Inferential feedback control of distillation composition based on PCR and PLS models

A principal component regression (PCR) and partial least squares (PLS) model based inferential feedback control strategy for distillation composition control is developed. PCR and PLS model based software sensors are developed from process operational data so that the top and bottom product compositions can be estimated from multiple tray temperature measurements. The PCR and PLS software sensors are used in the feedback control of the top and bottom product compositions. This strategy can overcome the problem of substantial time delay in composition analysers based control and the problem of substantial bias in single tray temperature control. Static estimation bias and the resulting static control offsets are eliminated through mean updating of process measurements. Applications to a simulated methanol-water separation column demonstrate the effectiveness of this control strategy