PID2018 Benchmark Challenge: learning feedforward control

TL;DR

This paper presents the design and evaluation of learning feedforward controllers for a refrigeration cycle, demonstrating improved control performance through simulation comparisons with traditional PID controllers.

Contribution

It introduces B-spline network and low-pass filter based LFFCs for refrigeration control, showing their effectiveness with minimal effort compared to PID controllers.

Findings

B-spline network LFFC achieved J=0.6536

Low-pass filter LFFC achieved J=0.4902

Combined PI and LFFC controller achieved J=0.6947

Abstract

The design and application of learning feedforward controllers (LFFC) for the one-staged refrigeration cycle model described in the PID2018 Benchmark Challenge is presented, and its effectiveness is evaluated. The control system consists of two components: 1) a preset PID component and 2) a learning feedforward component which is a function approximator that is adapted on the basis of the feedback signal. A B-spline network based LFFC and a low-pass filter based LFFC are designed to track the desired outlet temperature of evaporator secondary flux and the superheating degree of refrigerant at evaporator outlet. Encouraging simulation results are included. Qualitative and quantitative comparison results evaluations show that, with little effort, a high-performance control system can be obtained with this approach. Our initial simple attempt of low-pass filter based LFFC and B-spline network based LFFC give J=0.4902 and J=0.6536 relative to the decentralized PID controller, respectively. Besides, the initial attempt of a combination controller of our optimized PI controller and low-pass filter LFFC gives J=0.6947 relative to the multi-variable PID controller.