Machine Learning Based Technology for Reducing Engine Starting Vibration of Hybrid Vehicles

Engine starting vibration of hybrid vehicle with Toyota hybrid system has variations even in the same vehicle, and a large vibration that occurs rarely may cause stress to the passengers. The contribution analysis based on the vibration theory and statistical analysis has been done, but the primary factor of the rare large vibration has not been clarified because the number of factors is enormous. From this background, the authors apply machine learning that can reproduce multivariate and complicated relationships to analysis of variation factors of engine starting vibration. Variations in magnitude of the exciting force such as motor torque for starting the engine and in-cylinder pressure of the engine and timing of these forces are considered as factors of the variations. In addition, there are also nonlinear factors such as backlash of gears as a factor of variations. For the variation factor analysis, it is difficult to measure the physical quantities mentioned above from experiments, because of the high time load of installing measuring sensors and lack of measurement technology for some factors. On the other hand, it is possible to extract many factors related to the magnitude and timing of exciting forces by analyzing the command value of the ECU. Therefore, in this research, analysis data is narrowed down to the ECU command value, and the efficiency of analysis is improved by changing processing method of many data for analysis. In addition, a random forest, which is one type of machine learning, was used to contribution analysis of an enormous number of ECU command values to the engine starting vibration. As a result, new factors were extracted, and the authors calculated the quantitative influence of the factors on the variations of the vibration by analytical model. This result verified the method to reduce variations in vibration by controlling extracted factors by the random forest.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01714245
  • Record Type: Publication
  • Source Agency: SAE International
  • Report/Paper Numbers: 2019-01-1450
  • Files: TRIS, SAE
  • Created Date: Jun 17 2019 12:03PM