Premium
Use of artificial neural network to assess the effect of mean stress on fatigue of overhead conductors
Author(s) -
Pestana Mielle Silva,
Kalombo Remy Badibanga,
Freire Júnior Raimundo Carlos Silverio,
Ferreira Jorge Luiz Almeida,
Silva Cosme Roberto Moreira,
Araújo José Alexander
Publication year - 2018
Publication title -
fatigue and fracture of engineering materials and structures
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.887
H-Index - 84
eISSN - 1460-2695
pISSN - 8756-758X
DOI - 10.1111/ffe.12858
Subject(s) - conductor , materials science , aluminium , ultimate tensile strength , structural engineering , durability , artificial neural network , stress (linguistics) , electrical conductor , composite material , engineering , computer science , artificial intelligence , linguistics , philosophy
The aim of this work was to use artificial neural networks (ANNs) to model the effect of mean tensile stresses on the fatigue resistance of an aluminum conductor steel reinforced. To train the ANN, fatigue data available for this type of conductor subjected to 2 different levels of mean stresses in the aluminium wires (49 and 74 MPa) were used. It is shown that the use of ANN enabled the construction of constant life diagrams (10 5 , 10 6 , 10 7 , and 10 8 fatigue loading cycles) for the conductor. These results confirmed that the ANN is able to accurately estimate the effect of mean tensile stresses on conductor durability even considering just a limited number of data for its training.