Presentation 2012-02-09
Fault Classification Based on Likelihood Profile Feature
Takuya MIKAMI, Masashi ANDO, Jun KOYAMA, Seiji HOTTA, Hisae SHIBUYA, Shunji MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a feature called likelihood profile for classifying fault events of a precision machine. This feature is obtained by extending a conventional feature named likelihood histogram to time sequence one. By experiments with a real-life dataset, it is verified that our feature outperforms conventional ones.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) fault classification / sensor feature / likelihood profile
Paper # PRMU2011-192,SP2011-107
Date of Issue

Conference Information
Committee SP
Conference Date 2012/2/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fault Classification Based on Likelihood Profile Feature
Sub Title (in English)
Keyword(1) fault classification
Keyword(2) sensor feature
Keyword(3) likelihood profile
1st Author's Name Takuya MIKAMI
1st Author's Affiliation Tokyo University of Agriculture and Technology()
2nd Author's Name Masashi ANDO
2nd Author's Affiliation Tokyo University of Agriculture and Technology
3rd Author's Name Jun KOYAMA
3rd Author's Affiliation Tokyo University of Agriculture and Technology
4th Author's Name Seiji HOTTA
4th Author's Affiliation Tokyo University of Agriculture and Technology
5th Author's Name Hisae SHIBUYA
5th Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd.
6th Author's Name Shunji MAEDA
6th Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd.
Date 2012-02-09
Paper # PRMU2011-192,SP2011-107
Volume (vol) vol.111
Number (no) 431
Page pp.pp.-
#Pages 4
Date of Issue