The End-of-Line (EoL) calibration of semi-active suspension systems for road vehicles is usually a critical and expensive task, needing a team of vehicle and control experts as well as many hours of professional driving. In this paper, we propose a purely data-based tuning method enabling the automatic calibration of the parameters of a proprietary suspension controller by relying on little experimental time and exploiting Bayesian Optimization tools. A detailed methodology on how to select the most critical degrees of freedom of the algorithm is also provided. The effectiveness of the proposed approach is assessed on a commercial multi-body simulator as well as on a real car.

Experimental automatic calibration of a semi-active suspension controller via Bayesian Optimization

Savaia G.;Sohn Y.;Formentin S.;Panzani G.;Corno M.;Savaresi S. M.
2021-01-01

Abstract

The End-of-Line (EoL) calibration of semi-active suspension systems for road vehicles is usually a critical and expensive task, needing a team of vehicle and control experts as well as many hours of professional driving. In this paper, we propose a purely data-based tuning method enabling the automatic calibration of the parameters of a proprietary suspension controller by relying on little experimental time and exploiting Bayesian Optimization tools. A detailed methodology on how to select the most critical degrees of freedom of the algorithm is also provided. The effectiveness of the proposed approach is assessed on a commercial multi-body simulator as well as on a real car.
2021
Bayesian Optimization
Calibration
Design of experiments
Semi-active suspensions
File in questo prodotto:
File Dimensione Formato  
[savaia] Experimental automatic calibration of a semi-active suspension controller via Bayesian Optimization.pdf

Accesso riservato

: Publisher’s version
Dimensione 2.73 MB
Formato Adobe PDF
2.73 MB Adobe PDF   Visualizza/Apri
11311-1208188_Corno.pdf

Open Access dal 02/07/2023

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 2.97 MB
Formato Adobe PDF
2.97 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/11311/1208188
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 9
social impact