Fault Diagnosis Strategies for SOFC-Based Power Generation Plants
The success of distributed power generation by plants based on solid oxide fuel cells (SOFCs) is hindered by reliability problems that can be mitigated through an effective fault detection and isolation (FDI) system. However, the numerous operating conditions under which such plants can operate and...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/8/1336 |
| _version_ | 1811187273420505088 |
|---|---|
| author | Paola Costamagna Andrea De Giorgi Alberto Gotelli Loredana Magistri Gabriele Moser Emanuele Sciaccaluga Andrea Trucco |
| author_facet | Paola Costamagna Andrea De Giorgi Alberto Gotelli Loredana Magistri Gabriele Moser Emanuele Sciaccaluga Andrea Trucco |
| author_sort | Paola Costamagna |
| collection | DOAJ |
| description | The success of distributed power generation by plants based on solid oxide fuel cells (SOFCs) is hindered by reliability problems that can be mitigated through an effective fault detection and isolation (FDI) system. However, the numerous operating conditions under which such plants can operate and the random size of the possible faults make identifying damaged plant components starting from the physical variables measured in the plant very difficult. In this context, we assess two classical FDI strategies (model-based with fault signature matrix and data-driven with statistical classification) and the combination of them. For this assessment, a quantitative model of the SOFC-based plant, which is able to simulate regular and faulty conditions, is used. Moreover, a hybrid approach based on the random forest (RF) classification method is introduced to address the discrimination of regular and faulty situations due to its practical advantages. Working with a common dataset, the FDI performances obtained using the aforementioned strategies, with different sets of monitored variables, are observed and compared. We conclude that the hybrid FDI strategy, realized by combining a model-based scheme with a statistical classifier, outperforms the other strategies. In addition, the inclusion of two physical variables that should be measured inside the SOFCs can significantly improve the FDI performance, despite the actual difficulty in performing such measurements. |
| first_indexed | 2024-04-11T13:59:28Z |
| format | Article |
| id | doaj.art-913b16bdbe194d139a446eef860a11c6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:59:28Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-913b16bdbe194d139a446eef860a11c62022-12-22T04:20:09ZengMDPI AGSensors1424-82202016-08-01168133610.3390/s16081336s16081336Fault Diagnosis Strategies for SOFC-Based Power Generation PlantsPaola Costamagna0Andrea De Giorgi1Alberto Gotelli2Loredana Magistri3Gabriele Moser4Emanuele Sciaccaluga5Andrea Trucco6Department of Civil, Chemical and Environmental Engineering (DICCA), University of Genoa, Genova 16145, ItalyDepartment of Electrical, Electronic, Telecommunications Engineering, and Naval Architecture (DITEN), University of Genoa, Genova 16145, ItalyDepartment of Electrical, Electronic, Telecommunications Engineering, and Naval Architecture (DITEN), University of Genoa, Genova 16145, ItalyDepartment of Mechanics, Energetics, Management, and Transportation (DIME), University of Genoa, Genova 16145, ItalyDepartment of Electrical, Electronic, Telecommunications Engineering, and Naval Architecture (DITEN), University of Genoa, Genova 16145, ItalyDepartment of Electrical, Electronic, Telecommunications Engineering, and Naval Architecture (DITEN), University of Genoa, Genova 16145, ItalyDepartment of Electrical, Electronic, Telecommunications Engineering, and Naval Architecture (DITEN), University of Genoa, Genova 16145, ItalyThe success of distributed power generation by plants based on solid oxide fuel cells (SOFCs) is hindered by reliability problems that can be mitigated through an effective fault detection and isolation (FDI) system. However, the numerous operating conditions under which such plants can operate and the random size of the possible faults make identifying damaged plant components starting from the physical variables measured in the plant very difficult. In this context, we assess two classical FDI strategies (model-based with fault signature matrix and data-driven with statistical classification) and the combination of them. For this assessment, a quantitative model of the SOFC-based plant, which is able to simulate regular and faulty conditions, is used. Moreover, a hybrid approach based on the random forest (RF) classification method is introduced to address the discrimination of regular and faulty situations due to its practical advantages. Working with a common dataset, the FDI performances obtained using the aforementioned strategies, with different sets of monitored variables, are observed and compared. We conclude that the hybrid FDI strategy, realized by combining a model-based scheme with a statistical classifier, outperforms the other strategies. In addition, the inclusion of two physical variables that should be measured inside the SOFCs can significantly improve the FDI performance, despite the actual difficulty in performing such measurements.http://www.mdpi.com/1424-8220/16/8/1336solid oxide fuel cell (SOFC)quantitative modellingfault detection and isolation (FDI)model-based and data-driven strategiespattern recognitionrandom forest (RF) |
| spellingShingle | Paola Costamagna Andrea De Giorgi Alberto Gotelli Loredana Magistri Gabriele Moser Emanuele Sciaccaluga Andrea Trucco Fault Diagnosis Strategies for SOFC-Based Power Generation Plants Sensors solid oxide fuel cell (SOFC) quantitative modelling fault detection and isolation (FDI) model-based and data-driven strategies pattern recognition random forest (RF) |
| title | Fault Diagnosis Strategies for SOFC-Based Power Generation Plants |
| title_full | Fault Diagnosis Strategies for SOFC-Based Power Generation Plants |
| title_fullStr | Fault Diagnosis Strategies for SOFC-Based Power Generation Plants |
| title_full_unstemmed | Fault Diagnosis Strategies for SOFC-Based Power Generation Plants |
| title_short | Fault Diagnosis Strategies for SOFC-Based Power Generation Plants |
| title_sort | fault diagnosis strategies for sofc based power generation plants |
| topic | solid oxide fuel cell (SOFC) quantitative modelling fault detection and isolation (FDI) model-based and data-driven strategies pattern recognition random forest (RF) |
| url | http://www.mdpi.com/1424-8220/16/8/1336 |
| work_keys_str_mv | AT paolacostamagna faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT andreadegiorgi faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT albertogotelli faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT loredanamagistri faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT gabrielemoser faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT emanuelesciaccaluga faultdiagnosisstrategiesforsofcbasedpowergenerationplants AT andreatrucco faultdiagnosisstrategiesforsofcbasedpowergenerationplants |