Steel corrosion prediction based on support vector machines

Abstract

• The characteristics of sections of corroded bars are quantified to predict sectional corrosion rate of steel. • Seven digital parameters are innovatively proposed to define corroded bar shapes. • The SVM can be used to predict the sectional corrosion rate of steel. • PSO-SVM is more accurate than GS-SVM for prediction sectional corrosion rate of steel. In this paper, the 3D coordinate data of the corrosion condition of rebar are obtained by a 3D scanning method. Seven numerical parameters, such as the roundness, the section roughness, the inscribed circle radius/circumscribed circle radius and the eccentricity, are obtained by the numerical calculation method. These seven parameters are used to characterize the cross-section morphology of rusted steel bars. The particle swarm optimization support vector machine (PSO-SVM) and the grid search support vector machine (GS-SVM) are used to calculate these seven cross-section digitization parameters to predict the sectional corrosion rate of steel. This work concluded that these two optimization support vector machine (SVM) methods can accurately predict the sectional corrosion rate of steel. Compared with the GS-SVM model, the PSO-SVM steel corrosion prediction model is more accurate.