The Inferential Controller PLS-based for an Industrial FCCU Fractionator

X. Tian, H. Tian, and L. Tu (PRC)


PLS, Soft Sensor, Inferential Control, DMC


A quadratic Partial Least Squares algorithm based on nonlinear constrained programming is proposed. Sequential Unconstrained Minimization Technique is employed to calculate the outer input weights and the parameters of inner relationship. It was found that the arithmetic can not only explain more of the underlying variability of the data, but also has improved modelling and predictive ability. An inferential control system is implemented on the Distribute Control System (DCS) of a fluid catalytic cracking unit ( FCCU) main fractionator. A soft sensor QPLS–based was developed to estimate solidifying point of diesel oil on line. The controller was established via constrained Dynamic Matrix Control algorithm. Real time application results demonstrated the performance that the inferential control system based on QPLS was much better than the original tray temperature control system. This resulted in a 1.0% increase in production rate, and a significant increase in profit.

Important Links:

Go Back