents an investigation into the use of the finite element method and artificial neural networks in the identification of defects in industrial plants' metallic tubes, due to the aggressive actions of the fluids contained by them and/or atmospheric agents. The methodology used in this study consists of simulating a very large number of defects in a metallic tube, using the finite element method. Both variations in width and height of the defects are considered. Then, the obtained results are used to generate a set of vectors for the training of a multilayer perceptron artificial neural network. Finally, the obtained neural network is used to classify a group of new defects, simulated by the finite element method, but that do not belong to the original data set. The results obtained demonstrate the efficiency of the proposed approach and encourage future works on this subject.