Neural Soft-Sensor of Product Quality Prediction

Abstract

A novel soft-sensor model based on principal component analysis (PCA), radial basis function (RBF) networks, and multi-scale analysis (MSA) is proposed to predict the properties of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, multi-scale analysis is introduced to acquire much more information and to reduce the uncertainty of the system, and RBF networks are employed to characterize the nonlinearity of the process. The prediction of the melt index (MI) or quality of polypropylene produced in a practical industrial process is carried out as a case study. The research results show that the proposed method provides promising prediction reliability and accuracy