The identification of switched systems is a challenging problem, which entails both combinatorial (sample-mode assignment) and continuous (parameter estimation) features. A general framework for this problem has been recently developed, which alternates between parameter estimation and sample-mode assignment, solving both tasks to global optimality under mild conditions. This article extends this framework to the nonlinear case, which further aggravates the combinatorial complexity of the identification problem, since a model structure selection task has to be addressed for each mode of the system. To solve this issue, we reformulate the learning problem in terms of the optimization of a probability distribution over the space of all possible model structures. Then, a randomized approach is employed to tune this distribution. The performance of the proposed approach on some benchmark examples is analyzed in detail.

Model structure selection for switched NARX system identification: A randomized approach

Bianchi F.;Breschi V.;Piroddi L.
2021

Abstract

The identification of switched systems is a challenging problem, which entails both combinatorial (sample-mode assignment) and continuous (parameter estimation) features. A general framework for this problem has been recently developed, which alternates between parameter estimation and sample-mode assignment, solving both tasks to global optimality under mild conditions. This article extends this framework to the nonlinear case, which further aggravates the combinatorial complexity of the identification problem, since a model structure selection task has to be addressed for each mode of the system. To solve this issue, we reformulate the learning problem in terms of the optimization of a probability distribution over the space of all possible model structures. Then, a randomized approach is employed to tune this distribution. The performance of the proposed approach on some benchmark examples is analyzed in detail.
NARX systems
Randomized algorithms
Structure selection
Switched models
File in questo prodotto:
File Dimensione Formato  
SNARX_DP_v8.pdf

accesso aperto

Descrizione: Articolo principale (versione pre-referaggio)
: Pre-Print (o Pre-Refereeing)
Dimensione 809.81 kB
Formato Adobe PDF
809.81 kB Adobe PDF Visualizza/Apri
SNARX_F_v2.pdf

embargo fino al 30/12/2022

Descrizione: Articolo principale (versione post-referaggio)
: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 885.17 kB
Formato Adobe PDF
885.17 kB Adobe PDF   Visualizza/Apri
2021 - Automatica - BianchiBreschiPigaPiroddi.pdf

Accesso riservato

Descrizione: Articolo principale (versione dell'editore)
: Publisher’s version
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1166477
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact