A methodology for developing local smart diagnostic models using expert knowledge

Anders L. Madsen; Nicolaj Søndberg-Jeppesen; Niels Lohse; Mohamed S. Sayed

doi:10.1109/INDIN.2015.7281987

A methodology for developing local smart diagnostic models using expert knowledge

Anders L. Madsen, Nicolaj Søndberg-Jeppesen, Niels Lohse, Mohamed S. Sayed

Engineering and Physical Sciences

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

Abstract

This paper describes an innovative modular component-based modelling approach for diagnostics and condition-monitoring of manufacturing equipment. The approach is based on the use of object-oriented Bayesian networks, which supports a natural decomposition of a large and complex system into a set of less complex components. The methodology consists of six steps supporting the development process: Begin, Design, Implement, Test, Analyse, and Deploy. The process is iterative and the steps should be repeated until a satisfactory model has been achieved. The paper describes the details of the methodology as well as illustrates the use of the component-based modelling approach on a linear axis used in manufacturing. This application demonstrates the power and flexibility of the approach for diagnostics and condition-monitoring and shows a significant potential of the approach for modular component-based modelling in manufacturing and other domains.

Original language	English
Title of host publication	Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1682-1687
Number of pages	6
ISBN (Electronic)	9781479966493
DOIs	https://doi.org/10.1109/INDIN.2015.7281987
Publication status	Published - 28 Sept 2015
Event	13th International Conference on Industrial Informatics, INDIN 2015 - Cambridge, United Kingdom Duration: 22 Jul 2015 → 24 Jul 2015

Publication series

Name	Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015

Conference

Conference	13th International Conference on Industrial Informatics, INDIN 2015
Country/Territory	United Kingdom
City	Cambridge
Period	22/07/15 → 24/07/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

Analytical models
Bayes methods
Manufacturing systems
Object oriented modeling
Probabilistic logic
Sensitivity analysis

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Industrial and Manufacturing Engineering
Instrumentation
Computer Networks and Communications
Control and Systems Engineering

Access to Document

10.1109/INDIN.2015.7281987

Cite this

Madsen, A. L., Søndberg-Jeppesen, N., Lohse, N., & Sayed, M. S. (2015). A methodology for developing local smart diagnostic models using expert knowledge. In Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015 (pp. 1682-1687). Article 7281987 (Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/INDIN.2015.7281987

Madsen, Anders L. ; Søndberg-Jeppesen, Nicolaj ; Lohse, Niels et al. / A methodology for developing local smart diagnostic models using expert knowledge. Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 1682-1687 (Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015).

@inproceedings{f00bf63e6390429abfaa82fb80d647f0,

title = "A methodology for developing local smart diagnostic models using expert knowledge",

abstract = "This paper describes an innovative modular component-based modelling approach for diagnostics and condition-monitoring of manufacturing equipment. The approach is based on the use of object-oriented Bayesian networks, which supports a natural decomposition of a large and complex system into a set of less complex components. The methodology consists of six steps supporting the development process: Begin, Design, Implement, Test, Analyse, and Deploy. The process is iterative and the steps should be repeated until a satisfactory model has been achieved. The paper describes the details of the methodology as well as illustrates the use of the component-based modelling approach on a linear axis used in manufacturing. This application demonstrates the power and flexibility of the approach for diagnostics and condition-monitoring and shows a significant potential of the approach for modular component-based modelling in manufacturing and other domains.",

keywords = "Analytical models, Bayes methods, Manufacturing systems, Object oriented modeling, Probabilistic logic, Sensitivity analysis",

author = "Madsen, {Anders L.} and Nicolaj S{\o}ndberg-Jeppesen and Niels Lohse and Sayed, {Mohamed S.}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 13th International Conference on Industrial Informatics, INDIN 2015 ; Conference date: 22-07-2015 Through 24-07-2015",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/INDIN.2015.7281987",

language = "English",

series = "Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1682--1687",

booktitle = "Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015",

}

Madsen, AL, Søndberg-Jeppesen, N, Lohse, N & Sayed, MS 2015, A methodology for developing local smart diagnostic models using expert knowledge. in Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015., 7281987, Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015, Institute of Electrical and Electronics Engineers (IEEE), pp. 1682-1687, 13th International Conference on Industrial Informatics, INDIN 2015, Cambridge, United Kingdom, 22/07/15. https://doi.org/10.1109/INDIN.2015.7281987

A methodology for developing local smart diagnostic models using expert knowledge. / Madsen, Anders L.; Søndberg-Jeppesen, Nicolaj; Lohse, Niels et al.
Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1682-1687 7281987 (Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015).

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

TY - GEN

T1 - A methodology for developing local smart diagnostic models using expert knowledge

AU - Madsen, Anders L.

AU - Søndberg-Jeppesen, Nicolaj

AU - Lohse, Niels

AU - Sayed, Mohamed S.

PY - 2015/9/28

Y1 - 2015/9/28

N2 - This paper describes an innovative modular component-based modelling approach for diagnostics and condition-monitoring of manufacturing equipment. The approach is based on the use of object-oriented Bayesian networks, which supports a natural decomposition of a large and complex system into a set of less complex components. The methodology consists of six steps supporting the development process: Begin, Design, Implement, Test, Analyse, and Deploy. The process is iterative and the steps should be repeated until a satisfactory model has been achieved. The paper describes the details of the methodology as well as illustrates the use of the component-based modelling approach on a linear axis used in manufacturing. This application demonstrates the power and flexibility of the approach for diagnostics and condition-monitoring and shows a significant potential of the approach for modular component-based modelling in manufacturing and other domains.

AB - This paper describes an innovative modular component-based modelling approach for diagnostics and condition-monitoring of manufacturing equipment. The approach is based on the use of object-oriented Bayesian networks, which supports a natural decomposition of a large and complex system into a set of less complex components. The methodology consists of six steps supporting the development process: Begin, Design, Implement, Test, Analyse, and Deploy. The process is iterative and the steps should be repeated until a satisfactory model has been achieved. The paper describes the details of the methodology as well as illustrates the use of the component-based modelling approach on a linear axis used in manufacturing. This application demonstrates the power and flexibility of the approach for diagnostics and condition-monitoring and shows a significant potential of the approach for modular component-based modelling in manufacturing and other domains.

KW - Analytical models

KW - Bayes methods

KW - Manufacturing systems

KW - Object oriented modeling

KW - Probabilistic logic

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84949505176&partnerID=8YFLogxK

U2 - 10.1109/INDIN.2015.7281987

DO - 10.1109/INDIN.2015.7281987

M3 - Conference contribution

AN - SCOPUS:84949505176

T3 - Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015

SP - 1682

EP - 1687

BT - Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 13th International Conference on Industrial Informatics, INDIN 2015

Y2 - 22 July 2015 through 24 July 2015

ER -

Madsen AL, Søndberg-Jeppesen N, Lohse N, Sayed MS. A methodology for developing local smart diagnostic models using expert knowledge. In Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 1682-1687. 7281987. (Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015). doi: 10.1109/INDIN.2015.7281987

A methodology for developing local smart diagnostic models using expert knowledge

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this