The corrosion behavior of X65 steel and 304 stainless steel (SS) was investigated in typical passivation,uniform corrosion and pitting solution systems by electrochemical noise (EN) technique. Elevencharacteristic parameters were extracted from EN data based on statistical analysis, shot noise theory,and wavelet analysis methods. Subsequently, the data samples composed by the extracted parameterswere analyzed by gradient boosting decision tree (GBDT) model. The results indicated that the proposedGBDT model could efficiently and accurately discriminate the corrosion type for data samplescontaining X65 steel and 304SS. The discrimination results of GBDT for the corrosion type areconsistent with their corroded morphology analysis. Among the eleven parameters extracted from ENmeasurements, noise resistance Rn, average frequency fn and wavelet dimension of EPN (WD_E) havethe greatest influence on GBDT model.
展开▼
