Skip to main content

2022 | OriginalPaper | Buchkapitel

Intelligent Data Analytics with Artificial Intelligence for Hybrid Engine Restart

verfasst von : Florian Schuchter, Katharina Bause, Albert Albers

Erschienen in: 22. Internationales Stuttgarter Symposium

Verlag: Springer Fachmedien Wiesbaden

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The electrification of the powertrain results in complex functions, such as the engine restart in hybrid vehicles. At the same time, large amounts of data are generated in the development process that are only used to a limited extent. An experience-based and less systematic procedure for the manual evaluation of individual measurements or an elaborate statistical evaluation of data often produce little knowledge in the development process of transmission functions. However, in the course of digitalization data must be used efficiently and intelligently.
The authors present a method that uses artificial intelligence to analyze large amounts of data automatically and efficiently to identify similarities and differences. The DBSCAN cluster algorithm is an important part of this method.
The method analyzes vehicle data of a hybrid vehicle engine restart. About 300 engine restarts are detected from vehicle measurements, twelve key performance indicators per start are evaluated and commonalities are identified with the help of the cluster algorithm. The evaluation results can be used to define important operating points for an engine restart and evaluate the engine restart strategy. This method supports the development engineer to get a better understanding of the system and gain new knowledge about the transmission functions from data.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Kistner, B., Sanzenbacher, S., Munier, J., Fietkau, P.: Die digitale Antriebsentwicklung der Zukunft: ganzheitlich, systematisch und kundenzentriert. In: Liebl, J (ed.) Experten-Forum Powertrain: Simulation und Test 2019, S. 1–14. Springer Vieweg, Wiesbaden (2019) Kistner, B., Sanzenbacher, S., Munier, J., Fietkau, P.: Die digitale Antriebsentwicklung der Zukunft: ganzheitlich, systematisch und kundenzentriert. In: Liebl, J (ed.) Experten-Forum Powertrain: Simulation und Test 2019, S. 1–14. Springer Vieweg, Wiesbaden (2019)
2.
Zurück zum Zitat Albers, A., Bursac, N., Rapp, S.: PGE-product generation engineering by the example of the dual mass flywheel. Eng. Res. 81(1), 13–31 (2017) Albers, A., Bursac, N., Rapp, S.: PGE-product generation engineering by the example of the dual mass flywheel. Eng. Res. 81(1), 13–31 (2017)
3.
Zurück zum Zitat Schuchter, F., Bause, K., Albers, A.: Artificial intelligence in hybrid vehicle transmission control-literature review and research methodology. In: 2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC), S. 303–307. IEEE, Rome (2021) Schuchter, F., Bause, K., Albers, A.: Artificial intelligence in hybrid vehicle transmission control-literature review and research methodology. In: 2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC), S. 303–307. IEEE, Rome (2021)
4.
Zurück zum Zitat Russell, S., Norvig, P.: Artificial intelligence: a modern approach, Vol. 3, S. 944 ff. Pearson, Munich (2012) Russell, S., Norvig, P.: Artificial intelligence: a modern approach, Vol. 3, S. 944 ff. Pearson, Munich (2012)
5.
Zurück zum Zitat Krätschmer, A., Lutchen, R., Reuss, H.: AI-based diagnostic tool for offline evaluation of measurement data on test benches. In: 21th Stuttgart International Symposium, S. 203–214. Springer Vieweg, Wiesbaden (2021) Krätschmer, A., Lutchen, R., Reuss, H.: AI-based diagnostic tool for offline evaluation of measurement data on test benches. In: 21th Stuttgart International Symposium, S. 203–214. Springer Vieweg, Wiesbaden (2021)
6.
Zurück zum Zitat Zhang, X. et al.: New solution supporting efficient vehicle calibration using objective driveability evaluation and AI. In: 21. Internationales Stuttgarter Symposium, S. 278–293. Springer Vieweg, Wiesbaden (2021) Zhang, X. et al.: New solution supporting efficient vehicle calibration using objective driveability evaluation and AI. In: 21. Internationales Stuttgarter Symposium, S. 278–293. Springer Vieweg, Wiesbaden (2021)
7.
Zurück zum Zitat Förster, D., Inderka, R. B., Gauterin, F.: Data-driven identification of characteristic real-driving cycles based on k-Means clustering and mixed-integer optimization. IEEE Trans. Veh. Technol. 69(3), 2398–2410 (2020) Förster, D., Inderka, R. B., Gauterin, F.: Data-driven identification of characteristic real-driving cycles based on k-Means clustering and mixed-integer optimization. IEEE Trans. Veh. Technol. 69(3), 2398–2410 (2020)
8.
Zurück zum Zitat Tewiele, S., Driesch, P., Weber, T., Schramm, D.: Clustering of real BEV driving data with subsequent driving cycle construction using Markov chains. In: AmE 2018 − Automotive meets Electronics; 9th GMM-Symposium, S. 1–6. (2018) Tewiele, S., Driesch, P., Weber, T., Schramm, D.: Clustering of real BEV driving data with subsequent driving cycle construction using Markov chains. In: AmE 2018 − Automotive meets Electronics; 9th GMM-Symposium, S. 1–6. (2018)
9.
Zurück zum Zitat Albers, A., Reiß, N., Bursac, N., Urbanec, J., Ludcke, R.: Situation-appropriate method selection in product development process–empirical study of method application. In: DS 81: Proceedings of NordDesign 2014, S. 550–559. Design Society, Espoo (2014) Albers, A., Reiß, N., Bursac, N., Urbanec, J., Ludcke, R.: Situation-appropriate method selection in product development process–empirical study of method application. In: DS 81: Proceedings of NordDesign 2014, S. 550–559. Design Society, Espoo (2014)
10.
Zurück zum Zitat Ester, M., Kriegel, H., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. kdd (96), 226–231. AAAI, Portland (1996) Ester, M., Kriegel, H., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. kdd (96), 226–231. AAAI, Portland (1996)
11.
Zurück zum Zitat Schubert, E. et al.: DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans Database Syst. (TODS) 42(3), 1–21 (2017) Schubert, E. et al.: DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans Database Syst. (TODS) 42(3), 1–21 (2017)
Metadaten
Titel
Intelligent Data Analytics with Artificial Intelligence for Hybrid Engine Restart
verfasst von
Florian Schuchter
Katharina Bause
Albert Albers
Copyright-Jahr
2022
DOI
https://doi.org/10.1007/978-3-658-37011-4_6

    Premium Partner