Study on support vector machine based quality prediction of complex mechatronic systems

Abstract

Aimed to build a health monitoring scheme of complex mechatronic systems, a quality prediction on Tennessee Eastman (TE) process based on support vector machine (SVM) is proposed in this paper after a brief investigation on the regression ability of SVM. The SVM model is builded using the datasets generated by TE process simulation platform. Furthermore the prediction precision of SVM is testified using the simulation of TE process compared with other prediction methods. It indicates from the results that SVM is more beneficial according to the root mean square errors (RMSE) between the actual and the predicted data.