TY - JOUR
T1 - Locating and classifying defects with artificial neural networks
AU - Luna-Avilés, A.
AU - Hernández-Gómez, L. H.
AU - Durodola, J. F.
AU - Urriolagoitia-Calderón, G.
AU - Urriolagoitia-Sosa, G.
PY - 2008
Y1 - 2008
N2 - Locating defects and classifying them by their size was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). Postulated void of three different sizes (1×1 mm, 2×2 mm and 2×1 mm) were introduced in a bar with and without a notch. The size of a defect and its localization in a bar change its natural frequencies. Accordingly, synthetic data was generated with the finite element method. A parametric analysis was carried out. Only one defect was taken into account and the first five natural frequencies were calculated. 495 cases were evaluated. All the input data was classified in three groups. Each one has 165 cases and corresponds to one of the three defects mentioned above. 395 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. This procedure was followed in the cases of the plain bar and a bar with a notch. In the next stage of this work, the ANN output was optimized with ANFIS. The accuracy of the localization and classifications of the defects was improved.
AB - Locating defects and classifying them by their size was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). Postulated void of three different sizes (1×1 mm, 2×2 mm and 2×1 mm) were introduced in a bar with and without a notch. The size of a defect and its localization in a bar change its natural frequencies. Accordingly, synthetic data was generated with the finite element method. A parametric analysis was carried out. Only one defect was taken into account and the first five natural frequencies were calculated. 495 cases were evaluated. All the input data was classified in three groups. Each one has 165 cases and corresponds to one of the three defects mentioned above. 395 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. This procedure was followed in the cases of the plain bar and a bar with a notch. In the next stage of this work, the ANN output was optimized with ANFIS. The accuracy of the localization and classifications of the defects was improved.
KW - Artificial neural network
KW - Backpropagation
KW - Computational inverse technique
KW - Location and classification of defects
UR - http://www.scopus.com/inward/record.url?scp=60349103615&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMM.13-14.117
DO - 10.4028/www.scientific.net/AMM.13-14.117
M3 - Artículo de la conferencia
AN - SCOPUS:60349103615
SN - 1660-9336
VL - 13-14
SP - 117
EP - 123
JO - Applied Mechanics and Materials
JF - Applied Mechanics and Materials
T2 - 6th International Conference on Advances in Experimental Mechanics
Y2 - 9 September 2008 through 11 September 2008
ER -