Data-driven property verification of grey-box systems by Bayesian experiment design

S. Haesaert; P.M.J. Van den Hof; A. Abate

doi:10.1109/ACC.2015.7170994

Data-driven property verification of grey-box systems by Bayesian experiment design

S. Haesaert, P.M.J. Van den Hof, A. Abate

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

9 Citations (Scopus)

1 Downloads (Pure)

Abstract

A measurement-based statistical verification approach is developed for systems with partly unknown dynamics. These grey-box systems are subject to identification experiments which, new in this contribution, enable accepting or rejecting system properties expressed in a linear-time logic. We employ a Bayesian framework for the computation of a confidence level on the properties and for the design of optimal experiments. Applied to dynamical systems, this work enables data-driven verification of partly-known system dynamics with controllable non-determinism (inputs) and noisy output observations. A numerical case study concerning the safety of a dynamical system is used to elucidate this data-driven and model-based verification technique.

Original language	English
Title of host publication	Proceedings of the American Control Conference (ACC2015), 1-3 July 2015, Chicago, USA
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1800-1805
Number of pages	6
ISBN (Print)	978-1-4799-8684-2
DOIs	https://doi.org/10.1109/ACC.2015.7170994
Publication status	Published - 28 Jul 2015
Event	2015 American Control Conference, ACC 2015 - Hilton Palmer House, Chicago, United States Duration: 1 Jul 2015 → 3 Jul 2015 http://acc2015.a2c2.org/

Conference

Conference	2015 American Control Conference, ACC 2015
Abbreviated title	ACC 2015
Country/Territory	United States
City	Chicago
Period	1/07/15 → 3/07/15
Internet address	http://acc2015.a2c2.org/

Access to Document

10.1109/ACC.2015.7170994

Cite this

@inproceedings{c30f58d5bc2441978d250fde5bc3d6c4,

title = "Data-driven property verification of grey-box systems by Bayesian experiment design",

abstract = "A measurement-based statistical verification approach is developed for systems with partly unknown dynamics. These grey-box systems are subject to identification experiments which, new in this contribution, enable accepting or rejecting system properties expressed in a linear-time logic. We employ a Bayesian framework for the computation of a confidence level on the properties and for the design of optimal experiments. Applied to dynamical systems, this work enables data-driven verification of partly-known system dynamics with controllable non-determinism (inputs) and noisy output observations. A numerical case study concerning the safety of a dynamical system is used to elucidate this data-driven and model-based verification technique.",

author = "S. Haesaert and {Van den Hof}, P.M.J. and A. Abate",

year = "2015",

month = jul,

day = "28",

doi = "10.1109/ACC.2015.7170994",

language = "English",

isbn = "978-1-4799-8684-2",

pages = "1800--1805",

booktitle = "Proceedings of the American Control Conference (ACC2015), 1-3 July 2015, Chicago, USA",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2015 American Control Conference, ACC 2015, ACC 2015 ; Conference date: 01-07-2015 Through 03-07-2015",

url = "http://acc2015.a2c2.org/",

}

Haesaert, S , Van den Hof, PMJ & Abate, A 2015, Data-driven property verification of grey-box systems by Bayesian experiment design. in Proceedings of the American Control Conference (ACC2015), 1-3 July 2015, Chicago, USA., 7170994, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1800-1805, 2015 American Control Conference, ACC 2015, Chicago, Illinois, United States, 1/07/15. https://doi.org/10.1109/ACC.2015.7170994

Data-driven property verification of grey-box systems by Bayesian experiment design. / Haesaert, S.; Van den Hof, P.M.J.; Abate, A.
Proceedings of the American Control Conference (ACC2015), 1-3 July 2015, Chicago, USA. Piscataway: Institute of Electrical and Electronics Engineers, 2015. p. 1800-1805 7170994.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Data-driven property verification of grey-box systems by Bayesian experiment design

AU - Haesaert, S.

AU - Van den Hof, P.M.J.

AU - Abate, A.

PY - 2015/7/28

Y1 - 2015/7/28

N2 - A measurement-based statistical verification approach is developed for systems with partly unknown dynamics. These grey-box systems are subject to identification experiments which, new in this contribution, enable accepting or rejecting system properties expressed in a linear-time logic. We employ a Bayesian framework for the computation of a confidence level on the properties and for the design of optimal experiments. Applied to dynamical systems, this work enables data-driven verification of partly-known system dynamics with controllable non-determinism (inputs) and noisy output observations. A numerical case study concerning the safety of a dynamical system is used to elucidate this data-driven and model-based verification technique.

AB - A measurement-based statistical verification approach is developed for systems with partly unknown dynamics. These grey-box systems are subject to identification experiments which, new in this contribution, enable accepting or rejecting system properties expressed in a linear-time logic. We employ a Bayesian framework for the computation of a confidence level on the properties and for the design of optimal experiments. Applied to dynamical systems, this work enables data-driven verification of partly-known system dynamics with controllable non-determinism (inputs) and noisy output observations. A numerical case study concerning the safety of a dynamical system is used to elucidate this data-driven and model-based verification technique.

UR - http://www.scopus.com/inward/record.url?scp=84940922241&partnerID=8YFLogxK

U2 - 10.1109/ACC.2015.7170994

DO - 10.1109/ACC.2015.7170994

M3 - Conference contribution

AN - SCOPUS:84940922241

SN - 978-1-4799-8684-2

SP - 1800

EP - 1805

BT - Proceedings of the American Control Conference (ACC2015), 1-3 July 2015, Chicago, USA

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 2015 American Control Conference, ACC 2015

Y2 - 1 July 2015 through 3 July 2015

ER -

Data-driven property verification of grey-box systems by Bayesian experiment design

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this