Article ID Journal Published Year Pages File Type
1470724 Corrosion Science 2009 7 Pages PDF
Abstract

The support vector regression (SVR) approach combined with particle swarm optimization (PSO) for its parameter optimization is proposed to establish a model for prediction of the corrosion rate of 3C steel under five different seawater environment factors, including temperature, dissolved oxygen, salinity, pH value and oxidation–reduction potential. The prediction results strongly support that the generalization ability of SVR model consistently surpasses that of back-propagation neural network (BPNN) by applying identical training and test samples. The absolute percentage error (APE) of 80.43% test samples out of 46 samples does not exceed 1% such that the best prediction result was provided by leave-one-out cross validation (LOOCV) test of SVR. These suggest that SVR may be a promising and practical methodology to conduct a real-time corrosion tracking of steel surrounded by complicated and changeable seawater.

Related Topics
Physical Sciences and Engineering Materials Science Ceramics and Composites
Authors
, , , , , ,