Neural Network Training Using Closed-Loop Data

Hazards and an Instrumental Variable (IVNN) Solution

Journal article (2022)

Authors

Johan Kon Eindhoven University of Technology
Marcel Heertjes ASML, Eindhoven University of Technology
Tom Oomen Team Jan-Willem van Wingerden - Mechanical, Maritime and Materials Engineering , Eindhoven University of Technology
T.A.E. Oomen Team Jan-Willem van Wingerden - Mechanical, Maritime and Materials Engineering , Eindhoven University of Technology
Research Group
Team Jan-Willem van Wingerden (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2022 Johan Kon, Marcel Heertjes, T.A.E. Oomen
DOI: https://doi.org/10.1016/j.ifacol.2022.07.308
More Info
expand_more

Published Date

2022

Language

English

Faculty

Mechanical, Maritime and Materials Engineering

Department

Delft Center for Systems and Control

Research Group

Team Jan-Willem van Wingerden

Abstract

An increasing trend in the use of neural networks in control systems is being observed. The aim of this paper is to reveal that the straightforward application of learning neural network feedforward controllers with closed-loop data may introduce parameter inconsistency that degrades control performance, and to provide a solution. The proposed method employs instrumental variables to ensure consistent parameter estimates. A nonlinear system example reveals that the developed instrumental variable neural network (IVNN) approach asymptotically recovers the optimal solution, while pre-existing approaches are shown to lead to inconsistent estimates.