Quality prediction for polypropylene production process based on CLGPR model

Online measurement of the melt index is typically unavailable in industrial polypropylene production processes, soft sensing models are therefore required for estimation and prediction of this important quality variable. Polymerization is a highly nonlinear process, which usually produces products with multiple quality grades. In the present paper, an effective soft sensor, named combined local Gaussian process regression (CLGPR), is developed for prediction of the melt index. While the introduced Gaussian process regression model can well address the high nonlinearity of the process data in each operation mode, the local modeling structure can be effectively extended to processes with multiple operation modes. Feasibility and efficiency of the proposed soft sensor are demonstrated through the application to an industrial polypropylene production process.

Research highlights
► The Gaussian process regression model is extended for multimode process modeling.
► A combined local Gaussian process regression (CLGPR) model is developed.
► The CLGPR model is used for soft sensing of multimode processes.
► The effectiveness of the soft sensor is confirmed through an industrial case study.