Black box efficiency modelling of an electric drive unit utilizing methods of machine learning

• Autorzy: Bauer Lukas , Stütz Leon , Kley Markus

Identyfikatory

DOI

10.23743/acs-2021-25

• Języki publikacji: EN

Abstrakty

EN

The increasing electrification of powertrains leads to increased demands for the test technology to ensure the required functions. For conventional test rigs in particular, it is necessary to have knowledge of the test technology's capabilities that can be applied in practical testing. Modelling enables early knowledge of the test rigs dynamic capabilities and the feasibility of planned testing scenarios. This paper describes the modelling of complex subsystems by experimental modelling with artificial neural networks taking transmission efficiency as an example. For data generation, the experimental design and execution is described. The generated data is pre-processed with suitable methods and optimized for the neural networks. Modelling is executed with different variants of the inputs as well as different algorithms. The variants compare and compete with each other. The most suitable variant is validated using statistical methods and other adequate techniques. The result represents reality well and enables the performance investigation of the test systems in a realistic manner.

Słowa kluczowe

EN

electromobility; powertrain; electric drives; artificial neural network; efficiency modelling

PL

elektromobilność; układ napędowy; napędy elektryczne; sztuczna sieć neuronowa; modelowanie wydajności

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2021
• Tom: Vol. 17, no 4
• Strony: 5--19
• Opis fizyczny: Bibliogr. 24 poz., fig., tab.

Twórcy

autor

Bauer Lukas

• Aalen University, Institute for Drive Technology, Beethovenstraße 1, 73430 Aalen, Germany

• https://orcid.org/0000-0002-1641-0376

autor

Stütz Leon

• Aalen University, Institute for Drive Technology, Beethovenstraße 1, 73430 Aalen, Germany

• https://orcid.org/0000-0002-4754-3251

autor

Kley Markus

• Aalen University, Institute for Drive Technology, Beethovenstraße 1, 73430 Aalen, Germany

• https://orcid.org/0000-0003-4061-0797

Bibliografia

• [1] Albers, A., Behrendt, M., Klingler, S., & Matros, K. (2016). Verifikation und Validierung im Produktent-stehungsprozess [E-Book]. In M. Behrendt, S. Klingler & K. Matros (Eds.), Handbuch Produktentwicklung (pp. 541–557). Carl Hanser Verlag. https://doi.org/10.3139/9783446445819.019
• [2] Bauer, L., Bauer, M., & Kley, M. (2021). Modelbasierte Validierung der Prüfstandsdynamik zur Erprobung von Komponenten elektrifizierter Antriebsstränge mithilfe eines digitalen Zwillings. Stuttgarter Symposium für Produktentwicklung, SSP 2021, 105–116. https://doi.org/10.18419/opus-11478
• [3] Bauer, L., Beck, P., Stütz, L., & Kley, M. (2021). Enhanced efficiency prediction of an electrified off-highway vehicle transmission utilizing machine learning methods. Procedia Computer Science, 192, 417–426. https://doi.org/10.1016/j.procs.2021.08.043
• [4] Beine, M., & Rasche, R. (2018). Datenmanagement für das szenariobasierte Testen. ATZextra, 23(S4), 20–25. https://doi.org/10.1007/s35778-018-0024-9
• [5] ÇElik, E., Gör, H., ÖZtürk, N., & Kurt, E. (2017). Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator. International Journal of Hydrogen Energy, 42(28), 17692–17699. https://doi.org/10.1016/j.ijhydene.2017.01.168
• [6] Dismon, H. (2017). Wir sind gefordert, Entwicklungen schnell und treffsicher umzusetzen. MTZextra, 22(S1), 8–11. https://doi.org/10.1007/s41490-017-0009-4
• [7] Dohmen, H., Pfeiffer, K., & Schyr, C. (2009). Antriebsstrangprüftechnik: Vom stationären Komponententest zum fahrmanöverbasierten Testen (Die Bibliothek der Technik (BT)) (1. Aufl.). Süddeutscher Verlag onpact.
• [8] German Environment Agency. (2020). Submission under the United Nations Framework Convention on Climate Change and the Kyoto Protocol 2020.
• [9] Guggenmos, J., Rückert, J., Thalmair, S., & Wagner, M. (2018). Das Prüffeld der Antriebsentwicklung im Wandel. VPC – Simulation und Test 2015 (pp. 1–13). Springer. https://doi.org/10.1007/978-3-658-20736-6_1
• [10] Hoekstra, A. (2019). The Underestimated Potential of Battery Electric Vehicles to Reduce Emissions. Joule, 3(6), 1412–1414. https://doi.org/10.1016/j.joule.2019.06.002
• [11] Isermann, R. (2007). Mechatronische Systeme. Springer.
• [12] Jazayeri, K., Jazayeri, M., & Uysal, S. (2016). Comparative Analysis of Levenberg-Marquardt and Bayesian Regularization Backpropagation Algorithms in Photovoltaic Power Estimation Using Artificial Neural Network. Advances in Data Mining. Applications and Theoretical Aspects (pp. 80–95). Springer. https://doi.org/10.1007/978-3-319-41561-1_7
• [13] Khan, A., Mohammadi, M. H., Ghorbanian, V., & Lowther, D. (2020). Efficiency Map Prediction of Motor Drives Using Deep Learning. IEEE Transactions on Magnetics, 56(3), 1–4. https://doi.org/10.1109/tmag.2019.2957162
• [14] Li, Y. L., Kley, M., & Wang, S. J. (2014). Driveline Simulation of 2013 Formula Student Electric Racing Vehicle. Applied Mechanics and Materials, 541–542, 424–429. https://doi.org/10.4028/www.scientific.net/ amm.541-542.424
• [15] Machrowska, A., Karpiński, R., Jonak, J., & Krakowski, P. (2020). Numericalprediction of the component-ratio-dependent compressive strength of bone cement. Applied Computer Science, 16(3), 88–101. https://doi.org/10.23743/acs-2020-24
• [16] Martini, E., Voß, H., Töpfer, S., & Isermann, R. (2003). Effiziente Motorapplikation mit lokal linearen neuronalen Netzen. MTZ - Motortechnische Zeitschrift, 64(5), 406–413. https://doi.org/10.1007/bf03226705
• [17] Paulweber, M., & Lebert, K. (2014). Mess- und Prüfstandstechnik: Antriebsstrangentwicklung Hybridisierung Elektrifizierung (Der Fahrzeugantrieb) (2014. Aufl.). Springer. https://doi.org/10.1007/978-3-658-04453-4
• [18] Payal, A., Rai, C. S., & Reddy, B. V. R. (2013). Comparative analysis of Bayesian regularization and Levenberg-Marquardt training algorithm for localization in wireless sensor network. 15th International Conference on Advanced Communications Technology (ICACT) (pp. 191–194). IEEE. https://ieeexplore.ieee.org/document/6488169
• [19] Ratov, D., & Lyfar, V. (2020). Modeling transmission mechanisms with determination of efficiency. Applied Computer Science, 16(1), 33–40. https://doi.org/10.23743/acs-2020-03
• [20] Stütz, J., Bauer, L., & Kley, M. (2019). Intelligente Lastkollektivoptimierung für Erprobungen von elektrischen und hybriden Antriebssträngen. Stuttgarter Symposium für Produktentwicklung SSP 2019 (pp. 93–102). Fraunhofer-Institut für Arbeitswirtschaft und Organisation IAO. https://doi.org/10.18419/opus-10394
• [21] Stütz, L., Beck, P., & Kley, M. (2021). Wirkungsgraduntersuchungen am Antriebsstrang von Multifunktionsfahrzeugen unter Berücksichtigung von empirisch ermittelten Lastkollektiven. Stuttgarter Symposium für Produktentwicklung SSP 2021 (pp. 445–454). Fraunhofer-Institut für Arbeitswirtschaft und Organisation IAO. https://doi.org/10.18419/opus-11478
• [22] The MathWorks. (2020). Statistics and Machine Learning Toolbox User’s Guide. The MathWorks.
• [23] Willmerding, G., & Häckh, J. (2017). Echtzeitsimulation hochdynamischer Fahrzeugantriebe. ASIM-Treffen STS/GMMS 2017 (pp. 192–198). Ulm.
• [24] Yadav, R. N., & Yadava, V. (2017). Artificial neural network modelling of erosion-abrasion-based hybrid machining of aluminium-silicon carbide-boron carbide composite. International Journal of Engineering Systems Modelling and Simulation, 9(2), 63–77. https://doi.org/10.1504/ijesms.2017.083223

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).