Dynamic Bayesian Networks for Fault Prognosis

Ojas Pradhan; Jin Wen; Mengyuan Chu; Zheng O'Neill

doi:10.1145/3600100.3626268

Dynamic Bayesian Networks for Fault Prognosis

Ojas Pradhan
, Jin Wen
, Mengyuan Chu
, Zheng O'Neill

Architectural Engineering

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

2 Scopus citations

Abstract

A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.

Original language	English (US)
Title of host publication	BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
Publisher	Association for Computing Machinery, Inc
Pages	296-297
Number of pages	2
ISBN (Electronic)	9798400702303
DOIs	https://doi.org/10.1145/3600100.3626268
State	Published - Nov 15 2023
Event	10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023 - Istanbul, Turkey Duration: Nov 15 2023 → Nov 16 2023

Publication series

Name	BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Conference

Conference	10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023
Country/Territory	Turkey
City	Istanbul
Period	11/15/23 → 11/16/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Building and Construction
Architecture
Computer Networks and Communications
Information Systems
Renewable Energy, Sustainability and the Environment

Access to Document

10.1145/3600100.3626268

Cite this

Pradhan, O., Wen, J., Chu, M., & O'Neill, Z. (2023). Dynamic Bayesian Networks for Fault Prognosis. In BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (pp. 296-297). (BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation). Association for Computing Machinery, Inc. https://doi.org/10.1145/3600100.3626268

Pradhan, Ojas ; Wen, Jin ; Chu, Mengyuan et al. / Dynamic Bayesian Networks for Fault Prognosis. BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. Association for Computing Machinery, Inc, 2023. pp. 296-297 (BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation).

@inproceedings{8135925c0b854c1eb7ef7d431811efe6,

title = "Dynamic Bayesian Networks for Fault Prognosis",

abstract = "A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.",

author = "Ojas Pradhan and Jin Wen and Mengyuan Chu and Zheng O'Neill",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023 ; Conference date: 15-11-2023 Through 16-11-2023",

year = "2023",

month = nov,

day = "15",

doi = "10.1145/3600100.3626268",

language = "English (US)",

series = "BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation",

publisher = "Association for Computing Machinery, Inc",

pages = "296--297",

booktitle = "BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation",

}

Pradhan, O, Wen, J, Chu, M & O'Neill, Z 2023, Dynamic Bayesian Networks for Fault Prognosis. in BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, Association for Computing Machinery, Inc, pp. 296-297, 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023, Istanbul, Turkey, 11/15/23. https://doi.org/10.1145/3600100.3626268

Dynamic Bayesian Networks for Fault Prognosis. / Pradhan, Ojas; Wen, Jin; Chu, Mengyuan et al.
BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. Association for Computing Machinery, Inc, 2023. p. 296-297 (BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation).

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

TY - GEN

T1 - Dynamic Bayesian Networks for Fault Prognosis

AU - Pradhan, Ojas

AU - Wen, Jin

AU - Chu, Mengyuan

AU - O'Neill, Zheng

PY - 2023/11/15

Y1 - 2023/11/15

N2 - A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.

AB - A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.

UR - https://www.scopus.com/pages/publications/85179508399

UR - https://www.scopus.com/pages/publications/85179508399#tab=citedBy

U2 - 10.1145/3600100.3626268

DO - 10.1145/3600100.3626268

M3 - Conference contribution

AN - SCOPUS:85179508399

T3 - BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

SP - 296

EP - 297

BT - BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

PB - Association for Computing Machinery, Inc

T2 - 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023

Y2 - 15 November 2023 through 16 November 2023

ER -

Pradhan O, Wen J, Chu M, O'Neill Z. Dynamic Bayesian Networks for Fault Prognosis. In BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. Association for Computing Machinery, Inc. 2023. p. 296-297. (BuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation). doi: 10.1145/3600100.3626268

Dynamic Bayesian Networks for Fault Prognosis

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this