Prediction of Corrosion Rate of Process Pipeline Based on KPCA and SVM

In order to estimate the corrosion rate of process pipeline under limited condition data, a method based on kernel principal component analysis (KPCA) and support vector machine (SVM) was proposed. The kernel principal component analysis method was used to effectively integrate the factors that affect the corrosion rate of pipeline. The kernel components with low contribution rate were discarded. The principal components with higher contribution rate were taken as input variables of the support vector machine, and the corrosion rate was taken as output. The support vector machine model was established to predict the corrosion rate of pipelines. The prediction model was verified by engineering data of process pipelines. The results show that prediction error of the method based on kernel principal component analysis and support vector machine was low, and accurate prediction data could be obtained.