Neural Network Training Using Closed-Loop Data: Hazards and an Instrumental Variable (IVNN) Solution

Johan Kon*, Marcel Heertjes, Tom Oomen

*Corresponding author for this work

Research output: Contribution to journalConference articleScientificpeer-review

102 Downloads (Pure)

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.

Original languageEnglish
Pages (from-to)182-187
JournalIFAC-PapersOnline
Volume55
Issue number12
DOIs
Publication statusPublished - 2022
Event14th IFAC Workshop on Adaptive and Learning Control Systems, ALCOS 2022 - Casablanca, Morocco
Duration: 29 Jun 20221 Jul 2022

Keywords

  • Feedforward control
  • instrumental variables
  • neural networks

Fingerprint

Dive into the research topics of 'Neural Network Training Using Closed-Loop Data: Hazards and an Instrumental Variable (IVNN) Solution'. Together they form a unique fingerprint.

Cite this