Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines
Condition monitoring of components in internal combustion engines is an essential tool for increasing engine durability and avoiding critical engine operation. If lubrication at the crankshaft main bearings is insufficient, metal-to-metal contacts become likely and thus wear can occur. Bearing tempe...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Lubricants |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4442/10/5/103 |
_version_ | 1797498411015995392 |
---|---|
author | Christian Laubichler Constantin Kiesling Matheus Marques da Silva Andreas Wimmer Gunther Hager |
author_facet | Christian Laubichler Constantin Kiesling Matheus Marques da Silva Andreas Wimmer Gunther Hager |
author_sort | Christian Laubichler |
collection | DOAJ |
description | Condition monitoring of components in internal combustion engines is an essential tool for increasing engine durability and avoiding critical engine operation. If lubrication at the crankshaft main bearings is insufficient, metal-to-metal contacts become likely and thus wear can occur. Bearing temperature measurements with thermocouples serve as a reliable, fast responding, individual bearing-oriented method that is comparatively simple to apply. In combination with a corresponding reference model, such measurements could serve to monitor the bearing condition. Based on experimental data from an MAN D2676 LF51 heavy-duty diesel engine, the derivation of a data-driven model for the crankshaft main bearing temperatures under steady-state engine operation is discussed. A total of 313 temperature measurements per bearing are available for this task. Readily accessible engine operating data that represent the corresponding engine operating points serve as model inputs. Different machine learning methods are thoroughly tested in terms of their prediction error with the help of a repeated nested cross-validation. The methods include different linear regression approaches (i.e., with and without lasso regularization), gradient boosting regression and support vector regression. As the results show, support vector regression is best suited for the problem. In the final evaluation on unseen test data, this method yields a prediction error of less than 0.4 °C (root mean squared error). Considering the temperature range from approximately 76 °C to 112 °C, the results demonstrate that it is possible to reliably predict the bearing temperatures with the chosen approach. Therefore, the combination of a data-driven bearing temperature model and thermocouple-based temperature measurements forms a powerful tool for monitoring the condition of sliding bearings in internal combustion engines. |
first_indexed | 2024-03-10T03:33:02Z |
format | Article |
id | doaj.art-a2214a61f2d04d2e8e358ac7ff89f512 |
institution | Directory Open Access Journal |
issn | 2075-4442 |
language | English |
last_indexed | 2024-03-10T03:33:02Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Lubricants |
spelling | doaj.art-a2214a61f2d04d2e8e358ac7ff89f5122023-11-23T11:51:41ZengMDPI AGLubricants2075-44422022-05-0110510310.3390/lubricants10050103Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion EnginesChristian Laubichler0Constantin Kiesling1Matheus Marques da Silva2Andreas Wimmer3Gunther Hager4Large Engines Competence Center GmbH, 8010 Graz, AustriaLarge Engines Competence Center GmbH, 8010 Graz, AustriaInstitute of Thermodynamics and Sustainable Propulsion Systems, Graz University of Technology, 8010 Graz, AustriaLarge Engines Competence Center GmbH, 8010 Graz, AustriaMiba Gleitlager Austria GmbH, 4663 Laakirchen, AustriaCondition monitoring of components in internal combustion engines is an essential tool for increasing engine durability and avoiding critical engine operation. If lubrication at the crankshaft main bearings is insufficient, metal-to-metal contacts become likely and thus wear can occur. Bearing temperature measurements with thermocouples serve as a reliable, fast responding, individual bearing-oriented method that is comparatively simple to apply. In combination with a corresponding reference model, such measurements could serve to monitor the bearing condition. Based on experimental data from an MAN D2676 LF51 heavy-duty diesel engine, the derivation of a data-driven model for the crankshaft main bearing temperatures under steady-state engine operation is discussed. A total of 313 temperature measurements per bearing are available for this task. Readily accessible engine operating data that represent the corresponding engine operating points serve as model inputs. Different machine learning methods are thoroughly tested in terms of their prediction error with the help of a repeated nested cross-validation. The methods include different linear regression approaches (i.e., with and without lasso regularization), gradient boosting regression and support vector regression. As the results show, support vector regression is best suited for the problem. In the final evaluation on unseen test data, this method yields a prediction error of less than 0.4 °C (root mean squared error). Considering the temperature range from approximately 76 °C to 112 °C, the results demonstrate that it is possible to reliably predict the bearing temperatures with the chosen approach. Therefore, the combination of a data-driven bearing temperature model and thermocouple-based temperature measurements forms a powerful tool for monitoring the condition of sliding bearings in internal combustion engines.https://www.mdpi.com/2075-4442/10/5/103internal combustion enginebearing temperaturebearing weartribologylubricationcondition monitoring |
spellingShingle | Christian Laubichler Constantin Kiesling Matheus Marques da Silva Andreas Wimmer Gunther Hager Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines Lubricants internal combustion engine bearing temperature bearing wear tribology lubrication condition monitoring |
title | Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines |
title_full | Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines |
title_fullStr | Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines |
title_full_unstemmed | Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines |
title_short | Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines |
title_sort | data driven sliding bearing temperature model for condition monitoring in internal combustion engines |
topic | internal combustion engine bearing temperature bearing wear tribology lubrication condition monitoring |
url | https://www.mdpi.com/2075-4442/10/5/103 |
work_keys_str_mv | AT christianlaubichler datadrivenslidingbearingtemperaturemodelforconditionmonitoringininternalcombustionengines AT constantinkiesling datadrivenslidingbearingtemperaturemodelforconditionmonitoringininternalcombustionengines AT matheusmarquesdasilva datadrivenslidingbearingtemperaturemodelforconditionmonitoringininternalcombustionengines AT andreaswimmer datadrivenslidingbearingtemperaturemodelforconditionmonitoringininternalcombustionengines AT guntherhager datadrivenslidingbearingtemperaturemodelforconditionmonitoringininternalcombustionengines |