Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine
Condition monitoring of Internal Combustion Engines (ICE) benefits cost-effective operations in the modern industrial sector. Because of this, vibration signals are commonly monitored as part of a non-invasive approach to ICE analysis. However, vibration-based ICE monitoring poses a challenge due to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Instituto Tecnológico Metropolitano
2017-05-01
|
| Series: | TecnoLógicas |
| Subjects: | |
| Online Access: | http://itmojs.itm.edu.co/index.php/tecnologicas/article/view/1039/915 |
| _version_ | 1818305037780123648 |
|---|---|
| author | José Alberto Hernández-Muriel Andrés Marino Álvarez-Meza Julián David Echeverry-Correa Álvaro Ángel Orozco-Gutierrez Mauricio Alexánder Álvarez-López |
| author_facet | José Alberto Hernández-Muriel Andrés Marino Álvarez-Meza Julián David Echeverry-Correa Álvaro Ángel Orozco-Gutierrez Mauricio Alexánder Álvarez-López |
| author_sort | José Alberto Hernández-Muriel |
| collection | DOAJ |
| description | Condition monitoring of Internal Combustion Engines (ICE) benefits cost-effective operations in the modern industrial sector. Because of this, vibration signals are commonly monitored as part of a non-invasive approach to ICE analysis. However, vibration-based ICE monitoring poses a challenge due to the properties of this kind of signals. They are highly dynamic and non-stationary, let alone the diverse sources involved in the combustion process. In this paper, we propose a feature relevance estimation strategy for vibration-based ICE analysis. Our approach is divided into three main stages: signal decomposition using an Ensemble Empirical Mode Decomposition algorithm, multi-domain parameter estimation from time and frequency representations, and a supervised feature selection based on the Relief-F technique. Accordingly, we decomposed the vibration signals by using self-adaptive analysis to represent nonlinear and non-stationary time series. Afterwards, time and frequency-based parameters were calculated to code complex and/or non-stationary dynamics. Subsequently, we computed a relevance vector index to measure the contribution of each multi-domain feature to the discrimination of different fuel blend estimation/diagnosis categories for ICE. In particular, we worked with an ICE dataset collected from fuel blends under normal and fault scenarios at different engine speeds to test our approach. Our classification results presented nearly 98% of accuracy after using a k-Nearest Neighbors machine. They reveal the way our approach identifies a relevant subset of features for ICE condition monitoring. One of the benefits is the reduced number of parameters. |
| first_indexed | 2024-12-13T06:20:13Z |
| format | Article |
| id | doaj.art-fdabe4d2886b4b7b8a5ed15bf1b4eca1 |
| institution | Directory Open Access Journal |
| issn | 0123-7799 2256-5337 |
| language | English |
| last_indexed | 2024-12-13T06:20:13Z |
| publishDate | 2017-05-01 |
| publisher | Instituto Tecnológico Metropolitano |
| record_format | Article |
| series | TecnoLógicas |
| spelling | doaj.art-fdabe4d2886b4b7b8a5ed15bf1b4eca12022-12-21T23:56:51ZengInstituto Tecnológico MetropolitanoTecnoLógicas0123-77992256-53372017-05-012039Feature relevance estimation for vibration-based condition monitoring of an internal combustion engineJosé Alberto Hernández-Muriel0Andrés Marino Álvarez-Meza1Julián David Echeverry-Correa2Álvaro Ángel Orozco-Gutierrez3Mauricio Alexánder Álvarez-López4Universidad Tecnológica de PereiraUniversidad Tecnológica de PereiraUniversidad Tecnológica de PereiraUniversidad Tecnológica de PereiraUniversity of SheffieldCondition monitoring of Internal Combustion Engines (ICE) benefits cost-effective operations in the modern industrial sector. Because of this, vibration signals are commonly monitored as part of a non-invasive approach to ICE analysis. However, vibration-based ICE monitoring poses a challenge due to the properties of this kind of signals. They are highly dynamic and non-stationary, let alone the diverse sources involved in the combustion process. In this paper, we propose a feature relevance estimation strategy for vibration-based ICE analysis. Our approach is divided into three main stages: signal decomposition using an Ensemble Empirical Mode Decomposition algorithm, multi-domain parameter estimation from time and frequency representations, and a supervised feature selection based on the Relief-F technique. Accordingly, we decomposed the vibration signals by using self-adaptive analysis to represent nonlinear and non-stationary time series. Afterwards, time and frequency-based parameters were calculated to code complex and/or non-stationary dynamics. Subsequently, we computed a relevance vector index to measure the contribution of each multi-domain feature to the discrimination of different fuel blend estimation/diagnosis categories for ICE. In particular, we worked with an ICE dataset collected from fuel blends under normal and fault scenarios at different engine speeds to test our approach. Our classification results presented nearly 98% of accuracy after using a k-Nearest Neighbors machine. They reveal the way our approach identifies a relevant subset of features for ICE condition monitoring. One of the benefits is the reduced number of parameters.http://itmojs.itm.edu.co/index.php/tecnologicas/article/view/1039/915Internal combustion enginesvibration signalmulti-domain featuresrelevance analysisfeature selection |
| spellingShingle | José Alberto Hernández-Muriel Andrés Marino Álvarez-Meza Julián David Echeverry-Correa Álvaro Ángel Orozco-Gutierrez Mauricio Alexánder Álvarez-López Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine TecnoLógicas Internal combustion engines vibration signal multi-domain features relevance analysis feature selection |
| title | Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine |
| title_full | Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine |
| title_fullStr | Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine |
| title_full_unstemmed | Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine |
| title_short | Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine |
| title_sort | feature relevance estimation for vibration based condition monitoring of an internal combustion engine |
| topic | Internal combustion engines vibration signal multi-domain features relevance analysis feature selection |
| url | http://itmojs.itm.edu.co/index.php/tecnologicas/article/view/1039/915 |
| work_keys_str_mv | AT josealbertohernandezmuriel featurerelevanceestimationforvibrationbasedconditionmonitoringofaninternalcombustionengine AT andresmarinoalvarezmeza featurerelevanceestimationforvibrationbasedconditionmonitoringofaninternalcombustionengine AT juliandavidecheverrycorrea featurerelevanceestimationforvibrationbasedconditionmonitoringofaninternalcombustionengine AT alvaroangelorozcogutierrez featurerelevanceestimationforvibrationbasedconditionmonitoringofaninternalcombustionengine AT mauricioalexanderalvarezlopez featurerelevanceestimationforvibrationbasedconditionmonitoringofaninternalcombustionengine |