System of systems hazard analysis using simulation and machine learning

Robert Alexander; Dimitar Kazakov; Tim Kelly

doi:10.1007/11875567_1

System of systems hazard analysis using simulation and machine learning

Robert Alexander, Dimitar Kazakov, Tim Kelly

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In the operation of safety-critical systems, the sequences by which failures can lead to accidents can be many and complex. This is particularly true for the emerging class of systems known as systems of systems, as they are composed of many distributed, heterogenous and autonomous components. Performing hazard analysis on such systems is challenging, in part because it is difficult to know in advance which of the many observable or measurable features of the system are important for maintaining system safety. Hence there is a need for effective techniques to find causal relationships within these systems. This paper explores the use of machine learning techniques to extract potential causal relationships from simulation models. This is illustrated with a case study of a military system of systems.

Original language	English
Title of host publication	COMPUTER SAFETY, RELIABILITY, AND SECURITY, PROCEEDINGS
Subtitle of host publication	25th Annual Conference, SAFECOMP 2006
Editors	J Gorski
Place of Publication	BERLIN
Publisher	Springer
Pages	1-14
Number of pages	14
ISBN (Print)	3-540-45762-3
DOIs	https://doi.org/10.1007/11875567_1
Publication status	Published - 2006
Event	25th International Conference, SAFECOMP 2006 - Gdansk, Poland Duration: 27 Sept 2006 → 29 Sept 2006

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	4166

Conference

Conference	25th International Conference, SAFECOMP 2006
Country/Territory	Poland
City	Gdansk
Period	27/09/06 → 29/09/06

Access to Document

10.1007/11875567_1

http://dx.doi.org/10.1007/11875567_1

Cite this

@inproceedings{1cd7d94ff8dd45b8821fa75977ba20df,

title = "System of systems hazard analysis using simulation and machine learning",

abstract = "In the operation of safety-critical systems, the sequences by which failures can lead to accidents can be many and complex. This is particularly true for the emerging class of systems known as systems of systems, as they are composed of many distributed, heterogenous and autonomous components. Performing hazard analysis on such systems is challenging, in part because it is difficult to know in advance which of the many observable or measurable features of the system are important for maintaining system safety. Hence there is a need for effective techniques to find causal relationships within these systems. This paper explores the use of machine learning techniques to extract potential causal relationships from simulation models. This is illustrated with a case study of a military system of systems.",

author = "Robert Alexander and Dimitar Kazakov and Tim Kelly",

year = "2006",

doi = "10.1007/11875567_1",

language = "English",

isbn = "3-540-45762-3",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "1--14",

editor = "J Gorski",

booktitle = "COMPUTER SAFETY, RELIABILITY, AND SECURITY, PROCEEDINGS",

address = "Germany",

note = "25th International Conference, SAFECOMP 2006 ; Conference date: 27-09-2006 Through 29-09-2006",

}

Alexander, R , Kazakov, D & Kelly, T 2006, System of systems hazard analysis using simulation and machine learning. in J Gorski (ed.), COMPUTER SAFETY, RELIABILITY, AND SECURITY, PROCEEDINGS: 25th Annual Conference, SAFECOMP 2006. Lecture Notes in Computer Science, vol. 4166, Springer, BERLIN, pp. 1-14, 25th International Conference, SAFECOMP 2006, Gdansk, Poland, 27/09/06. https://doi.org/10.1007/11875567_1

System of systems hazard analysis using simulation and machine learning. / Alexander, Robert ; Kazakov, Dimitar ; Kelly, Tim.
COMPUTER SAFETY, RELIABILITY, AND SECURITY, PROCEEDINGS: 25th Annual Conference, SAFECOMP 2006. ed. / J Gorski. BERLIN: Springer, 2006. p. 1-14 (Lecture Notes in Computer Science; Vol. 4166).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - System of systems hazard analysis using simulation and machine learning

AU - Alexander, Robert

AU - Kazakov, Dimitar

AU - Kelly, Tim

PY - 2006

Y1 - 2006

N2 - In the operation of safety-critical systems, the sequences by which failures can lead to accidents can be many and complex. This is particularly true for the emerging class of systems known as systems of systems, as they are composed of many distributed, heterogenous and autonomous components. Performing hazard analysis on such systems is challenging, in part because it is difficult to know in advance which of the many observable or measurable features of the system are important for maintaining system safety. Hence there is a need for effective techniques to find causal relationships within these systems. This paper explores the use of machine learning techniques to extract potential causal relationships from simulation models. This is illustrated with a case study of a military system of systems.

AB - In the operation of safety-critical systems, the sequences by which failures can lead to accidents can be many and complex. This is particularly true for the emerging class of systems known as systems of systems, as they are composed of many distributed, heterogenous and autonomous components. Performing hazard analysis on such systems is challenging, in part because it is difficult to know in advance which of the many observable or measurable features of the system are important for maintaining system safety. Hence there is a need for effective techniques to find causal relationships within these systems. This paper explores the use of machine learning techniques to extract potential causal relationships from simulation models. This is illustrated with a case study of a military system of systems.

U2 - 10.1007/11875567_1

DO - 10.1007/11875567_1

M3 - Conference contribution

SN - 3-540-45762-3

T3 - Lecture Notes in Computer Science

SP - 1

EP - 14

BT - COMPUTER SAFETY, RELIABILITY, AND SECURITY, PROCEEDINGS

A2 - Gorski, J

PB - Springer

CY - BERLIN

T2 - 25th International Conference, SAFECOMP 2006

Y2 - 27 September 2006 through 29 September 2006

ER -