Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics

Lisandro Jimenez; Nicolae Rusnac; Matthias Volk; Mariëlle I.A. Stoelinga

doi:10.1007/978-3-031-68150-9_5

Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics

Lisandro Jimenez^*, Nicolae Rusnac, Matthias Volk, Mariëlle I.A. Stoelinga

^*Corresponding author for this work

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

Abstract

Abstract. In the domain of reliability engineering and risk assessment, the development of fault tree (FT) models is pivotal for decision-making
in complex systems. Traditional FT model development, relying on manual efforts and expert collaboration, is both time-consuming and error-prone. The era of Industry 4.0 introduces capabilities for automatically deriving FTs from inspection and monitoring data. This paper presents FT-MOEA-CM, an extension of the FT-MOEA algorithm for inferring FT models from failure data using multi-objective optimization. FT-MOEA-CM enhances its predecessor by integrating confusion matrix-derived metrics and incorporating parallelization and caching mechanisms. Our evaluation on six FTs from diverse application areas showcases that FT-MOEA-CM exhibits (1) enhanced robustness, (2) faster convergence and (3) better scalability than FT-MOEA, suggesting its potential in efficiently inferring larger FT models.

Original language	English
Title of host publication	Formal Methods for Industrial Critical Systems
Subtitle of host publication	29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings
Editors	Anne E. Haxthausen, Wendelin Serwe
Place of Publication	Milan
Publisher	Springer
Pages	80-96
Number of pages	17
ISBN (Electronic)	978-3-031-68150-9
ISBN (Print)	978-3-031-68149-3
DOIs	https://doi.org/10.1007/978-3-031-68150-9_5
Publication status	Published - 21 Aug 2024
Event	29th International Conference on Formal Methods for Industrial Critical Systems, FMICS 2024 - Milan, Italy Duration: 9 Sept 2024 → 11 Sept 2024 Conference number: 29 https://fmics.inria.fr/2024/

Conference

Conference	29th International Conference on Formal Methods for Industrial Critical Systems, FMICS 2024
Abbreviated title	FMICS 2024
Country/Territory	Italy
City	Milan
Period	9/09/24 → 11/09/24
Internet address	https://fmics.inria.fr/2024/

Keywords

2024 OA procedure
Multi-Objective Evolutionary Algorithm
Confusion Matrix
Model learning
Fault Tree Analysis

Access to Document

10.1007/978-3-031-68150-9_5

Embargoed Document

978-3-031-68150-9_5
Final published version, 2.79 MB
Licence: Taverne
Embargo ends: 21/02/25

Cite this

Jimenez, L., Rusnac, N., Volk, M., & Stoelinga, M. I. A. (2024). Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics. In A. E. Haxthausen, & W. Serwe (Eds.), Formal Methods for Industrial Critical Systems: 29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings (pp. 80-96). Springer. https://doi.org/10.1007/978-3-031-68150-9_5

Jimenez, Lisandro ; Rusnac, Nicolae ; Volk, Matthias et al. / Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics. Formal Methods for Industrial Critical Systems: 29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings. editor / Anne E. Haxthausen ; Wendelin Serwe. Milan : Springer, 2024. pp. 80-96

@inproceedings{6725f48a6cfc4485a52ae68fe8b07518,

title = "Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics",

abstract = "Abstract. In the domain of reliability engineering and risk assessment, the development of fault tree (FT) models is pivotal for decision-makingin complex systems. Traditional FT model development, relying on manual efforts and expert collaboration, is both time-consuming and error-prone. The era of Industry 4.0 introduces capabilities for automatically deriving FTs from inspection and monitoring data. This paper presents FT-MOEA-CM, an extension of the FT-MOEA algorithm for inferring FT models from failure data using multi-objective optimization. FT-MOEA-CM enhances its predecessor by integrating confusion matrix-derived metrics and incorporating parallelization and caching mechanisms. Our evaluation on six FTs from diverse application areas showcases that FT-MOEA-CM exhibits (1) enhanced robustness, (2) faster convergence and (3) better scalability than FT-MOEA, suggesting its potential in efficiently inferring larger FT models.",

keywords = "2024 OA procedure, Multi-Objective Evolutionary Algorithm, Confusion Matrix, Model learning, Fault Tree Analysis",

author = "Lisandro Jimenez and Nicolae Rusnac and Matthias Volk and Stoelinga, {Mari{\"e}lle I.A.}",

year = "2024",

month = aug,

day = "21",

doi = "10.1007/978-3-031-68150-9_5",

language = "English",

isbn = "978-3-031-68149-3",

pages = "80--96",

editor = "Haxthausen, {Anne E.} and Wendelin Serwe",

booktitle = "Formal Methods for Industrial Critical Systems",

publisher = "Springer",

address = "Germany",

note = "29th International Conference on Formal Methods for Industrial Critical Systems, FMICS 2024, FMICS 2024 ; Conference date: 09-09-2024 Through 11-09-2024",

url = "https://fmics.inria.fr/2024/",

}

Jimenez, L, Rusnac, N, Volk, M & Stoelinga, MIA 2024, Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics. in AE Haxthausen & W Serwe (eds), Formal Methods for Industrial Critical Systems: 29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings. Springer, Milan, pp. 80-96, 29th International Conference on Formal Methods for Industrial Critical Systems, FMICS 2024, Milan, Italy, 9/09/24. https://doi.org/10.1007/978-3-031-68150-9_5

Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics. / Jimenez, Lisandro; Rusnac, Nicolae; Volk, Matthias et al.
Formal Methods for Industrial Critical Systems: 29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings. ed. / Anne E. Haxthausen; Wendelin Serwe. Milan: Springer, 2024. p. 80-96.

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

TY - GEN

T1 - Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics

AU - Jimenez, Lisandro

AU - Rusnac, Nicolae

AU - Volk, Matthias

AU - Stoelinga, Mariëlle I.A.

N1 - Conference code: 29

PY - 2024/8/21

Y1 - 2024/8/21

N2 - Abstract. In the domain of reliability engineering and risk assessment, the development of fault tree (FT) models is pivotal for decision-makingin complex systems. Traditional FT model development, relying on manual efforts and expert collaboration, is both time-consuming and error-prone. The era of Industry 4.0 introduces capabilities for automatically deriving FTs from inspection and monitoring data. This paper presents FT-MOEA-CM, an extension of the FT-MOEA algorithm for inferring FT models from failure data using multi-objective optimization. FT-MOEA-CM enhances its predecessor by integrating confusion matrix-derived metrics and incorporating parallelization and caching mechanisms. Our evaluation on six FTs from diverse application areas showcases that FT-MOEA-CM exhibits (1) enhanced robustness, (2) faster convergence and (3) better scalability than FT-MOEA, suggesting its potential in efficiently inferring larger FT models.

AB - Abstract. In the domain of reliability engineering and risk assessment, the development of fault tree (FT) models is pivotal for decision-makingin complex systems. Traditional FT model development, relying on manual efforts and expert collaboration, is both time-consuming and error-prone. The era of Industry 4.0 introduces capabilities for automatically deriving FTs from inspection and monitoring data. This paper presents FT-MOEA-CM, an extension of the FT-MOEA algorithm for inferring FT models from failure data using multi-objective optimization. FT-MOEA-CM enhances its predecessor by integrating confusion matrix-derived metrics and incorporating parallelization and caching mechanisms. Our evaluation on six FTs from diverse application areas showcases that FT-MOEA-CM exhibits (1) enhanced robustness, (2) faster convergence and (3) better scalability than FT-MOEA, suggesting its potential in efficiently inferring larger FT models.

KW - 2024 OA procedure

KW - Multi-Objective Evolutionary Algorithm

KW - Confusion Matrix

KW - Model learning

KW - Fault Tree Analysis

U2 - 10.1007/978-3-031-68150-9_5

DO - 10.1007/978-3-031-68150-9_5

M3 - Conference contribution

SN - 978-3-031-68149-3

SP - 80

EP - 96

BT - Formal Methods for Industrial Critical Systems

A2 - Haxthausen, Anne E.

A2 - Serwe, Wendelin

PB - Springer

CY - Milan

T2 - 29th International Conference on Formal Methods for Industrial Critical Systems, FMICS 2024

Y2 - 9 September 2024 through 11 September 2024

ER -

Jimenez L, Rusnac N, Volk M, Stoelinga MIA. Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics. In Haxthausen AE, Serwe W, editors, Formal Methods for Industrial Critical Systems: 29th International Conference, FMICS 2024, Milan, Italy, September 9–11, 2024, Proceedings. Milan: Springer. 2024. p. 80-96 doi: 10.1007/978-3-031-68150-9_5

Fault Tree Inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based Metrics

Abstract

Conference

Keywords

Access to Document

Embargoed Document

Fingerprint

Cite this