Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting
An optimal control of the combustion process of an engine ensures lower emissions and fuel consumption plus high efficiencies. Combustion parameters such as the peak firing pressure (PFP) and the crank angle (CA) corresponding to 50% of mass fraction burned (MFB50) are essential for a closed-loop co...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/11/4235 |
| _version_ | 1797491606162505728 |
|---|---|
| author | Achilles Kefalas Andreas B. Ofner Gerhard Pirker Stefan Posch Bernhard C. Geiger Andreas Wimmer |
| author_facet | Achilles Kefalas Andreas B. Ofner Gerhard Pirker Stefan Posch Bernhard C. Geiger Andreas Wimmer |
| author_sort | Achilles Kefalas |
| collection | DOAJ |
| description | An optimal control of the combustion process of an engine ensures lower emissions and fuel consumption plus high efficiencies. Combustion parameters such as the peak firing pressure (PFP) and the crank angle (CA) corresponding to 50% of mass fraction burned (MFB50) are essential for a closed-loop control strategy. These parameters are based on the measured in-cylinder pressure that is typically gained by intrusive pressure sensors (PSs). These are costly and their durability is uncertain. To overcome these issues, the potential of using a virtual sensor based on the vibration signals acquired by a knock sensor (KS) for control of the combustion process is investigated. The present work introduces a data-driven approach where a signal-processing technique, designated as discrete wavelet transform (DWT), will be used as the preprocessing step for extracting informative features to perform regression tasks of the selected combustion parameters with extreme gradient boosting (XGBoost) regression models. The presented methodology will be applied to data from two different spark-ignited, single cylinder gas engines. Finally, an analysis is obtained where the important features based on the model’s decisions are identified. |
| first_indexed | 2024-03-10T00:50:47Z |
| format | Article |
| id | doaj.art-419cca9fc1ff4c7396655cfc9930d658 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:50:47Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-419cca9fc1ff4c7396655cfc9930d6582023-11-23T14:50:44ZengMDPI AGSensors1424-82202022-06-012211423510.3390/s22114235Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient BoostingAchilles Kefalas0Andreas B. Ofner1Gerhard Pirker2Stefan Posch3Bernhard C. Geiger4Andreas Wimmer5Institute of Thermodynamics and Sustainable Propulsion Systems, Graz University of Technology, 8010 Graz, AustriaKnow-Center GmbH, Research Center for Data-Driven Business & Big Data Analytics, 8010 Graz, AustriaLEC GmbH, Large Engine Competence Center, 8010 Graz, AustriaLEC GmbH, Large Engine Competence Center, 8010 Graz, AustriaKnow-Center GmbH, Research Center for Data-Driven Business & Big Data Analytics, 8010 Graz, AustriaInstitute of Thermodynamics and Sustainable Propulsion Systems, Graz University of Technology, 8010 Graz, AustriaAn optimal control of the combustion process of an engine ensures lower emissions and fuel consumption plus high efficiencies. Combustion parameters such as the peak firing pressure (PFP) and the crank angle (CA) corresponding to 50% of mass fraction burned (MFB50) are essential for a closed-loop control strategy. These parameters are based on the measured in-cylinder pressure that is typically gained by intrusive pressure sensors (PSs). These are costly and their durability is uncertain. To overcome these issues, the potential of using a virtual sensor based on the vibration signals acquired by a knock sensor (KS) for control of the combustion process is investigated. The present work introduces a data-driven approach where a signal-processing technique, designated as discrete wavelet transform (DWT), will be used as the preprocessing step for extracting informative features to perform regression tasks of the selected combustion parameters with extreme gradient boosting (XGBoost) regression models. The presented methodology will be applied to data from two different spark-ignited, single cylinder gas engines. Finally, an analysis is obtained where the important features based on the model’s decisions are identified.https://www.mdpi.com/1424-8220/22/11/4235knock sensorpressure sensorvirtual sensorengine vibrationscombustion parametersdiscrete wavelet transform |
| spellingShingle | Achilles Kefalas Andreas B. Ofner Gerhard Pirker Stefan Posch Bernhard C. Geiger Andreas Wimmer Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting Sensors knock sensor pressure sensor virtual sensor engine vibrations combustion parameters discrete wavelet transform |
| title | Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting |
| title_full | Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting |
| title_fullStr | Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting |
| title_full_unstemmed | Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting |
| title_short | Estimation of Combustion Parameters from Engine Vibrations Based on Discrete Wavelet Transform and Gradient Boosting |
| title_sort | estimation of combustion parameters from engine vibrations based on discrete wavelet transform and gradient boosting |
| topic | knock sensor pressure sensor virtual sensor engine vibrations combustion parameters discrete wavelet transform |
| url | https://www.mdpi.com/1424-8220/22/11/4235 |
| work_keys_str_mv | AT achilleskefalas estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting AT andreasbofner estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting AT gerhardpirker estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting AT stefanposch estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting AT bernhardcgeiger estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting AT andreaswimmer estimationofcombustionparametersfromenginevibrationsbasedondiscretewavelettransformandgradientboosting |