This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Machine-Learning-Based Fault Detection in Electric Vehicle Powertrains Using a Digital Twin
Technical Paper
2023-01-1214
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Electric Vehicles are subject to effects that lead to more or less rapid degradation of functions. This can cause hazards for the drivers and uninvolved road participants. For this reason, the must be detected and mitigated, to maintain the vehicle function even in critical situations until a safe operating mode can be established. This publication presents an intelligent digital twin, located in the edge and connected with an electric vehicle via 5G. That can improve the operation of electrified vehicles by enabling the online detection of abnormal situations in the electrified powertrain and vehicle dynamics. Its core component is the fault detection system, which is implemented based on a 1-Nearest Neighbor algorithm. It is initially trained on synthetic data, generated in CarMaker for real-world powertrain issues such as demagnetization and open-/short-switch failures, using detailed mathematical models. In this context 139 simulations were performed with three different velocities (10 km/h, 18 km/h and unlimited) in sum. Thereby 36 variables were recorded in each simulation. This leads to a total number of 953,534 data points. Out of this, 77 % are used for training and 23 % are used for validation. Based on the detected fault, a self-healing strategy is applied. Therefore, a look-up table, also located in the edge, is used to limit the motor torque to predefined levels. During the evaluation two major results are shown. The fault is well detected after a short detection time, but situations like accelerating or braking shows a similar signal behavior like the considered faults, leading to false positives. The effect of a fault can be mitigated by an online self-healing approach located in the edge in nearly real time. For connected vehicles, it seems realistic to apply an online digital twin enabling the fault detection and mitigation to the edge.
Authors
- Falk Dettinger - IAS - University of Stuttgart
- Nasser Jazdi - IAS - University of Stuttgart
- Michael Weyrich - IAS - University of Stuttgart
- Lukas Brandl - IFS - University of Stuttgart
- Hans-Christian Reuss - IFS - University of Stuttgart
- Urs Pecha - IEW - University of Stuttgart
- Nejila Parspour - IEW - University of Stuttgart
- Shiqing Li - FAST - Karlsruhe Institute of Technology
- Michael Frey - FAST - Karlsruhe Institute of Technology
- Frank Gauterin - FAST - Karlsruhe Institute of Technology
- Ann-Therese Nägele - ITIV - Karlsruhe Institute of Technology
- Vitus Alexander Lüntzel - ITIV - Karlsruhe Institute of Technology
- Eric Sax - ITIV - Karlsruhe Institute of Technology
Topic
Citation
Dettinger, F., Jazdi, N., Weyrich, M., Brandl, L. et al., "Machine-Learning-Based Fault Detection in Electric Vehicle Powertrains Using a Digital Twin," SAE Technical Paper 2023-01-1214, 2023, https://doi.org/10.4271/2023-01-1214.Also In
References
- Anselma , P. and Belingardi , G. Enhancing Energy Saving Opportunities through Rightsizing of a Battery Electric Vehicle Powertrain for Optimal Cooperative Driving SAE Intl. J CAV 3 2 2020 71 83 https://doi.org/10.4271/12-03-02-0007
- Bagnall , A. , Lines , J. , Bostrom , A. , Large , J. et al. The Great Time Series Classification Bake Off: A Review and Experimental Evaluation of Recent Algorithmic Advances Data Mining and Knowledge Discovery 31 3 2017 606 660 10.1007/s10618-016-0483-9
- BUP21 - Versuchsträger ‘eVee’ 2023 https://www.icmbw.de/forschung/projektuebersicht/detailseite/bup21
- Fawcett , T. An Introduction to ROC Analysis Pattern Recognition Letters 27 8 2006 861 874 10.1016/j.patrec.2005.10.010
- Grimm , D. , Weber , M. , and Sax , E. An Extended Hybrid Anomaly Detection System for Automotive Electronic Control Units Communicating via Ethernet - Efficient and Effective Analysis using a Specification- and Machine Learning-based Approach Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems Funchal, Madeira, Portugal 462 473 2018
- Jombo , G. and Zhang , Y. Fault Detection and Isolation in Electric Vehicle Powertrain Asef , P. , Sanjeevikumar , P. and Lapthorn , A. Modern Automotive Electrical Systems 10 Hoboken Wiley-Scrivener 2023 193 225
- Kliman , G.B. and Stein , J. Methods of Motor Current Signature Analysis Electric Machines & Power Systems 20 5 1992 463 474 10.1080/07313569208909609
- Liu , Z. , Zhang , W. , and Zhao , F. Impact, Challenges and Prospect of Software-Defined Vehicles Automot. Innov. 5 2 2022 180 194 10.1007/s42154-022-00179-z
- Löning , M. , Király , F. , Bagnall , T. , Middlehurst , M. et al. 2022
- Matsumori , H. , Kosaka , T. , Matsui , N. , and Saha , S. Inverter Power Device Fault Detection and Fail Safe Action Strategy for Electric Vehicle with a Dual Inverter fed Open Winding Motor IEEE Trans. on Ind. Applicat. 2023 1 15 10.1109/TIA.2023.3256386
- Narayanan , A. , Ramadan , E. , Carpenter , J. , Liu , Q. et al. A First Look at Commercial 5G Performance on Smartphones Huang , Y. , King , I. , Liu , T.-Y. , and van Steen , M. WWW ‘20: The Web Conference 2020 Taipei Taiwan 894 905 2020
- Nguyen , D.C. , Ding , M. , Pathirana , P.N. , Seneviratne , A. et al. Federated Learning for Internet of Things: A Comprehensive Survey IEEE Commun. Surv. Tutorials 23 3 2021 1622 1658 10.1109/COMST.2021.3075439
- Pech , M. , Vrchota , J. , and Bednář , J. Predictive Maintenance and Intelligent Sensors in Smart Factory: Review Sensors (Basel, Switzerland) 21 4 2021 10.3390/s21041470
- Ruiz , A.P. , Flynn , M. , Large , J. , Middlehurst , M. et al. The Great Multivariate Time Series Classification Bake Off: A Review and Experimental Evaluation of Recent Algorithmic Advances Data Mining and Knowledge Discovery 35 2 2021 401 449 10.1007/s10618-020-00727-3
- Russell , S. and Norvig , P. Artificial Intelligence: A Modern Approach 3rd Pearson 2010
- Sayed , K. , Kassem , A. , Saleeb , H. , Alghamdi , A.S. et al. Energy-Saving of Battery Electric Vehicle Powertrain and Efficiency Improvement during Different Standard Driving Cycles Sustainability 12 24 2020 10466 10.3390/su122410466
- Shen , T. Diagnosis of the Powertrain Systems for Autonomous Electric Vehicles Wiesbaden, Germany Springer (Research) 2022
- Tang , Q. , Shu , X. , Zhu , G. , Wang , J. et al. Reliability Study of BEV Powertrain System and Its Components—A Case Study Processes 9 5 2021 762 10.3390/pr9050762
- Thanh Le , T.T. and Moh , S. Comprehensive Survey of Radio Resource Allocation Schemes for 5G V2X Communications IEEE Access 9 2021 123117 123133 10.1109/ACCESS.2021.3109894
- Wang , P. , Lu , J. , Shi , L. , Zhang , Y. et al. Method for Extracting Current Envelope for Broken Rotor Bar Fault Detection of Induction Motors at Time-Varying Loads IET Electric Power Applications 14 6 2020 1067 1077 10.1049/iet-epa.2019.0779
- Wu , C. , Sehab , R. , Akrad , A. , and Morel , C. Fault Diagnosis Methods and Fault Tolerant Control Strategies for the Electric Vehicle Powertrains Energies 15 13 2022 4840 10.3390/en15134840
- Xie , G. , Wu , W. , Zeng , G. , Li , R. et al. Risk Assessment and Development Cost Optimization in Software Defined Vehicles IEEE Trans. Intell. Transport. Syst. 22 6 2021 3675 3686 10.1109/TITS.2020.3027469
- Yang , J. , Cheng , F. , Duodu , M. , Li , M. et al. High-Precision Fault Detection for Electric Vehicle Battery System Based on Bayesian Optimization SVDD Energies 15 22 2022 8331 10.3390/en15228331
- Zeller , M. , Grosse , S. , Eilers , D. , and Knorr , R. Fail-Safe Data Management in Self-Healing Automotive Systems Bauer , M.A. , Mauri , J.L. , Dini , O. ICAS 2010. Proceedings, the Sixth International Conference on Autonomic and Autonomous Systems Cancun, Mexico 2010 24 29
- Zhou , H. , Xu , W. , Chen , J. , and Wang , W. Evolutionary V2X Technologies Toward the Internet of Vehicles: Challenges and Opportunities Proc. IEEE 108 2 2020 308 323 10.1109/JPROC.2019.2961937
- Zhou , Z.-H. Ensemble Methods. Foundations and Algorithms. Online-ausg Boca Raton, FL Taylor & Francis (Chapman & Hall) 2012 http://site.ebrary.com/lib/alltitles/Doc?id=10574375