Presentation 2020-06-05
Early detection and prevention of combustion oscillations using a symbolic dynamics/machine learning-based approach
Kazuki Asami, Shinga Masuda, Hiroshi Gotoda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have conducted an experimental study on an early detection and prevention of combustion oscillations in a laboratory-scale gas-turbine model combustor using a symbolic dynamics/machine learning-based approach. The generalized entropy plane consisting of the R?nyi and Tsallis entropies appropriately captures the subtle changes in the combustion state from stable combustion to well-developed combustion oscillations. The feature space of the generalized entropy plane obtained by the support vector machine is useful for detecting a precursor of combustion oscillations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) combustion oscillations / symbolic dynamics / generalized entropy plane / machine learning / support vector machine
Paper # NLP2020-19,CCS2020-9
Date of Issue 2020-05-29 (NLP, CCS)

Conference Information
Committee CCS / NLP
Conference Date 2020/6/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Shonan Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Kiyohisa Natsume(Kyushu Inst. of Tech.)
Vice Chair Tetsuya Asai(Hokkaido Univ.) / Megumi Akai(Hokkaido Univ.) / Takuji Kosaka(Chukyo Univ.)
Secretary Tetsuya Asai(Kanagawa Inst. of Tech.) / Megumi Akai(TDK) / Takuji Kosaka(Kyushu Inst. of Tech.)
Assistant Hidehiro Nakano(Tokyo City Univ.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Kobe Univ.) / Kosuke Sanada(Mie Univ.) / Toshikaza Samura(Yamaguchi Univ.) / Hideyuki Kato(Oita Univ.)

Paper Information
Registration To Technical Committee on Complex Communication Sciences / Technical Committee on Nonlinear Problems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Early detection and prevention of combustion oscillations using a symbolic dynamics/machine learning-based approach
Sub Title (in English)
Keyword(1) combustion oscillations
Keyword(2) symbolic dynamics
Keyword(3) generalized entropy plane
Keyword(4) machine learning
Keyword(5) support vector machine
1st Author's Name Kazuki Asami
1st Author's Affiliation Tokyo University of Science Graduate School(TUS)
2nd Author's Name Shinga Masuda
2nd Author's Affiliation Tokyo University of Science Graduate School(TUS)
3rd Author's Name Hiroshi Gotoda
3rd Author's Affiliation Tokyo University of Science(TUS)
Date 2020-06-05
Paper # NLP2020-19,CCS2020-9
Volume (vol) vol.120
Number (no) NLP-55,CCS-56
Page pp.pp.41-44(NLP), pp.41-44(CCS),
#Pages 4
Date of Issue 2020-05-29 (NLP, CCS)