Details

Autor(en) / Beteiligte

• Kenny, Elaine D.
• Paredes, Ramón S.C.
• de Lacerda, Luiz A.
• Sica, Yuri C.
• de Souza, Gabriel P.
• Lázaris, José

Titel

Artificial neural network corrosion modeling for metals in an equatorial climate

Ist Teil von

• Corrosion science, 2009-10, Vol.51 (10), p.2266-2278

Ort / Verlag

Kidlington: Elsevier Ltd

Erscheinungsjahr

2009

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• The majority of the metals used in the distribution and transmission electric energy lines, such as cables, towers and accessories are susceptible to the corrosion degradation process. For that reason, studying the factors that influence the atmospheric corrosion is an important issue. In this paper, an artificial neural network model was developed with linear and sigmoidal functions, aiming to predict low-carbon steel, copper and aluminum corrosion rates according to environmental parameters in the area of São Luis – Maranhão, Brazil. The area along the “702 – São Luis II –Presidente Dutra” 500 kV transmission line, located in an equatorial region, is employed for this purpose. A specific methodology was developed to determine the local corrosivity rate for these metals. Five atmospheric corrosion stations (ACS) were installed along the 702 transmission line in an extension of 200 km. Along with the meteorological data, local pollutants were collected and analyzed during a period of two years. In the same period, specimens were exposed to this atmosphere and periodically collected for corrosion evaluation. The obtained results indicate that the neural network can be used as a good corrosion estimator.