GPR model with signal preprocessing and bias update for dynamic processes modeling

This paper introduces a Gaussian process regression (GPR) model which could adapt to both linear and nonlinear systems automatically without prior introduction of kernel functions. The applications of GPR model for two industrial examples are presented. The first example addresses a biological anaerobic system in a wastewater treatment plant and the second models a nonlinear dynamic process of propylene polymerization. Special emphasis is placed on signal preprocessing methods including the Savitzky-Golay and Kalman filters. Applications of these filters are shown to enhance the performance of the GPR model, and facilitate bias update leading to reduction of the offset between the predicted and measured values.

► We presented GPR adapts to both linear and nonlinear dynamic system modeling. ► Performance of GPR was significantly improved by online adaptive filtering. ► Adaptability of GPR was significantly improved by bias correction. ► Two industrial dynamic processes were used to present the performance of GPR model.