Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging

Predictive maintenance has become important for avoiding unplanned downtime of modern vehicles. With increasing functionality the exchanged data between Electronic Control Units (ECU) grows simultaneously rapidly. A large number of in-vehicle signals are provided for monitoring an aging process. Var...

Full description

Saved in:
Bibliographic Details
Main Authors: A. Udo Sass, E. Esatbeyoglu, T. Iwwerks
Format: Article
Language:Russian
Published: Belarusian National Technical University 2019-12-01
Series:Наука и техника
Subjects:
Online Access:https://sat.bntu.by/jour/article/view/2231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846145160160739328
author A. Udo Sass
E. Esatbeyoglu
T. Iwwerks
author_facet A. Udo Sass
E. Esatbeyoglu
T. Iwwerks
author_sort A. Udo Sass
collection DOAJ
description Predictive maintenance has become important for avoiding unplanned downtime of modern vehicles. With increasing functionality the exchanged data between Electronic Control Units (ECU) grows simultaneously rapidly. A large number of in-vehicle signals are provided for monitoring an aging process. Various components of a vehicle age due to their usage. This component aging is only visible in a certain number of in-vehicle signals. In this work, we present a signal selection method for in-vehicle signals in order to determine relevant signals to monitor and predict powertrain component aging of vehicles. Our application considers the aging of powertrain components with respect to clogging of structural components. We measure the component aging process in certain time intervals. Owing to this, unevenly spaced time series data is preprocessed to generate comparable in-vehicle data. First, we aggregate the data in certain intervals. Thus, the dynamic in-vehicle database is reduced which enables us to analyze the signals more efficiently. Secondly, we implement machine learning algorithms to generate a digital model of the measured aging process. With the help of Local Interpretable Model-Agnostic Explanations (LIME) the model gets interpretable. This allows us to extract the most relevant signals and to reduce the amount of processed data. Our results show that a certain number of in-vehicle signals are sufficient for predicting the aging process of the considered structural component. Consequently, our approach allows to reduce data transmission of in-vehicle signals with the goal of predictive maintenance.
format Article
id doaj-art-bfbefe78b22f4aca89484b076ec596a8
institution Kabale University
issn 2227-1031
2414-0392
language Russian
publishDate 2019-12-01
publisher Belarusian National Technical University
record_format Article
series Наука и техника
spelling doaj-art-bfbefe78b22f4aca89484b076ec596a82024-12-02T06:20:03ZrusBelarusian National Technical UniversityНаука и техника2227-10312414-03922019-12-0118651952410.21122/2227-1031-2019-18-6-519-5242000Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component AgingA. Udo Sass0E. Esatbeyoglu1T. Iwwerks2Volkswagen AGVolkswagen AGVolkswagen AGPredictive maintenance has become important for avoiding unplanned downtime of modern vehicles. With increasing functionality the exchanged data between Electronic Control Units (ECU) grows simultaneously rapidly. A large number of in-vehicle signals are provided for monitoring an aging process. Various components of a vehicle age due to their usage. This component aging is only visible in a certain number of in-vehicle signals. In this work, we present a signal selection method for in-vehicle signals in order to determine relevant signals to monitor and predict powertrain component aging of vehicles. Our application considers the aging of powertrain components with respect to clogging of structural components. We measure the component aging process in certain time intervals. Owing to this, unevenly spaced time series data is preprocessed to generate comparable in-vehicle data. First, we aggregate the data in certain intervals. Thus, the dynamic in-vehicle database is reduced which enables us to analyze the signals more efficiently. Secondly, we implement machine learning algorithms to generate a digital model of the measured aging process. With the help of Local Interpretable Model-Agnostic Explanations (LIME) the model gets interpretable. This allows us to extract the most relevant signals and to reduce the amount of processed data. Our results show that a certain number of in-vehicle signals are sufficient for predicting the aging process of the considered structural component. Consequently, our approach allows to reduce data transmission of in-vehicle signals with the goal of predictive maintenance.https://sat.bntu.by/jour/article/view/2231predictive maintenancefeature extractionsignal selectiontime seriesmachine learningmodel explanation
spellingShingle A. Udo Sass
E. Esatbeyoglu
T. Iwwerks
Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
Наука и техника
predictive maintenance
feature extraction
signal selection
time series
machine learning
model explanation
title Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
title_full Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
title_fullStr Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
title_full_unstemmed Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
title_short Signal Pre-Selection for Monitoring and Prediction of Vehicle Powertrain Component Aging
title_sort signal pre selection for monitoring and prediction of vehicle powertrain component aging
topic predictive maintenance
feature extraction
signal selection
time series
machine learning
model explanation
url https://sat.bntu.by/jour/article/view/2231
work_keys_str_mv AT audosass signalpreselectionformonitoringandpredictionofvehiclepowertraincomponentaging
AT eesatbeyoglu signalpreselectionformonitoringandpredictionofvehiclepowertraincomponentaging
AT tiwwerks signalpreselectionformonitoringandpredictionofvehiclepowertraincomponentaging