Estimation Method of Knocking Sound and In-cylinder Pressure from Engine Radiation Noise by Deep Learning (Third Report)

The deep learning model the authors developed estimates knocking sound pressure and knocking component superimposed on in-cylinder pressure from engine radiation noise measured by a microphone. This model obtains the time frequency mask and frequency response from many pair data of engine radiation noise and in-cylinder pressure. The time frequency mask extracts the knocking sound from engine radiation noise. The frequency response converts the extracted knocking sound into the knocking component superimposed on in-cylinder pressure. The authors propose an improved model to separate the knocking sound from the engine radiated sound in order to evaluate the magnitude of the knocking sound.

• Record URL:
  • https://doi.org/10.11351/jsaeronbun.52.263
• Record URL:
  • https://www.jstage.jst.go.jp/article/jsaeronbun/52/2/52_20214133/_pdf
• 
• Record URL:
  • https://scholar.google.com/scholar_lookup?title=Estimation%20Method%20of%20Knocking%20Sound%20and%20In-cylinder%20Pressure%20from%20Engine%20Radiation%20Noise%20by%20Deep%20Learning%20(Third%20Report)&author=T.%20Kasahara&author=H.%20Watabe&author=T.%20Ikeda&author=H.%20Yoshikoshi&publication_year=2021
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/02878321
• Authors:
  • Kasahara, Taro
  • Watabe, Hikaru
  • Ikeda, Taichi
  • Yoshikoshi, Hiroshi
• Publication Date: 2021-3

Language

• English
• Japanese

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 263-268
• Serial:
  • Transactions of Society of Automotive Engineers of Japan
  • Volume: 52
  • Issue Number: 2
  • Publisher: Society of Automotive Engineers of Japan
  • ISSN: 0287-8321
  • EISSN: 1883-0811
  • Serial URL: https://www.jstage.jst.go.jp/browse/jsaeronbun
• Publication flags:

  Open Access (libre)

Subject/Index Terms

• TRT Terms: Effective sound pressure; Engine cylinders; Engine knock; Estimating; Machine learning; Mathematical models; Noise; Pressure; Spark ignition engines
• Subject Areas: Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01767522
• Record Type: Publication
• Source Agency: Japan Science and Technology Agency (JST)
• Files: TRIS, JSTAGE
• Created Date: Mar 22 2021 10:36AM