Prediction of Metal Corrosion by Neural Networks

Z. Jančíková, O Zimný, P. Koštial, Faculty of Metallurgy and Material Engineering, VŠB – Technical University of Ostrava, Czech Republic The contribution deals with the use of artifi cial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are not known so far. Classical analytical and mathematical functions are of limited use to describe this type of strongly non-linear system depending on various meteorological-chemical factors and interaction between them and on material parameters. Nowadays there is certain chance to predict a corrosion loss of materials by artifi cial neural networks. Neural networks are used primarily in real systems, which are characterized by high nonlinearity, considerable complexity and great diffi culty of their formal mathematical description.