Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Learning-based Model Predictive Control Scheme with Application to Temperature Control Units

Jing Xie, Léo Simpson, Jonas Asprion, Riccardo Scattolini

TL;DR

This paper explores the use of Neural Nonlinear AutoRegressive eXogenous (NNARX) models for nonlinear system identification and model predictive control of a temperature control unit and illustrates that the proposed scheme achieves satisfactory tracking performance while incurring the lowest energy cost among the compared controllers.

Abstract

Temperature control is a complex task due to its often unknown dynamics and disturbances. This paper explores the use of Neural Nonlinear AutoRegressive eXogenous (NNARX) models for nonlinear system identification and model predictive control of a temperature control unit. First, the NNARX model is identified from input-output data collected from the real plant, and a state-space representation with known measurable states consisting of past input and output variables is formulated. Second, a tailored model predictive controller is designed based on the trained NNARX network. The proposed control architecture is experimentally tested on the temperature control units manufactured by Tool-Temp AG. The results achieved are compared with those obtained using a PI controller and a linear MPC. The findings illustrate that the proposed scheme achieves satisfactory tracking performance while incurring the lowest energy cost among the compared controllers.

A Learning-based Model Predictive Control Scheme with Application to Temperature Control Units

TL;DR

This paper explores the use of Neural Nonlinear AutoRegressive eXogenous (NNARX) models for nonlinear system identification and model predictive control of a temperature control unit and illustrates that the proposed scheme achieves satisfactory tracking performance while incurring the lowest energy cost among the compared controllers.

Abstract

Temperature control is a complex task due to its often unknown dynamics and disturbances. This paper explores the use of Neural Nonlinear AutoRegressive eXogenous (NNARX) models for nonlinear system identification and model predictive control of a temperature control unit. First, the NNARX model is identified from input-output data collected from the real plant, and a state-space representation with known measurable states consisting of past input and output variables is formulated. Second, a tailored model predictive controller is designed based on the trained NNARX network. The proposed control architecture is experimentally tested on the temperature control units manufactured by Tool-Temp AG. The results achieved are compared with those obtained using a PI controller and a linear MPC. The findings illustrate that the proposed scheme achieves satisfactory tracking performance while incurring the lowest energy cost among the compared controllers.
Paper Structure (14 sections, 18 equations, 11 figures, 1 table)

This paper contains 14 sections, 18 equations, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Problem Statement
  3. System Identification
  4. Data Collection using a PI controller
  5. Identification of a linear model
  6. Neural NARX models
  7. NNARX model training
  8. Control Scheme
  9. Cost design
  10. Reference generation for input and state
  11. State estimation
  12. Model Predictive Control
  13. Experimental Results
  14. Conclusion

Figures (11)

  • Figure 1: Temperature Control Unit manufactured by Tool-Temp AG
  • Figure 2: Overall system with TCU and external system
  • Figure 3: Analog input signal $u$ together with its digital conversion $\tilde{u}$.
  • Figure 4: System abstraction
  • Figure 5: Exemplary sample of the collected data
  • ...and 6 more figures