Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults
There are many challenges that an effective diagnostic system must overcome for successful fault diagnosis in gas turbines. Among others, it has to be robust to engine-to-engine variations in the fleet, it has to discriminate between gradual deterioration and abrupt faults, and it has to identify se...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Machines |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-1702/9/12/308 |
_version_ | 1797502823333625856 |
---|---|
author | Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis |
author_facet | Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis |
author_sort | Valentina Zaccaria |
collection | DOAJ |
description | There are many challenges that an effective diagnostic system must overcome for successful fault diagnosis in gas turbines. Among others, it has to be robust to engine-to-engine variations in the fleet, it has to discriminate between gradual deterioration and abrupt faults, and it has to identify sensor faults correctly and be robust in case of such faults. To combine their benefits and overcome their limitations, two diagnostic methods were integrated in this work to form a multi-layer system. An adaptive performance model was used to track gradual deterioration and detect rapid or abrupt anomalies, while a series of static and dynamic Bayesian networks were integrated to identify component degradation, component abrupt faults, and sensor faults. The proposed approach was tested on synthetic data and field data from a single-shaft gas turbine of 50 MW class. The results showed that the approach could give acceptable accuracy in the isolation and identification of multiple faults, with 99% detection and isolation accuracy and 1% maximum error in the identified fault magnitude. The approach was also proven robust to sensor faults, by replacing the faulty signal with an estimated value that had only 3% error compared to the real measurement. |
first_indexed | 2024-03-10T03:41:38Z |
format | Article |
id | doaj.art-096c3b83e57e46d78d61df7122135074 |
institution | Directory Open Access Journal |
issn | 2075-1702 |
language | English |
last_indexed | 2024-03-10T03:41:38Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Machines |
spelling | doaj.art-096c3b83e57e46d78d61df71221350742023-11-23T09:16:19ZengMDPI AGMachines2075-17022021-11-0191230810.3390/machines9120308Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid FaultsValentina Zaccaria0Amare Desalegn Fentaye1Konstantinos Kyprianidis2Future Energy Center, Mälardalen University, 721 23 Västerås, SwedenFuture Energy Center, Mälardalen University, 721 23 Västerås, SwedenFuture Energy Center, Mälardalen University, 721 23 Västerås, SwedenThere are many challenges that an effective diagnostic system must overcome for successful fault diagnosis in gas turbines. Among others, it has to be robust to engine-to-engine variations in the fleet, it has to discriminate between gradual deterioration and abrupt faults, and it has to identify sensor faults correctly and be robust in case of such faults. To combine their benefits and overcome their limitations, two diagnostic methods were integrated in this work to form a multi-layer system. An adaptive performance model was used to track gradual deterioration and detect rapid or abrupt anomalies, while a series of static and dynamic Bayesian networks were integrated to identify component degradation, component abrupt faults, and sensor faults. The proposed approach was tested on synthetic data and field data from a single-shaft gas turbine of 50 MW class. The results showed that the approach could give acceptable accuracy in the isolation and identification of multiple faults, with 99% detection and isolation accuracy and 1% maximum error in the identified fault magnitude. The approach was also proven robust to sensor faults, by replacing the faulty signal with an estimated value that had only 3% error compared to the real measurement.https://www.mdpi.com/2075-1702/9/12/308gas turbine diagnosticsBayesian networkhybrid models |
spellingShingle | Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults Machines gas turbine diagnostics Bayesian network hybrid models |
title | Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults |
title_full | Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults |
title_fullStr | Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults |
title_full_unstemmed | Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults |
title_short | Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults |
title_sort | assessment of dynamic bayesian models for gas turbine diagnostics part 2 discrimination of gradual degradation and rapid faults |
topic | gas turbine diagnostics Bayesian network hybrid models |
url | https://www.mdpi.com/2075-1702/9/12/308 |
work_keys_str_mv | AT valentinazaccaria assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart2discriminationofgradualdegradationandrapidfaults AT amaredesalegnfentaye assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart2discriminationofgradualdegradationandrapidfaults AT konstantinoskyprianidis assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart2discriminationofgradualdegradationandrapidfaults |