Presentation 2021-06-12
A Study on Dual-task VAE with Weibull distribution for RUL estimation and application to Aero-Propulsion System data
Ryosuke Sato, Mitsuhiro Kimura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Remaining Useful Life (RUL) is one of the most important assessment measures in reliability engineering. Although several widely-used public datasets have information on failure times, they do not have information on RUL. As a simple way, we can consider a linear degradation concerning the difference between the future failure time and the current time. However, since it is not always the case that such a linear degradation occurs, then we need to generate complex teacher labels incorporating the detection of changing points in the degradation states. In one of the previous studies, one proposed a failure prediction model that takes into account the degradation states and achieved some improvement in prediction accuracy. However, this model sometimes does not perform well, for example, it cannot be adapted to specific tagging methods. Therefore we propose Dual-task VAE incorporating Weibull distribution as a prediction model which does not depend on the tagging methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) C-MAPSS / dual-task / Long Short-Term Memory (LSTM) / Remaining Usefule Life (RUL) / Variational AutoEncoder(VAE)
Paper # R2021-12
Date of Issue 2021-06-05 (R)

Conference Information
Committee R
Conference Date 2021/6/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online (Zoom)
Topics (in Japanese) (See Japanese page)
Topics (in English) Reliability General
Chair Akira Asato(Fujitsu)
Vice Chair Tadashi Dohi(Hiroshima Univ.)
Secretary Tadashi Dohi(Hosei Univ.)
Assistant Hiroyuki Okamura(Hiroshima Univ.) / Shinji Yokogawa(Univ. of Electro-Comm.)

Paper Information
Registration To Technical Committee on Reliability
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Dual-task VAE with Weibull distribution for RUL estimation and application to Aero-Propulsion System data
Sub Title (in English)
Keyword(1) C-MAPSS
Keyword(2) dual-task
Keyword(3) Long Short-Term Memory (LSTM)
Keyword(4) Remaining Usefule Life (RUL)
Keyword(5) Variational AutoEncoder(VAE)
1st Author's Name Ryosuke Sato
1st Author's Affiliation Hosei University(Hosei Univ.)
2nd Author's Name Mitsuhiro Kimura
2nd Author's Affiliation Hosei University(Hosei Univ.)
Date 2021-06-12
Paper # R2021-12
Volume (vol) vol.121
Number (no) R-64
Page pp.pp.7-12(R),
#Pages 6
Date of Issue 2021-06-05 (R)